Sample on how to work with XPATH

[Ravi Doddi]

Hai....
I have a xml file and I want to parse specific element using XPATH.
Could anyone give an sample java code that could parse an xml through XPATH.
Thankyou.

[Tushar Madhukar]

By "parsing" XML, I am assuming you want to query your DOM.

JDK 1.5 comes bundled with an XPath API (pl refer to package documentation of javax.xml.xpath). It is quite easy to use, with the Javadoc itself mentioning a working example.

Regards

[Siegfried Heintze]

/*
 * Begin commands to execute this file using Java with bash
 * if [ `uname` == 'Linux' ]
 * then
 * export CLASSPATH=bin:.
 * else
 * export CLASSPATH=bin\;.
 * fi
 * pushd .
 * if [ -e "bin" ]
 * then
 * echo "already have build (bin) directory"
 * else
 * echo "mkdir bin"
 * mkdir bin
 * fi
 * javac -g kkk.java -d bin
 * java  package_name_goes_here.kkk "/kkk/datum[1]/value/text()" '/kkk/datum[@name="abc"]' <<EOF 
 * <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 * <kkk>
 *   <datum name="xyz"><value>Insert your sample data here</value></datum>
 *   <datum name="abc"><value>def</value></datum>
 * </kkk>
 * EOF
 * rm bin/package_name_goes_here/kkk.class
 * popd
 * End commands to execute this file using Java with bash
 *
 */
package package_name_goes_here;
import java.io.FileInputStream;
import java.io.OutputStreamWriter;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.traversal.NodeIterator;
import org.xml.sax.InputSource;
 
public class kkk
{
  static java.io.PrintStream out = System.out;
  static java.io.BufferedReader in=new java.io.BufferedReader(new java.io.InputStreamReader(System.in));
  protected String sXPath = null;
 
  /** Process input args and execute the XPath.  */
  public void doMain(String[] args)
    throws Exception
  {
    int kk = 0;
    String sFileName = "";
    if(args[0].equals("-f")){
      kk += 2;
      sFileName = args[1];
    }
    // Set up a DOM tree to query.
    //InputSource in = new InputSource(new FileInputStream(sFileName));
    InputSource inSource = new InputSource(
      sFileName.equals("")?
      new FileInputStream(java.io.FileDescriptor.in)
      : new FileInputStream(sFileName)
      );
    DocumentBuilderFactory dfactory = DocumentBuilderFactory.newInstance();
    dfactory.setNamespaceAware(true);
    Document doc = dfactory.newDocumentBuilder().parse(inSource);
      
    // Set up an identity transformer to use as serializer.
    Transformer serializer = TransformerFactory.newInstance().newTransformer();
    serializer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
 
    for(int ii = kk; ii < args.length; ++ii){
      out.println("arg["+ii+"]="+args[ii]);
      sXPath = args[ii];
 
      // Use the simple XPath API to select a nodeIterator.
      
      out.println("Querying DOM using "+sXPath);
      XPath xpathInstance = XPathFactory.newInstance().newXPath();
 
      if ((sXPath != null) && (sXPath.length() > 0)){
        NodeList nodes = (NodeList) xpathInstance.evaluate(sXPath, doc.getDocumentElement(), XPathConstants.NODESET);
 
        int cNodes = nodes.getLength();
        // Serialize the found nodes to System.out.
        out.println("<output count=\""+cNodes+"\">");
             
        for(int jj = 0; jj < cNodes; ++jj){
          Node n = nodes.item(jj); 
          out.println("<!--name=["+n.getNodeName()+"] value:["+n.getNodeValue()+"] textContent:["+n.getTextContent()+"] type:["+getType(n.getNodeType())+"]-->");
          if (isTextNode(n)) {
            out.println(n.getTextContent());
          }
          else {
            serializer.transform(new DOMSource(n), new StreamResult(new OutputStreamWriter(System.out)));
          }
          out.println();
        }
        out.println("</output>");
      }
    }
  }
  
  /** Decide if the node is text, and so must be handled specially */
  static boolean isTextNode(Node n)  {
    if (n == null)
      return false;
    short nodeType = n.getNodeType();
    return nodeType == Node.CDATA_SECTION_NODE || nodeType == Node.TEXT_NODE || nodeType == Node.ATTRIBUTE_NODE;
  }
  static String getType(int s) {
    final String[] types= new String[]{"", 
     "ELEMENT_NODE", "ATTRIBUTE_NODE", "TEXT_NODE", "CDATA_SECTION_NODE", "ENTITY_REFERENCE_NODE", "ENTITY_NODE", "PROCESSING_INSTRUCTION_NODE", "COMMENT_NODE",
     "DOCUMENT_NODE", "DOCUMENT_TYPE_NODE", "DOCUMENT_FRAGMENT_NODE", "NOTATION_NODE"    };
    return types[s];
  }
  /** Main method to run from the command line.    */
  public static void main (String[] args)
    throws Exception
  {
    if (args.length > 1 )
    {
      kkk app = new kkk();
      app.doMain(args);
    }else{
      out.println("java kkk sFileName.xml xpath"
        + "Reads sFileName.xml and applies the xpath; prints the nodelist found.");
      return;
    }
  }     
} // end of class kkk

Here is the output of the embedded bash script when executed with Java 1.6 on windows with cygwin installed:

cd c:/Documents and Settings/Administrator/workspace/Hello_SWT/src/examples/ch8/xmlview/
 
if [ `uname` == 'Linux' ]
then
export CLASSPATH=bin:.
else
export CLASSPATH=bin\;.
fi
pushd .
if [ -e "bin" ]
then
echo "already have build (bin) directory"
else
echo "mkdir bin"
mkdir bin
fi
javac -g kkk.java -d bin
java  package_name_goes_here.kkk "/kkk/datum[1]/value/text()" '/kkk/datum[@name="abc"]' <<EOF 
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<kkk>
  <datum name="xyz"><value>Insert your sample data here</value></datum>
  <datum name="abc"><value>def</value></datum>
</kkk>
EOF
rm bin/package_name_goes_here/kkk.class
popd
 
~/Documents and Settings/Administrator/workspace/Hello_SWT/src/examples/ch8/xmlview ~/Documents and Settings/Administrator/workspace/Hello_SWT/src/examples/ch8/xmlview
mkdir bin
arg[0]=/kkk/datum[1]/value/text()
 
Querying DOM using /kkk/datum[1]/value/text()
 
<output count="1">
 
<!--name=[#text] value:[Insert your sample data here] textContent:[Insert your sample data here] type:[TEXT_NODE]-->
 
Insert your sample data here
 

 
</output>
 
arg[1]=/kkk/datum[@name="abc"]
 
Querying DOM using /kkk/datum[@name="abc"]
 
<output count="1">
 
<!--name=[datum] value:[null] textContent:[def] type:[ELEMENT_NODE]-->
 
<datum name="abc"><value>def</value></datum>
 
</output>
 
~/Documents and Settings/Administrator/workspace/Hello_SWT/src/examples/ch8/xmlview
 
Compilation finished at Sun Jan 20 22:53:19
 

[ January 20, 2008: Message edited by: Siegfried Heintze ]