WIP: HTML API: Add support for H1-H6 elements in HTML Processor

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

@@ -106,7 +106,7 @@ public function current_node() {
 	 *
 	 * @see https://html.spec.whatwg.org/#has-an-element-in-the-specific-scope
 	 *
-	 * @param string   $tag_name         Name of tag check.
+	 * @param string   $tag_name         Name of tag check, or the class constant HEADING_ELEMENTS to specify H1-H6.
 	 * @param string[] $termination_list List of elements that terminate the search.
 	 * @return bool Whether the element was found in a specific scope.
 	 */
@@ -116,6 +116,13 @@ public function has_element_in_specific_scope( $tag_name, $termination_list ) {
 				return true;
 			}
 
+			if (
+				self::HEADING_ELEMENTS === $tag_name &&
+				in_array( $node->node_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true )
+			) {
+				return true;
+			}
+
 			switch ( $node->node_name ) {
 				case 'HTML':
 					return false;
@@ -263,13 +270,21 @@ public function pop() {
 	 *
 	 * @see WP_HTML_Open_Elements::pop
 	 *
-	 * @param string $tag_name Name of tag that needs to be popped off of the stack of open elements.
+	 * @param string $tag_name Name of tag that needs to be popped off of the stack of open elements,
+	 *                         or the class constant HEADING_ELEMENTS to specify any of H1-H6.
 	 * @return bool Whether a tag of the given name was found and popped off of the stack of open elements.
 	 */
 	public function pop_until( $tag_name ) {
 		foreach ( $this->walk_up() as $item ) {
 			$this->pop();
 
+			if (
+				self::HEADING_ELEMENTS === $tag_name &&
+				in_array( $item->node_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true )
+			) {
+				return true;
+			}
+
 			if ( $tag_name === $item->node_name ) {
 				return true;
 			}
@@ -429,4 +444,15 @@ public function after_element_pop( $item ) {
 				break;
 		}
 	}
+
+	/**
+	 * Represents the collection of H1-H6 elements.
+	 *
+	 * @since 6.5.0
+	 *
+	 * @see has_element_in_scope()
+	 *
+	 * @var string
+	 */
+	const HEADING_ELEMENTS = 'heading-elements';
 }

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

@@ -102,7 +102,7 @@
  *  - Containers: ADDRESS, BLOCKQUOTE, DETAILS, DIALOG, DIV, FOOTER, HEADER, MAIN, MENU, SPAN, SUMMARY.
  *  - Form elements: BUTTON, FIELDSET, SEARCH.
  *  - Formatting elements: B, BIG, CODE, EM, FONT, I, SMALL, STRIKE, STRONG, TT, U.
- *  - Heading elements: HGROUP.
+ *  - Heading elements: H1, H2, H3, H4, H5, H6, HGROUP.
  *  - Links: A.
  *  - Lists: DL.
  *  - Media elements: FIGCAPTION, FIGURE, IMG.
@@ -697,6 +697,64 @@ private function step_in_body() {
 				$this->state->stack_of_open_elements->pop_until( $tag_name );
 				return true;
 
+			/*
+			 * > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+			 */
+			case '+H1':
+			case '+H2':
+			case '+H3':
+			case '+H4':
+			case '+H5':
+			case '+H6':
+				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+					$this->close_a_p_element();
+				}
+
+				if (
+					in_array(
+						$this->state->stack_of_open_elements->current_node()->node_name,
+						array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
+						true
+					)
+				) {
+					// @TODO: Indicate a parse error once it's possible.
+					$this->state->stack_of_open_elements->pop();
+				}
+
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+			 */
+			case '-H1':
+			case '-H2':
+			case '-H3':
+			case '-H4':
+			case '-H5':
+			case '-H6':
+				if (
+					! $this->state->stack_of_open_elements->has_element_in_scope(
+						WP_HTML_Open_Elements::HEADING_ELEMENTS
+					)
+				) {
+					/*
+					 * This is a parse error; ignore the token.
+					 *
+					 * @TODO: Indicate a parse error once it's possible.
+					 */
+					return $this->step();
+				}
+
+				$this->generate_implied_end_tags();
+
+				if ( $this->state->stack_of_open_elements->current_node()->node_name !== $tag_name ) {
+					// @TODO: Record parse error: this error doesn't impact parsing.
+				}
+
+				$this->state->stack_of_open_elements->pop_until( WP_HTML_Open_Elements::HEADING_ELEMENTS );
+				return true;
+
 			/*
 			 * > An end tag whose tag name is "p"
 			 */

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

@@ -91,8 +91,6 @@ public function test_stops_processing_after_unsupported_elements() {
 	 *
 	 * @covers WP_HTML_Processor::next_tag
 	 * @covers WP_HTML_Processor::seek
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_clear_to_navigate_after_seeking() {
 		$p = WP_HTML_Processor::create_fragment( '<div one><strong></strong></div><p><strong two></strong></p>' );

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

@@ -56,6 +56,12 @@ public function data_single_tag_of_supported_elements() {
 			'FIGURE',
 			'FONT',
 			'FOOTER',
+			'H1',
+			'H2',
+			'H3',
+			'H4',
+			'H5',
+			'H6',
 			'HEADER',
 			'HGROUP',
 			'I',
@@ -142,12 +148,6 @@ public function data_unsupported_elements() {
 			'FORM',
 			'FRAME',
 			'FRAMESET',
-			'H1',
-			'H2',
-			'H3',
-			'H4',
-			'H5',
-			'H6',
 			'HEAD',
 			'HR',
 			'HTML',

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

@@ -120,10 +120,6 @@ public function data_article_container_group() {
 	 * element in scope, that it skips the tag entirely.
 	 *
 	 * @ticket 58961
-	 *
-	 * @since 6.4.0
-	 *
-	 * @throws Exception
 	 */
 	public function test_in_body_skips_unexpected_button_closer() {
 		$p = WP_HTML_Processor::create_fragment( '<div>Test</button></div>' );
@@ -145,10 +141,6 @@ public function test_in_body_skips_unexpected_button_closer() {
 	 * Verifies insertion of a BUTTON element when no existing BUTTON is already in scope.
 	 *
 	 * @ticket 58961
-	 *
-	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_no_button_in_scope() {
 		$p = WP_HTML_Processor::create_fragment( '<div><p>Click the button <button one>here</button>!</p></div><button two>not here</button>' );
@@ -174,8 +166,6 @@ public function test_in_body_button_with_no_button_in_scope() {
 	 * @ticket 58961
 	 *
 	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_button_in_scope_as_parent() {
 		$p = WP_HTML_Processor::create_fragment( '<div><p>Click the button <button one>almost<button two>here</button>!</p></div><button three>not here</button>' );
@@ -209,8 +199,6 @@ public function test_in_body_button_with_button_in_scope_as_parent() {
 	 * @ticket 58961
 	 *
 	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_button_in_scope_as_ancestor() {
 		$p = WP_HTML_Processor::create_fragment( '<div><button one><p>Click the button <span><button two>here</button>!</span></p></div><button three>not here</button>' );
@@ -236,7 +224,39 @@ public function test_in_body_button_with_button_in_scope_as_ancestor() {
 		$this->assertSame( array( 'HTML', 'BODY', 'BUTTON' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting for third button.' );
 	}
 
-	/*
+	/**
+	 * Verifies that H1 through H6 elements close an open P element.
+	 *
+	 * @ticket {TICKET_NUMBER}
+	 *
+	 * @dataProvider data_heading_elements
+	 *
+	 * @param string $tag_name Name of H1 - H6 element under test.
+	 */
+	public function test_heading_element_closes_open_p_tag( $tag_name ) {
+		$p = WP_HTML_Processor::create_fragment( "<p>Open<{$tag_name}>Closed P</{$tag_name}></p>" );
+
+		$p->next_tag( $tag_name );
+		$this->assertSame( array( 'HTML', 'BODY', $tag_name ), $p->get_breadcrumbs() );
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return array[].
+	 */
+	public function data_heading_elements() {
+		return array(
+			array( 'H1' ),
+			array( 'H2' ),
+			array( 'H3' ),
+			array( 'H4' ),
+			array( 'H5' ),
+			array( 'H5' ),
+		);
+	}
+
+	/**
 	 * Verifies that when "in body" and encountering "any other end tag"
 	 * that the HTML processor ignores the end tag if there's a special
 	 * element on the stack of open elements before the matching opening.
@@ -259,7 +279,7 @@ public function test_in_body_any_other_end_tag_with_unclosed_special_element() {
 		$this->assertSame( array( 'HTML', 'BODY', 'DIV', 'SPAN', 'DIV' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting: SPAN should still be open and DIV should be its child.' );
 	}
 
-	/*
+	/**
 	 * Verifies that when "in body" and encountering "any other end tag"
 	 * that the HTML processor closes appropriate elements on the stack of
 	 * open elements up to the matching opening.