Fix for keeping lists structure

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;
 import org.chromium.distiller.proto.DomDistillerProtos.TimingEntry;
 import org.chromium.distiller.proto.DomDistillerProtos.TimingInfo;
 import org.chromium.distiller.webdocument.DomConverter;
 import org.chromium.distiller.webdocument.WebDocument;
 import org.chromium.distiller.webdocument.WebDocumentBuilder;
 import org.chromium.distiller.webdocument.WebImage;
 import org.chromium.distiller.webdocument.filters.RelevantElements;
 import org.chromium.distiller.webdocument.filters.LeadImageFinder;
+import org.chromium.distiller.webdocument.filters.NestedElementRetainer;
 
 import com.google.gwt.dom.client.Document;
 import com.google.gwt.dom.client.Element;
 import com.google.gwt.dom.client.Node;
 import com.google.gwt.dom.client.NodeList;
 
 import java.util.ArrayList;
 import java.util.LinkedList;
 import java.util.List;
 import java.util.Set;
@@ skipping 57 matching lines @@
 
     public String extractContent(boolean textOnly) {
         double 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();
         for (WebImage wi : images) {
             imageUrls.add(wi.getSrc());
         }
         mTimingInfo.setArticleProcessingTime(DomUtil.getTime() - now);
 
         now = DomUtil.getTime();
         String html = documentInfo.document.generateOutput(textOnly);
         mTimingInfo.setFormattingTime(DomUtil.getTime() - now);
@@ skipping 100 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();
     }
 }