Add some support for adoption agency algorithm

Author: dmsnell

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

@@ -1553,12 +1553,7 @@ private function run_adoption_agency_algorithm() {
 			return;
 		}
 
-		$outer_loop_counter = 0;
-		while ( $budget-- > 0 ) {
-			if ( $outer_loop_counter++ >= 8 ) {
-				return;
-			}
-
+		for ( $outer_loop_counter = 0; $outer_loop_counter < 8; $outer_loop_counter++ ) {
 			/*
 			 * > Let formatting element be the last element in the list of active formatting elements that:
 			 * >   - is between the end of the list and the last marker in the list,
@@ -1579,8 +1574,35 @@ private function run_adoption_agency_algorithm() {
 
 			// > If there is no such element, then return and instead act as described in the "any other end tag" entry above.
 			if ( null === $formatting_element ) {
-				$this->last_error = self::ERROR_UNSUPPORTED;
-				throw new WP_HTML_Unsupported_Exception( 'Cannot run adoption agency when "any other end tag" is required.' );
+				/*
+				 * > Any other end tag
+				 */
+
+				/*
+				 * Find the corresponding tag opener in the stack of open elements, if
+				 * it exists before reaching a special element, which provides a kind
+				 * of boundary in the stack. For example, a `</custom-tag>` should not
+				 * close anything beyond its containing `P` or `DIV` element.
+				 */
+				foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) {
+					if ( $subject === $node->node_name ) {
+						break;
+					}
+
+					if ( self::is_special( $node->node_name ) ) {
+						// This is a parse error, ignore the token.
+						return;
+					}
+				}
+
+				$this->generate_implied_end_tags( $subject );
+
+				foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
+					$this->state->stack_of_open_elements->pop();
+					if ( $node === $item ) {
+						return;
+					}
+				}
 			}
 
 			// > If formatting element is not in the stack of open elements, then this is a parse error; remove the element from the list, and return.
@@ -1594,14 +1616,18 @@ private function run_adoption_agency_algorithm() {
 				return;
 			}
 
+			/*
+			 * > If formatting element is not the current node, this is a parse error. (But do not return.)
+			 */
+
 			/*
 			 * > Let furthest block be the topmost node in the stack of open elements that is lower in the stack
 			 * > than formatting element, and is an element in the special category. There might not be one.
 			 */
 			$is_above_formatting_element = true;
 			$furthest_block              = null;
 			foreach ( $this->state->stack_of_open_elements->walk_down() as $item ) {
-				if ( $is_above_formatting_element && $formatting_element->bookmark_name !== $item->bookmark_name ) {
+				if ( $is_above_formatting_element && $formatting_element !== $item ) {
 					continue;
 				}
 
@@ -1625,19 +1651,87 @@ private function run_adoption_agency_algorithm() {
 				foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
 					$this->state->stack_of_open_elements->pop();
 
-					if ( $formatting_element->bookmark_name === $item->bookmark_name ) {
+					if ( $formatting_element === $item ) {
 						$this->state->active_formatting_elements->remove_node( $formatting_element );
 						return;
 					}
 				}
 			}
 
+			/*
+			 * > Let common ancestor be the element immediately above formatting element in the stack of open elements.
+			 */
+			$common_ancestor = null;
+			foreach ( $this->state->stack_of_open_elements->walk_up( $formatting_element ) as $item ) {
+				$common_ancestor = $item;
+				break;
+			}
+
+			/*
+			 * Let a bookmark note the position of formatting element in the list of active formatting elements relative to the elements on either side of it in the list.
+			 */
+			$formatting_element_index = 0;
+			foreach ( $this->state->active_formatting_elements->walk_down() as $item ) {
+				if ( $formatting_element === $item ) {
+					break;
+				}
+
+				++$formatting_element_index;
+			}
+
+			/*
+			 * > Let node and last node be furthest block.
+			 */
+			$node      = $furthest_block;
+			$last_node = $furthest_block;
+
+			$inner_loop_counter = 0;
+			while ( $budget-- > 0 ) {
+				++$inner_loop_counter;
+
+				if ( $this->state->stack_of_open_elements->contains_node( $node ) ) {
+					foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
+						$node = $item;
+						break;
+					}
+				} else {
+					$this->last_error = self::ERROR_UNSUPPORTED;
+					throw new WP_HTML_Unsupported_Exception( 'Cannot adjust node pointer above removed node.' );
+				}
+
+				if ( $formatting_element === $node ) {
+					break;
+				}
+
+				if ( $inner_loop_counter > 3 && $this->state->active_formatting_elements->contains_node( $node ) ) {
+					$this->state->active_formatting_elements->remove_node( $node );
+				}
+
+				if ( ! $this->state->active_formatting_elements->contains_node( $node ) ) {
+					$this->state->stack_of_open_elements->remove_node( $node );
+					continue;
+				}
+
+				/*
+				 * > Create an element for the token for which the element node was created,
+				 * in the HTML namespace, with common ancestor as the intended parent;
+				 * replace the entry for node in the list of active formatting elements
+				 * with an entry for the new element, replace the entry for node in the
+				 * stack of open elements with an entry for the new element, and let node
+				 * be the new element.
+				 */
+				$this->last_error = self::ERROR_UNSUPPORTED;
+				throw new WP_HTML_Unsupported_Exception( 'Cannot create and reference new element for which no token exists.' );
+			}
+
+			/*
+			 * > Insert whatever last node ended up being in the previous step at the appropriate
+			 * > palce for inserting a node, but using common ancestor as the override target.
+			 */
+
 			$this->last_error = self::ERROR_UNSUPPORTED;
-			throw new WP_HTML_Unsupported_Exception( 'Cannot extract common ancestor in adoption agency algorithm.' );
+			throw new WP_HTML_Unsupported_Exception( 'Cannot create and reference new element for which no token exists.' );
 		}
-
-		$this->last_error = self::ERROR_UNSUPPORTED;
-		throw new WP_HTML_Unsupported_Exception( 'Cannot run adoption agency when looping required.' );
 	}
 
 	/**

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

@@ -125,11 +125,16 @@ public function test_clear_to_navigate_after_seeking() {
 	 *
 	 * @covers WP_HTML_Processor::reconstruct_active_formatting_elements
 	 */
-	public function test_fails_to_reconstruct_formatting_elements() {
+	public function test_reconstructs_formatting_elements() {
 		$p = WP_HTML_Processor::create_fragment( '<p><em>One<p><em>Two<p><em>Three<p><em>Four' );
 
 		$this->assertTrue( $p->next_tag( 'EM' ), 'Could not find first EM.' );
-		$this->assertFalse( $p->next_tag( 'EM' ), 'Should have aborted before finding second EM as it required reconstructing the first EM.' );
+		$this->assertTrue( $p->next_tag( 'EM' ), 'Should have found second EM.' );
+		$this->assertSame(
+			array( 'HTML', 'BODY', 'P', 'EM', 'EM' ),
+			$p->get_breadcrumbs(),
+			'Should have reconstructed the previous EM before finding the second.'
+		);
 	}
 
 	/**

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

@@ -251,11 +251,6 @@ public function test_fails_when_encountering_unsupported_markup( $html, $descrip
 	 */
 	public function data_unsupported_markup() {
 		return array(
-			'A with formatting following unclosed A' => array(
-				'<a><strong>Click <a supported><big unsupported>Here</big></a></strong></a>',
-				'Unclosed formatting requires complicated reconstruction.',
-			),
-
 			'A after unclosed A inside DIV'          => array(
 				'<a><div supported><a unsupported></div></a>',
 				'A is a formatting element, which requires more complicated reconstruction.',
@@ -340,6 +335,13 @@ public function data_html_target_with_breadcrumbs() {
 			'P after closed P'                      => array( '<p><i>something</i></p><p target>This one</p>', array( 'HTML', 'BODY', 'P' ), 2 ),
 			'A after unclosed A'                    => array( '<a><a target>', array( 'HTML', 'BODY', 'A' ), 2 ),
 			'A after unclosed A, after a P'         => array( '<p><a><a target>', array( 'HTML', 'BODY', 'P', 'A' ), 2 ),
+
+			'A with formatting following unclosed A' => array(
+				'<a><strong>Click <a><big target>Here</big></a></strong></a>',
+				array( 'HTML', 'BODY', 'STRONG', 'A', 'BIG' ),
+				1
+			),
+
 			// This one adds a test at a deep stack depth to ensure things work for situations beyond short test docs.
 			'Large HTML document with deep P'       => array(
 				'<div><div><div><div><div><div><div><div><p></p><p></p><p><div><strong><em><code></code></em></strong></div></p></div></div></div></div></div></div></div></div><div><div><div><div><div><div><div><div><p></p><p></p><p><div><strong><em><code target></code></em></strong></div></p></div></div></div></div></div></div></div></div>',