Strip unwanted classNames from all nodes

java/org/chromium/distiller/webdocument/WebText.java

 // Copyright 2015 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.webdocument;
 
 import com.google.gwt.dom.client.Document;
 import com.google.gwt.dom.client.Element;
 import org.chromium.distiller.DomUtil;
 import org.chromium.distiller.TreeCloneBuilder;
@@ skipping 115 matching lines @@
             if ("BODY".equals(Element.as(srcRoot).getTagName())) break;
             Node parentClone = srcRoot.cloneNode(false);
             parentClone.appendChild(clonedRoot);
             clonedRoot = parentClone;
         }
 
         // Make sure links are absolute and IDs are gone.
         DomUtil.makeAllLinksAbsolute(clonedRoot);
         DomUtil.stripTargetAttributes(clonedRoot);
         DomUtil.stripIds(clonedRoot);
+        DomUtil.stripUnwantedClassNames(clonedRoot);
         DomUtil.stripFontColorAttributes(clonedRoot);
         DomUtil.stripStyleAttributes(clonedRoot);
         // TODO(wychen): if we allow images in WebText later, add stripImageElements().
 
         // Since there are tag elements that are being wrapped
         // by a pair of {@link WebTag}s, we only need to
         // get the innerHTML, otherwise these tags would be duplicated.
         Element elementClonedRoot = Element.as(clonedRoot);
         if (textOnly) {
             return DomUtil.getInnerText(elementClonedRoot);
@@ skipping 54 matching lines @@
     }
 
     public void setGroupNumber(int group) {
         groupNumber = group;
     }
 
     public int getGroupNumber() {
         return groupNumber;
     }
 }