Merge pull request #32 from wmde/html

Throw errors from HTML parsing

Author: codders

src/HtmlParser.php

@@ -28,7 +28,7 @@ public function parseHtml( string $html ): DOMDocument {
 		// LIBXML_NOBLANKS Constant excludes "ghost nodes" to avoid violating
 		// vue's single root node constraint
 		if ( !$document->loadHTML( '<?xml encoding="utf-8" ?>' . $html, LIBXML_NOBLANKS ) ) {
-			//TODO Test failure
+			throw new Exception( 'Failed to parse HTML' );
 		}
 
 		/** @var LibXMLError[] $errors */
@@ -41,9 +41,15 @@ public function parseHtml( string $html ): DOMDocument {
 			libxml_disable_entity_loader( $entityLoaderDisabled );
 		}
 
+		$exception = null;
 		foreach ( $errors as $error ) {
-			//TODO html5 tags can fail parsing
-			//TODO Throw an exception
+			if ( strpos( $error->message, 'Tag template invalid' ) === 0 ) {
+				continue;
+			}
+			$exception = new Exception( $error->message, $error->code, $exception );
+		}
+		if ( $exception !== null ) {
+			throw $exception;
 		}
 
 		return $document;

tests/php/HtmlParserTest.php

@@ -63,4 +63,11 @@ public function testTwoRootNodes() {
 		$this->parseAndGetRootNode( '<p></p><p></p>' );
 	}
 
+	public function testMalformedHtml(): void {
+		$htmlParser = new HtmlParser();
+		$this->expectException( Exception::class );
+		$this->expectExceptionMessage( 'Unexpected end tag' );
+		$htmlParser->parseHtml( '</p>' );
+	}
+
 }