Fastest and optimized way to read the xml

Question

I have this below XML file

<book>
<person>
  <first>Kiran</first>
  <last>Pai</last>
  <age>22</age>
</person>
<person>
  <first>Bill</first>
  <last>Gates</last>
  <age>46</age>
</person>
<person>
  <first>Steve</first>
  <last>Jobs</last>
  <age>40</age>
</person>
</book>

now the Java program to read data from an XML file is shown below..

import java.io.File;
import org.w3c.dom.Document;
import org.w3c.dom.*;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.DocumentBuilder;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException; 

public class ReadAndPrintXMLFile{

    public static void main (String argv []){
    try {

            DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
            DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
            Document doc = docBuilder.parse (new File("book.xml"));

            // normalize text representation
            doc.getDocumentElement ().normalize ();
            System.out.println ("Root element of the doc is " + 
                 doc.getDocumentElement().getNodeName());


            NodeList listOfPersons = doc.getElementsByTagName("person");
            int totalPersons = listOfPersons.getLength();
            System.out.println("Total no of people : " + totalPersons);

            for(int s=0; s<listOfPersons.getLength() ; s++){


                Node firstPersonNode = listOfPersons.item(s);
                if(firstPersonNode.getNodeType() == Node.ELEMENT_NODE){


                    Element firstPersonElement = (Element)firstPersonNode;

                    //-------
                    NodeList firstNameList = firstPersonElement.getElementsByTagName("first");
                    Element firstNameElement = (Element)firstNameList.item(0);

                    NodeList textFNList = firstNameElement.getChildNodes();
                    System.out.println("First Name : " + 
                           ((Node)textFNList.item(0)).getNodeValue().trim());

                    //-------
                    NodeList lastNameList = firstPersonElement.getElementsByTagName("last");
                    Element lastNameElement = (Element)lastNameList.item(0);

                    NodeList textLNList = lastNameElement.getChildNodes();
                    System.out.println("Last Name : " + 
                           ((Node)textLNList.item(0)).getNodeValue().trim());

                    //----
                    NodeList ageList = firstPersonElement.getElementsByTagName("age");
                    Element ageElement = (Element)ageList.item(0);

                    NodeList textAgeList = ageElement.getChildNodes();
                    System.out.println("Age : " + 
                           ((Node)textAgeList.item(0)).getNodeValue().trim());

                    //------


                }//end of if clause


            }//end of for loop with s var


        }catch (SAXParseException err) {
        System.out.println ("** Parsing error" + ", line " 
             + err.getLineNumber () + ", uri " + err.getSystemId ());
        System.out.println(" " + err.getMessage ());

        }catch (SAXException e) {
        Exception x = e.getException ();
        ((x == null) ? e : x).printStackTrace ();

        }catch (Throwable t) {
        t.printStackTrace ();
        }
        //System.exit (0);

    }//end of main


}

and the outcome was ..

Root element of the doc is book
Total no of people : 3
First Name : Kiran
Last Name : Pai
Age : 22
First Name : Bill
Last Name : Gates
Age : 46
First Name : Steve
Last Name : Jobs
Age : 40

Now my query is please advise is there any other way which is fastest to read this xml , I was looking the fastes , Please advise..!!

Answer 1

Using ReadAndPrintXMLFileWithStAX below, when I compare with ReadAndPrintXMLFileWithSAX from the answer given by gontard the StAX approach is faster. My test involved running both sample code 500000 times on JDK 1.7.0_07 for the Mac.

ReadAndPrintXMLFileWithStAX:  103 seconds
ReadAndPrintXMLFileWithSAX:   125 seconds

---

ReadAndPrintXMLFileWithStAX (using Java SE 7)

Below is a more optimized StAX (JSR-173) example using XMLStreamReader instead of XMLEventReader.

import java.io.FileInputStream;
import java.io.InputStream;
import javax.xml.stream.*;

public class ReadAndPrintXMLFileWithStAX {

    public static void main(String argv[]) throws Exception {
        XMLInputFactory inputFactory = XMLInputFactory.newInstance();
        InputStream in = new FileInputStream("book.xml");
        XMLStreamReader streamReader = inputFactory.createXMLStreamReader(in);
        streamReader.nextTag(); // Advance to "book" element
        streamReader.nextTag(); // Advance to "person" element

        int persons = 0;
        while (streamReader.hasNext()) {
            if (streamReader.isStartElement()) {
                switch (streamReader.getLocalName()) {
                case "first": {
                    System.out.print("First Name : ");
                    System.out.println(streamReader.getElementText());
                    break;
                }
                case "last": {
                    System.out.print("Last Name : ");
                    System.out.println(streamReader.getElementText());
                    break;
                }
                case "age": {
                    System.out.print("Age : ");
                    System.out.println(streamReader.getElementText());
                    break;
                }
                case "person" : {
                    persons ++;
                }
                }
            }
            streamReader.next();
        }
        System.out.print(persons);
        System.out.println(" persons");
    }

}

Output

First Name : Kiran
Last Name : Pai
Age : 22
First Name : Bill
Last Name : Gates
Age : 46
First Name : Steve
Last Name : Jobs
Age : 40
3 persons