Merge branch 'html-api/add-spawn-fragment-parser-method' into block-bindings/html-api-private-set-inner-html

Author: sirreal

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

@@ -428,13 +428,35 @@ function ( WP_HTML_Token $token ): void {
 	 * Creates a fragment processor at the current node.
 	 *
 	 * HTML Fragment parsing always happens with a context node. HTML Fragment Processors can be
-	 * instantiated with a `BODY` context node via `WP_HTML_Processor::create_fragment()`.
+	 * instantiated with a `BODY` context node via `WP_HTML_Processor::create_fragment( $html )`.
 	 *
-	 * The context node may impact how a fragment of HTML is parsed. For example, when parsing
-	 * `<rect />A</rect>B`:
+	 * The context node may impact how a fragment of HTML is parsed. For example, consider the HTML
+	 * fragment `<td />Inside TD?</td>`.
 	 *
 	 * With a BODY context node results in the following tree:
 	 *
+	 *     └─#text Inside TD?
+	 *
+	 * Notice that the `<td>` tags are completely ignored.
+	 *
+	 * Compare that with an SVG context node that produces the following tree:
+	 *
+	 *     ├─svg:td
+	 *     └─#text Inside TD?
+	 *
+	 * Here, a `td` node in the `svg` namespace is created, and its self-closing flag is respected.
+	 * This is a peculiarity of parsing HTML in foreign content like SVG.
+	 *
+	 * Finally, consider the tree produced with a TABLE context node:
+	 *
+	 *     └─TBODY
+	 *       └─TR
+	 *         └─TD
+	 *           └─#text Inside TD?
+	 *
+	 * These examples demonstrate how important the context node may be when processing an HTML
+	 * fragment. Special care must be taken when processing fragments that are expected to appear
+	 * in specific contexts. SVG and TABLE are good examples, but there are others.
 	 *
 	 * @see https://html.spec.whatwg.org/multipage/parsing.html#html-fragment-parsing-algorithm
 	 *
@@ -462,6 +484,9 @@ public function create_fragment_at_current_node( string $html ) {
 		}
 
 		$fragment_processor = static::create_fragment( $html );
+		if ( null === $fragment_processor ) {
+			return null;
+		}
 
 		$fragment_processor->change_parsing_namespace(
 			$this->current_element->token->integration_node_type ? 'html' : $namespace
@@ -494,7 +519,9 @@ public function create_fragment_at_current_node( string $html ) {
 		 */
 		foreach ( $this->state->stack_of_open_elements->walk_up() as $element ) {
 			if ( 'FORM' === $element->node_name && 'html' === $element->namespace ) {
-				$fragment_processor->state->form_element = $element;
+				$fragment_processor->state->form_element                = clone $element;
+				$fragment_processor->state->form_element->bookmark_name = null;
+				$fragment_processor->state->form_element->on_destroy    = null;
 				break;
 			}
 		}

tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

@@ -213,7 +213,7 @@ private static function build_tree_representation( ?string $fragment_context, st
 				if ( null !== $parent_processor->get_last_error() ) {
 					throw new Exception( $parent_processor->get_last_error() );
 				}
-				$processor = $parent_processor->spawn_fragment_parser( $html );
+				$processor = $parent_processor->create_fragment_at_current_node( $html );
 			}
 
 			if ( null === $processor ) {
@@ -226,11 +226,6 @@ private static function build_tree_representation( ?string $fragment_context, st
 			}
 		}
 
-		/*
-		 * The fragment parser will start in 2 levels deep at: html > body > [position]
-		 * and requires adjustment to initial parameters.
-		 * The full parser will not.
-		 */
 		$output       = '';
 		$indent_level = 0;
 		$was_text     = null;