Using Java to remove all xml attributes from a XML file that match a attribute-name?

Question

I am trying to use Java to remove all xml attributes from a XML file that match a attribute-name. I am stuck at this point. At the bottom of this code I am able to get the attribute value of each node as I loop through but I can't figure out how to delete the attribute from the Node altogether . Any ideas?

import java.io.IOException;
import java.io.StringWriter;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.TransformerFactoryConfigurationError;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.w3c.dom.*;
import org.xml.sax.SAXException;


public class StripAttribute { 

  public static void main(String[] args) { 

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); 
    factory.setNamespaceAware(true); 
    org.w3c.dom.Document doc = null;
    NodeList nodes = null;
    try {
      DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();  
      DocumentBuilder db = dbf.newDocumentBuilder(); 
      doc = db.parse("a.xml");
      nodes = doc.getChildNodes();
    }  catch (IOException e) {
      e.printStackTrace();
    } catch (ParserConfigurationException e) {
      e.printStackTrace();
    } catch (SAXException e) {
      e.printStackTrace();
    }
    for ( int i = 0; i < nodes.getLength(); i++ ) { 
      String id = nodes.item(i).getNodeValue();
      if ( id.equals("siteKey")) {
        Element el = ((Attr) nodes.item(i)).getOwnerElement(); 
        el.removeAttribute(id);
      }
    } 

    Transformer transformer;
    StreamResult result = null;
    try {
      transformer = TransformerFactory.newInstance().newTransformer();
      transformer.setOutputProperty(OutputKeys.INDENT, "yes");
      result = new StreamResult(new StringWriter()); 
      DOMSource source = new DOMSource(doc); 
      transformer.transform(source, result); 
    } catch (TransformerConfigurationException e) {
      e.printStackTrace();
    } catch (TransformerFactoryConfigurationError e) {
      e.printStackTrace();
    } catch (TransformerException e) {
      e.printStackTrace();
    } 
    String xmlString = result.getWriter().toString(); 
    System.out.println(xmlString); 
  } 
}    

Here is a sample of the XML I want to transform:

https://gist.github.com/2784907

Answer 1

Try:

for ( int i = 0; i < nodes.getLength(); i++ ) { 
    String id = nodes.item(i).getNodeValue();
    if ( id.equals("siteKey")) {
        //doc.removeChild(nodes.item(i));
        Element el = ((Attr) nodes.item(i)).getOwnerElement(); 
        el.removeAttribute(id);
    }
} 

It seems that the nodes returned by the query are detached from the document so getParentNode is null. - no, they are not detached, I updated the code.

I found an article that says that the nodes returned by XPathExpression are still attached to the document.

You're original code + the above change:

public static void main(String[] args) throws Exception {

    DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
    factory.setNamespaceAware(true);
    Document doc = null;
    NodeList nodes = null;
    Set<String> ids = null;
    try {
        doc = factory.newDocumentBuilder().parse(new File("d:/a.xml"));

        XPathExpression expr = XPathFactory.newInstance().newXPath().compile("//@siteKey");
        ids = new HashSet<String>();
        nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
    } catch (SAXException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (ParserConfigurationException e) {
        e.printStackTrace();
    } catch (XPathExpressionException e) {
        e.printStackTrace();
    }

    for (int i = 0; i < nodes.getLength(); i++) {
        String id = nodes.item(i).getNodeValue();
        if (id.equals("siteKey")) {
            Element el = ((Attr) nodes.item(i)).getOwnerElement();
            el.removeAttribute(id);
        }
    }

    int dupes = 0;
    for (int i = 0; i < nodes.getLength(); i++) {
        String id = nodes.item(i).getNodeValue();
        if (ids.contains(id)) {
            System.out.format("%s is duplicate\n\n", id);
            dupes++;
        } else {
            ids.add(id);
        }
    }

    System.out.format("Total ids = %d\n Total Duplicates = %d\n", ids.size(), dupes);

    Transformer transformer;
    StreamResult result = null;
    try {
        transformer = TransformerFactory.newInstance().newTransformer();
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        result = new StreamResult(new StringWriter());
        DOMSource source = new DOMSource(doc);
        transformer.transform(source, result);
    } catch (TransformerConfigurationException e) {
        e.printStackTrace();
    } catch (TransformerFactoryConfigurationError e) {
        e.printStackTrace();
    } catch (TransformerException e) {
        e.printStackTrace();
    }

    String xmlString = result.getWriter().toString();
    System.out.println(xmlString);

} 

Update:

for (int i = 0; i < nodes.getLength(); i++) {
    String id = nodes.item(i).getNodeValue();
    Element el = ((Attr) nodes.item(i)).getOwnerElement();
    el.removeAttribute(id);
}