HTML API: Improve implementation of adoption agency algorithm

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

@@ -622,12 +622,23 @@ public function remove_node( WP_HTML_Token $token ): bool {
 	 * see WP_HTML_Open_Elements::walk_up().
 	 *
 	 * @since 6.4.0
+	 * @since 6.7.0 Accepts $below_this_node to start traversal below a given node, if it exists.
+	 *
+	 * @param ?WP_HTML_Token $below_this_node Start traversing below this node, if provided and if the node exists.
 	 */
-	public function walk_down() {
-		$count = count( $this->stack );
+	public function walk_down( $below_this_node = null ) {
+		$has_found_node = null === $below_this_node;
+		$count          = count( $this->stack );
 
 		for ( $i = 0; $i < $count; $i++ ) {
-			yield $this->stack[ $i ];
+			$node = $this->stack[ $i ];
+
+			if ( ! $has_found_node ) {
+				$has_found_node = $node === $below_this_node;
+				continue;
+			}
+
+			yield $node;
 		}
 	}
 

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

@@ -2360,7 +2360,9 @@ private function step_in_body(): bool {
 							break;
 
 						case 'A':
-							$this->run_adoption_agency_algorithm();
+							if ( 'ignore' === $this->run_adoption_agency_algorithm() ) {
+								$this->bail( 'Cannot ignore token after running adoption agency algorithm.' );
+							}
 							$this->state->active_formatting_elements->remove_node( $item );
 							$this->state->stack_of_open_elements->remove_node( $item );
 							break;
@@ -2401,7 +2403,9 @@ private function step_in_body(): bool {
 
 				if ( $this->state->stack_of_open_elements->has_element_in_scope( 'NOBR' ) ) {
 					// Parse error.
-					$this->run_adoption_agency_algorithm();
+					if ( 'ignore' === $this->run_adoption_agency_algorithm() ) {
+						$this->bail( 'Cannot ignore token after running adoption agency algorithm.' );
+					}
 					$this->reconstruct_active_formatting_elements();
 				}
 
@@ -2426,7 +2430,9 @@ private function step_in_body(): bool {
 			case '-STRONG':
 			case '-TT':
 			case '-U':
-				$this->run_adoption_agency_algorithm();
+				if ( 'ignore' === $this->run_adoption_agency_algorithm() ) {
+					$this->bail( 'Cannot ignore token after running adoption agency algorithm.' );
+				}
 				return true;
 
 			/*
@@ -5312,32 +5318,31 @@ public function reset_insertion_mode(): void {
 	 *
 	 * @see https://html.spec.whatwg.org/#adoption-agency-algorithm
 	 */
-	private function run_adoption_agency_algorithm(): void {
+	private function run_adoption_agency_algorithm(): ?string {
 		$budget       = 1000;
 		$subject      = $this->get_tag();
 		$current_node = $this->state->stack_of_open_elements->current_node();
 
+		/*
+		 * > 2. If the current node is an HTML element whose tag name is subject,
+		 * >    and the current node is not in the list of active formatting elements,
+		 * >    then pop the current node off the stack of open elements and return.
+		 */
 		if (
-			// > If the current node is an HTML element whose tag name is subject
-			$current_node && $subject === $current_node->node_name &&
-			// > the current node is not in the list of active formatting elements
+			'html' === $current_node->namespace &&
+			$subject === $current_node->node_name &&
 			! $this->state->active_formatting_elements->contains_node( $current_node )
 		) {
 			$this->state->stack_of_open_elements->pop();
-			return;
+			return null;
 		}
 
-		$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,
-			 * >     if any, or the start of the list otherwise,
-			 * >   - and has the tag name subject.
+			 * > 3. 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,
+			 * >        if any, or the start of the list otherwise,
+			 * >      - and has the tag name subject.
 			 */
 			$formatting_element = null;
 			foreach ( $this->state->active_formatting_elements->walk_up() as $item ) {
@@ -5351,64 +5356,216 @@ private function run_adoption_agency_algorithm(): void {
 				}
 			}
 
-			// > If there is no such element, then return and instead act as described in the "any other end tag" entry above.
+			/*
+			 * > 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->bail( 'Cannot run adoption agency when "any other end tag" is required.' );
+				/*
+				 * These steps are copied here from above. This may remove the node
+				 * or ignore it, meaning the following code must respect that.
+				 */
+				foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) {
+					if ( 'html' === $node->namespace && $subject === $node->node_name ) {
+						break;
+					}
+
+					if ( self::is_special( $node ) ) {
+						return 'ignore';
+					}
+				}
+
+				$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 null;
+					}
+				}
 			}
 
-			// > 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.
+			/*
+			 * > 4. 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.
+			 */
 			if ( ! $this->state->stack_of_open_elements->contains_node( $formatting_element ) ) {
 				$this->state->active_formatting_elements->remove_node( $formatting_element );
-				return;
+				return null;
 			}
 
-			// > If formatting element is in the stack of open elements, but the element is not in scope, then this is a parse error; return.
+			/*
+			 * > 5. If formatting element is in the stack of open elements, but the element
+			 * >    is not in scope, then this is a parse error; return.
+			 */
 			if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $formatting_element->node_name ) ) {
-				return;
+				return null;
 			}
 
 			/*
-			 * > 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.
+			 * > 6. If formatting element is not the current node, this is a parse error. (But do not return.)
 			 */
-			$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 ) {
-					continue;
-				}
-
-				if ( $is_above_formatting_element ) {
-					$is_above_formatting_element = false;
-					continue;
-				}
 
+			/*
+			 * > 7. 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.
+			 */
+			$furthest_block = null;
+			foreach ( $this->state->stack_of_open_elements->walk_down( $formatting_element ) as $item ) {
 				if ( self::is_special( $item ) ) {
 					$furthest_block = $item;
 					break;
 				}
 			}
 
 			/*
-			 * > If there is no furthest block, then the UA must first pop all the nodes from the bottom of the
-			 * > stack of open elements, from the current node up to and including formatting element, then
-			 * > remove formatting element from the list of active formatting elements, and finally return.
+			 * > 8. If there is no furthest block, then the UA must first pop all the nodes from the bottom of
+			 * >    the stack of open elements, from the current node up to and including formatting element,
+			 * >    then remove formatting element from the list of active formatting elements, and finally return.
 			 */
 			if ( null === $furthest_block ) {
 				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;
+						return null;
 					}
 				}
 			}
 
-			$this->bail( 'Cannot extract common ancestor in adoption agency algorithm.' );
-		}
+			/*
+			 * > 9. 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;
+			}
+
+			/*
+			 * > 10. 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;
+			}
+
+			/*
+			 * > 11. Let node and last node be furthest block.
+			 */
+			$node      = $furthest_block;
+			$last_node = $furthest_block;
+
+			$inner_loop_counter = 0;
+			while ( $budget-- > 0 ) {
+				/*
+				 * > 1. Increment innerLoopCounter by 1.
+				 */
+				++$inner_loop_counter;
 
-		$this->bail( 'Cannot run adoption agency when looping required.' );
+				/*
+				 * > 2. Let node be the element immediately above node in the stack of open elements,
+				 * >    or if node is no longer in the stack of open elements (e.g. because it got
+				 * >    removed by this algorithm), the element that was immediately above node in
+				 * >    the stack of open elements before node was removed.
+				 */
+				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->bail( 'Cannot adjust node pointer above removed node.' );
+				}
+
+				/*
+				 * > 3. If node is formattingElement, the break.
+				 */
+				if ( $formatting_element === $node ) {
+					break;
+				}
+
+				/*
+				 * > 4. If innerLoopCounter is greater than 3 and node is in the list of active formatting
+				 * >    elements, then remove node from the list of active formatting elements.
+				 */
+				if ( $inner_loop_counter > 3 && $this->state->active_formatting_elements->contains_node( $node ) ) {
+					$this->state->active_formatting_elements->remove_node( $node );
+				}
+
+				/*
+				 * > 5. If node is not in the list of active formatting elements, then remove node from
+				 * >    the stack of open elements and continue.
+				 */
+				if ( ! $this->state->active_formatting_elements->contains_node( $node ) ) {
+					$this->state->stack_of_open_elements->remove_node( $node );
+					continue;
+				}
+
+				/*
+				 * > 6. 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->bail( 'Cannot create and reference new element for which no token exists.' );
+
+				/*
+				 * > 7. If last node is furthestBlock, then move the aforementioned bookmark to
+				 * >    be immediately after the new node in the list of active formatting elements.
+				 */
+
+				/*
+				 * > 8. Append lastNode to node.
+				 */
+
+				/*
+				 * > 9. Set lastNode to node.
+				 */
+				$last_node = $node;
+			}
+
+			/*
+			 * > 14. Insert whatever last node ended up being in the previous step at the appropriate
+			 * >     place for inserting a node, but using common ancestor as the override target.
+			 */
+			$this->bail( 'Cannot create and reference new element for which no token exists.' );
+
+			/*
+			 * > 15. Create an element for the token for which formattingElement was created,
+			 * >     in the HTML namespace, with furthestBlock as the intended parent.
+			 */
+
+			/*
+			 * > 16. Take all of the child nodes of furthestBlock and append them to the element
+			 * >     created in the last step.
+			 */
+
+			/*
+			 * > 17. Append that new element to furthestBlock.
+			 */
+
+			/*
+			 * > 18. Remove formattingElement from the list of active formatting elements,
+			 * >     and insert the new element into the list of active formatting elements
+			 * >     at the position of the aforementioned bookmark.
+			 */
+
+			/*
+			 * > 19. Remove formattingElement from the stack of open elements, and insert the
+			 * >     new element into the stack of open elements immediately below the position
+			 * >     of furthestBlock in that stack.
+			 */
+		}
 	}
 
 	/**