WAT extractor: do not add <meta itemprop="..." > from body as metadata

- rebase to recent head / master
- unit test: merge methods to verify metadata attributes

Author: sebastian-nagel

src/test/java/org/archive/resource/html/ExtractingParseObserverTest.java

@@ -255,20 +255,6 @@ private void checkLinks(Resource resource, String[][] expectedLinks) {
 		}
 	}
 
-	private void checkExtractHtmlLangAttribute(Resource resource, String... langAttributes)
-			throws JSONException {
-		assertNotNull(resource);
-		assertTrue("Wrong instance type of Resource: " + resource.getClass(), resource instanceof HTMLResource);
-		JSONArray metas = resource.getMetaData().getJSONObject("Head").getJSONArray("Metas");
-		assertNotNull(metas);
-		JSONObject meta = metas.getJSONObject(0);
-		for (int i = 0; i < langAttributes.length; i += 2) {
-			String key = langAttributes[i];
-			assertNotNull(meta.get(key));
-			assertEquals(meta.get(key), langAttributes[i+1]);
-		}
-	}
-
 	public void testLinkExtraction() throws ResourceParseException, IOException {
 		String testFileName = "link-extraction-test.warc";
 		ResourceProducer producer = ProducerUtils.getProducer(getClass().getResource(testFileName).getPath());
@@ -448,11 +434,11 @@ public void testHtmlLanguageAttributeExtraction() throws ResourceParseException,
 		ResourceProducer producer = ProducerUtils.getProducer(getClass().getResource(testFileName).getPath());
 		ResourceFactoryMapper mapper = new ExtractingResourceFactoryMapper();
 		ExtractingResourceProducer extractor = new ExtractingResourceProducer(producer, mapper);
-		checkExtractHtmlLangAttribute(extractor.getNext(), "name", "HTML@/lang", "content", "en");
-		checkExtractHtmlLangAttribute(extractor.getNext(), "name", "HTML@/lang", "content", "zh-CN");
-		checkExtractHtmlLangAttribute(extractor.getNext(), "name", "HTML@/lang", "content", "cs-cz");
-		checkExtractHtmlLangAttribute(extractor.getNext(), "name", "HTML@/lang", "content", "en");
-		checkExtractHtmlLangAttribute(extractor.getNext(), "name", "HTML@/xml:lang", "content", "es-MX");
+		checkExtractedAttributes(extractor.getNext(), "name", "HTML@/lang", "content", "en");
+		checkExtractedAttributes(extractor.getNext(), "name", "HTML@/lang", "content", "zh-CN");
+		checkExtractedAttributes(extractor.getNext(), "name", "HTML@/lang", "content", "cs-cz");
+		checkExtractedAttributes(extractor.getNext(), "name", "HTML@/lang", "content", "en");
+		checkExtractedAttributes(extractor.getNext(), "name", "HTML@/xml:lang", "content", "es-MX");
 	}
 
 	public void testBodyMetaElements() throws ResourceParseException, IOException {