Add support for "any other tag" categories in IN BODY

Author: dmsnell

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

@@ -879,6 +879,8 @@ private function step_in_body() {
 		 * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inbody
 		 */
 		switch ( $tag_name ) {
+			case 'ABBR':
+			case 'ACRONYM':
 			case 'APPLET':
 			case 'AREA':
 			case 'BASE':
@@ -945,6 +947,47 @@ private function step_in_body() {
 				throw new WP_HTML_Unsupported_Exception( "Cannot process {$tag_name} element." );
 		}
 
+		if ( ! $this->is_tag_closer() ) {
+			// > Any other start tag.
+			$this->reconstruct_active_formatting_elements();
+			$this->insert_html_element( $this->state->current_token );
+			return true;
+		} else {
+			// > Any other end tag
+			$node = $this->state->stack_of_open_elements->current_node();
+
+			in_body_any_other_end_tag_loop:
+			if ( $tag_name === $node->node_name ) {
+				$this->generate_implied_end_tags( $tag_name );
+				if ( $node !== $this->state->stack_of_open_elements->current_node() ) {
+					// @todo Record parse error: this error doesn't impact parsing.
+				}
+				$pop_count = 0;
+				foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
+					++$pop_count;
+					if ( $node === $item ) {
+						break;
+					}
+				}
+				while ( $pop_count-- > 0 ) {
+					$this->state->stack_of_open_elements->pop();
+				}
+				return true;
+			} elseif ( self::is_special( $node->node_name ) ) {
+				// This is a parse error, ignore the token.
+				return $this->step();
+			}
+			$one_shot = false;
+			foreach ( $this->state->stack_of_open_elements->walk_up() as $item ) {
+				if ( $one_shot ) {
+					$node = $item;
+					goto in_body_any_other_end_tag_loop;
+				}
+
+				$one_shot = true;
+			}
+		}
+
 		$this->last_error = self::ERROR_UNSUPPORTED;
 		throw new WP_HTML_Unsupported_Exception( "Cannot process {$tag_name} element." );
 	}

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

@@ -60,22 +60,6 @@ public function test_get_tag_is_null_once_document_is_finished() {
 		$this->assertNull( $p->get_tag() );
 	}
 
-	/**
-	 * Ensures that if the HTML Processor encounters inputs that it can't properly handle,
-	 * that it stops processing the rest of the document. This prevents data corruption.
-	 *
-	 * @ticket 59167
-	 *
-	 * @covers WP_HTML_Processor::next_tag
-	 */
-	public function test_stops_processing_after_unsupported_elements() {
-		$p = WP_HTML_Processor::create_fragment( '<p><x-not-supported></p><p></p>' );
-		$p->next_tag( 'P' );
-		$this->assertFalse( $p->next_tag(), 'Stepped into a tag after encountering X-NOT-SUPPORTED element when it should have aborted.' );
-		$this->assertNull( $p->get_tag(), "Should have aborted processing, but still reported tag {$p->get_tag()} after properly failing to step into tag." );
-		$this->assertFalse( $p->next_tag( 'P' ), 'Stepped into normal P element after X-NOT-SUPPORTED element when it should have aborted.' );
-	}
-
 	/**
 	 * Ensures that the HTML Processor maintains its internal state through seek calls.
 	 *

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

@@ -216,10 +216,6 @@ public function data_unsupported_elements() {
 			'VIDEO',
 			'WBR',
 			'XMP', // Deprecated, use PRE instead.
-
-			// Made up elements, custom elements.
-			'X-NOT-AN-HTML-ELEMENT',
-			'HUMAN-TIME',
 		);
 
 		$data = array();
@@ -360,6 +356,10 @@ public function data_html_target_with_breadcrumbs() {
 			'H4 inside H2'                          => array( '<h2><span>Major<h4 target>Minor</h3></span>', array( 'HTML', 'BODY', 'H2', 'SPAN', 'H4' ), 1 ),
 			'H5 after unclosed H4 inside H2'        => array( '<h2><span>Major<h4>Minor</span></h3><h5 target>', array( 'HTML', 'BODY', 'H2', 'SPAN', 'H5' ), 1 ),
 			'H5 after H4 inside H2'                 => array( '<h2><span>Major<h4>Minor</h4></span></h3><h5 target>', array( 'HTML', 'BODY', 'H5' ), 1 ),
+
+			// Custom elements.
+			'WP-EMOJI'                              => array( '<div><wp-emoji target></wp-emoji></div>', array( 'HTML', 'BODY', 'DIV', 'WP-EMOJI' ), 1 ),
+			'WP-EMOJI then IMG'                     => array( '<div><wp-emoji></wp-emoji><img target></div>', array( 'HTML', 'BODY', 'DIV', 'IMG' ), 1 ),
 		);
 	}