Add "area", "br", "embed", "img", "keygen", "wbr" tag rules

Author: sirreal

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

@@ -925,12 +925,29 @@ private function step_in_body() {
 				$this->run_adoption_agency_algorithm();
 				return true;
 
+
+			/*
+			 * > An end tag whose tag name is "br"
+			 * >   Parse error. Drop the attributes from the token, and act as described in the next
+			 * >   entry; i.e. act as if this was a "br" start tag token with no attributes, rather
+			 * >   than the end tag token that it actually is.
+			 */
+			case '-BR':
+				$this->last_error = self::ERROR_UNSUPPORTED;
+				throw new WP_HTML_Unsupported_Exception( "Closing BR tags require unimplemented special handling." );
+
 			/*
 			 * > A start tag whose tag name is one of: "area", "br", "embed", "img", "keygen", "wbr"
 			 */
+			case '+AREA':
+			case '+BR':
+			case '+EMBED':
 			case '+IMG':
+			case '+KEYGEN':
+			case '+WBR':
 				$this->reconstruct_active_formatting_elements();
 				$this->insert_html_element( $this->state->current_token );
+				$this->state->frameset_ok = false;
 				return true;
 		}
 
@@ -957,13 +974,11 @@ private function step_in_body() {
 			case 'BASEFONT':
 			case 'BGSOUND':
 			case 'BODY':
-			case 'BR':
 			case 'CAPTION':
 			case 'COL':
 			case 'COLGROUP':
 			case 'DD':
 			case 'DT':
-			case 'EMBED':
 			case 'FORM':
 			case 'FRAME':
 			case 'FRAMESET':
@@ -972,7 +987,6 @@ private function step_in_body() {
 			case 'HTML':
 			case 'IFRAME':
 			case 'INPUT':
-			case 'KEYGEN':
 			case 'LI':
 			case 'LINK':
 			case 'LISTING':
@@ -1012,7 +1026,6 @@ private function step_in_body() {
 			case 'TR':
 			case 'TRACK':
 			case 'UL':
-			case 'WBR':
 			case 'XMP':
 				$this->last_error = self::ERROR_UNSUPPORTED;
 				throw new WP_HTML_Unsupported_Exception( "Cannot process {$tag_name} element." );

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

@@ -159,16 +159,13 @@ public function test_step_in_body_fails_on_unsupported_tags( $tag_name ) {
 	public function data_unsupported_special_in_body_tags() {
 		return array(
 			'APPLET'    => array( 'APPLET' ),
-			'AREA'      => array( 'AREA' ),
 			'BASE'      => array( 'BASE' ),
 			'BASEFONT'  => array( 'BASEFONT' ),
 			'BGSOUND'   => array( 'BGSOUND' ),
 			'BODY'      => array( 'BODY' ),
-			'BR'        => array( 'BR' ),
 			'CAPTION'   => array( 'CAPTION' ),
 			'COL'       => array( 'COL' ),
 			'COLGROUP'  => array( 'COLGROUP' ),
-			'EMBED'     => array( 'EMBED' ),
 			'FORM'      => array( 'FORM' ),
 			'FRAME'     => array( 'FRAME' ),
 			'FRAMESET'  => array( 'FRAMESET' ),
@@ -177,7 +174,6 @@ public function data_unsupported_special_in_body_tags() {
 			'HTML'      => array( 'HTML' ),
 			'IFRAME'    => array( 'IFRAME' ),
 			'INPUT'     => array( 'INPUT' ),
-			'KEYGEN'    => array( 'KEYGEN' ),
 			'LINK'      => array( 'LINK' ),
 			'LISTING'   => array( 'LISTING' ),
 			'MARQUEE'   => array( 'MARQUEE' ),
@@ -214,7 +210,6 @@ public function data_unsupported_special_in_body_tags() {
 			'TITLE'     => array( 'TITLE' ),
 			'TR'        => array( 'TR' ),
 			'TRACK'     => array( 'TRACK' ),
-			'WBR'       => array( 'WBR' ),
 			'XMP'       => array( 'XMP' ),
 		);
 	}

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

@@ -376,4 +376,33 @@ public function test_in_body_any_other_end_tag_with_unclosed_non_special_element
 		$this->assertSame( 'DIV', $p->get_tag(), "Expected to find DIV element, but found {$p->get_tag()} instead." );
 		$this->assertSame( array( 'HTML', 'BODY', 'DIV', 'DIV' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting: SPAN should be closed and DIV should be its sibling.' );
 	}
+
+	/**
+	 * Verifies that when "in body" and encountering a br close tag `</br …>`:
+	 *
+	 * > An end tag whose tag name is "br"
+	 * >   Parse error. Drop the attributes from the token, and act as described in the next entry;
+	 * >   i.e. act as if this was a "br" start tag token with no attributes, rather than the end
+	 * >   tag token that it actually is.
+	 *
+	 * @covers WP_HTML_Processor::step_in_body
+	 *
+	 * @ticket 58907
+	 *
+	 * @since 6.4.0
+	 */
+	public function test_br_close_tag_special_behavior() {
+		$this->markTestIncomplete( 'BR end tag special handling is unimplemented' );
+
+		$p = WP_HTML_Processor::create_fragment( '</br attribute="must be removed">' );
+
+		$this->assertTrue( $p->next_tag( 'BR' ), 'No BR tag found.' );
+		$this->assertNull( $p->get_attribute_names_with_prefix( '' ), 'BR end tag had attributes.' );
+		$this->assertFalse( $p->is_tag_closer(), '</br> is treated as a BR start tag.' );
+
+		$this->assertFalse( $p->set_attribute( 'new-attribute', 'added' ), 'BR end tag becomes an opener' );
+		$this->assertCount( 1, $p->get_attribute_names_with_prefix( '' ), 'Tag should have 1 attribute.' );
+		$this->assertSame( 'added', $p->get_attribute( 'new-attribute' ), 'Tag did not set attribute value correctly.' );
+		$this->assertSame( '<br new-attribute="added">', $p->get_updated_html(), 'Tag HTML was not updated correctly.' );
+	}
 }