Add support for Schema.org/Recipe

java/org/chromium/distiller/ContentExtractor.java

 // Copyright 2014 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 package org.chromium.distiller;
 
 import org.chromium.distiller.document.TextDocument;
 import org.chromium.distiller.document.TextDocumentStatistics;
 import org.chromium.distiller.extractors.ArticleExtractor;
 import org.chromium.distiller.proto.DomDistillerProtos.StatisticsInfo;
@@ skipping 68 matching lines @@
         ensureTitleInitialized();
         assert candidateTitles.size() > 0;
         return candidateTitles.get(0);
     }
 
     public String extractContent() {
         return extractContent(false);
     }
 
     public String extractContent(boolean textOnly) {
+

[wychen, 2016/07/24 23:06:34]

nit: extra line

         double now = DomUtil.getTime();
+        String structuredData = parser.getStructuredData();
+        LogUtil.addTimingInfo(now, mTimingInfo, "parser.getStructuredData()");

[wychen, 2016/07/24 23:06:33]

Maybe just "getStructuredData" for consistency.

+        if (!structuredData.isEmpty()) {
+            return structuredData;
+        }
+        now = DomUtil.getTime();
         WebDocumentInfo documentInfo = createWebDocumentInfoFromPage();
         mTimingInfo.setDocumentConstructionTime(DomUtil.getTime() - now);
 
         now = DomUtil.getTime();
         processDocument(documentInfo.document);
         RelevantElements.process(documentInfo.document);
         LeadImageFinder.process(documentInfo.document);
         NestedElementRetainer.process(documentInfo.document);
 
         List<WebImage> images = documentInfo.document.getContentImages();
@@ skipping 86 matching lines @@
      *
      * @param document the WebDocument representation of the page extracted from the DOM.
      */
     private void processDocument(WebDocument document) {
         TextDocument textDocument = document.createTextDocumentView();
         ArticleExtractor.INSTANCE.process(textDocument, candidateTitles);
         mStatisticsInfo.setWordCount(TextDocumentStatistics.countWordsInContent(textDocument));
         textDocument.applyToModel();
     }
 }