[dom4j-user] dom4j - DOMWriter, TreeWalker bug?

Mah, Terry
Thu, 09 Nov 2006 09:35:46 -0800

Hello,

I'm hoping someone can help me figure out a strange problem.

I have a string which contains xml, and I have 2 scenarios that produce different results:

Scenario 1:

1. I first use DocumentHelper.parseText to parse the string into a dom4j.Document.

2. I then use DOMWriter to convert the document to a w3c.Document

3. I then create an instance of a xerces TreeWalker

4. Upon traversing the tree, I get new nodes where there should not be.

Scenario 2:

1. I use DocumentBuilderFactory->DocumentBuilder->InputSource to create a w3c.Document from the original source string

2. I then create an instance of a xerces TreeWalker

3. Tree traversal gives the expected nodes.

Here is my code:

------------------------------------------------------------------------------------------

import java.io.StringReader;
import java.io.StringWriter;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.apache.xerces.dom.DocumentImpl;
import org.apache.xerces.dom.TreeWalkerImpl;
import org.apache.xml.serialize.LineSeparator;
import org.apache.xml.serialize.OutputFormat;
import org.apache.xml.serialize.XMLSerializer;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.io.DOMWriter;
import org.w3c.dom.Node;
import org.w3c.dom.traversal.NodeFilter;
import org.w3c.dom.traversal.TreeWalker;
import org.xml.sax.InputSource;

public class Dom4jTest {
 public static void main(String[] args) {
 try {
 Dom4jTest dt = new Dom4jTest();
 String source ="<?xml version=\"1.0\" encoding=\"UTF-8\"?>"+
 "<body>This Office is a test document: Officert "Bert". y "Sam". "Bert" ow aobl him. Jreine aine.</body>";
 Document dom4jDoc = DocumentHelper.parseText(source);
 org.w3c.dom.Document domDoc = dt.convert(dom4jDoc);
 System.out.println("----Calling createDocument with dom4j Document converted----");
 System.out.println("domDoc: "+dt.serializeDom(domDoc));
 dt.createDocument(domDoc);

 DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
 DocumentBuilder builder = factory.newDocumentBuilder();
 InputSource is = new InputSource(new StringReader(source));
 domDoc = builder.parse(is);
 System.out.println("----Calling createDocument with w3c Document----");
 System.out.println("domDoc: "+dt.serializeDom(domDoc));
 dt.createDocument(domDoc);

        } catch (Exception e) {
            System.out.println("Exception has occurred.");
        }
    }
    public Dom4jTest() {
        super();
    }
    public org.w3c.dom.Document convert(Document dom4jDoc) throws DocumentException {
        DOMWriter writer = new DOMWriter();
        return writer.write(dom4jDoc);
    }
    public void createDocument(org.w3c.dom.Document srcDoc) throws Exception {
        AllElements allelements = new AllElements();
        Node sourceRoot = srcDoc.getLastChild();
        DocumentImpl sourceImpl = (DocumentImpl)srcDoc;
        TreeWalkerImpl tw =
           (TreeWalkerImpl)sourceImpl.createTreeWalker(sourceRoot,
              NodeFilter.SHOW_ALL, allelements, true);
        walk(tw);
    }
    private void walk(TreeWalker sourceIterator) {
        Node n = sourceIterator.getCurrentNode();
        for (Node tagSourceElem = sourceIterator.firstChild();tagSourceElem != null; tagSourceElem = sourceIterator.nextSibling()) {
            if (tagSourceElem.getNodeValue() != null) {
                System.out.println("The name and value of the node: "+tagSourceElem.getNodeName() + " " + tagSourceElem.getNodeValue());
            }
            walk(sourceIterator);
        }
        sourceIterator.setCurrentNode(n);
    }
    // filters the elements of the XML document
    class AllElements implements NodeFilter
    {
      public short acceptNode (Node n)
      {
        if (n.getNodeType() > 0 )
          return FILTER_ACCEPT;
        return FILTER_SKIP;
      }
    }
    private static String serializeDom(org.w3c.dom.Document xmlDom) {
        OutputFormat format = new OutputFormat(xmlDom);
        format.setLineSeparator(LineSeparator.Windows);
        StringWriter writer = new StringWriter();

        XMLSerializer serializer = new XMLSerializer(writer, format);
        try {
        serializer.asDOMSerializer();
        serializer.serialize(xmlDom);
        } catch (Exception e) {
            System.out.println("Exception in SerializeDom");
        }
        return writer.toString();
    }
}

------------------------------------------------------------------------------------------

Here is my output:

----Calling createDocument with dom4j Document converted----

domDoc: <?xml version="1.0" encoding="UTF-8"?>

<body>This Office is a test document: Officert "Bert". y "Sam". "Bert" ow aobl him. Jreine aine.</body>

The name and value of the node: #text This Office is a

The name and value of the node: #text test document: Officer

The name and value of the node: #text t