How to read and write XML files?

I have to read and write to and from an XML file. What is the easiest way to read and write XML files using Java?

Here is a quick DOM example that shows how to read and write a simple xml file with its dtd:

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE roles SYSTEM "roles.dtd">
<roles>
    <role1>User</role1>
    <role2>Author</role2>
    <role3>Admin</role3>
    <role4/>
</roles>

and the dtd:

<?xml version="1.0" encoding="UTF-8"?>
<!ELEMENT roles (role1,role2,role3,role4)>
<!ELEMENT role1 (#PCDATA)>
<!ELEMENT role2 (#PCDATA)>
<!ELEMENT role3 (#PCDATA)>
<!ELEMENT role4 (#PCDATA)>

First import these:

import javax.xml.parsers.*;
import javax.xml.transform.*;
import javax.xml.transform.dom.*;
import javax.xml.transform.stream.*;
import org.xml.sax.*;
import org.w3c.dom.*;

Here are a few variables you will need:

private String role1 = null;
private String role2 = null;
private String role3 = null;
private String role4 = null;
private ArrayList<String> rolev;

Here is a reader (String xml is the name of your xml file):

public boolean readXML(String xml) {
        rolev = new ArrayList<String>();
        Document dom;
        // Make an  instance of the DocumentBuilderFactory
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        try {
            // use the factory to take an instance of the document builder
            DocumentBuilder db = dbf.newDocumentBuilder();
            // parse using the builder to get the DOM mapping of the    
            // XML file
            dom = db.parse(xml);

            Element doc = dom.getDocumentElement();

            role1 = getTextValue(role1, doc, "role1");
            if (role1 != null) {
                if (!role1.isEmpty())
                    rolev.add(role1);
            }
            role2 = getTextValue(role2, doc, "role2");
            if (role2 != null) {
                if (!role2.isEmpty())
                    rolev.add(role2);
            }
            role3 = getTextValue(role3, doc, "role3");
            if (role3 != null) {
                if (!role3.isEmpty())
                    rolev.add(role3);
            }
            role4 = getTextValue(role4, doc, "role4");
            if ( role4 != null) {
                if (!role4.isEmpty())
                    rolev.add(role4);
            }
            return true;

        } catch (ParserConfigurationException pce) {
            System.out.println(pce.getMessage());
        } catch (SAXException se) {
            System.out.println(se.getMessage());
        } catch (IOException ioe) {
            System.err.println(ioe.getMessage());
        }

        return false;
    }

And here a writer:

public void saveToXML(String xml) {
    Document dom;
    Element e = null;

    // instance of a DocumentBuilderFactory
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    try {
        // use factory to get an instance of document builder
        DocumentBuilder db = dbf.newDocumentBuilder();
        // create instance of DOM
        dom = db.newDocument();

        // create the root element
        Element rootEle = dom.createElement("roles");

        // create data elements and place them under root
        e = dom.createElement("role1");
        e.appendChild(dom.createTextNode(role1));
        rootEle.appendChild(e);

        e = dom.createElement("role2");
        e.appendChild(dom.createTextNode(role2));
        rootEle.appendChild(e);

        e = dom.createElement("role3");
        e.appendChild(dom.createTextNode(role3));
        rootEle.appendChild(e);

        e = dom.createElement("role4");
        e.appendChild(dom.createTextNode(role4));
        rootEle.appendChild(e);

        dom.appendChild(rootEle);

        try {
            Transformer tr = TransformerFactory.newInstance().newTransformer();
            tr.setOutputProperty(OutputKeys.INDENT, "yes");
            tr.setOutputProperty(OutputKeys.METHOD, "xml");
            tr.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
            tr.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM, "roles.dtd");
            tr.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "4");

            // send DOM to file
            tr.transform(new DOMSource(dom), 
                                 new StreamResult(new FileOutputStream(xml)));

        } catch (TransformerException te) {
            System.out.println(te.getMessage());
        } catch (IOException ioe) {
            System.out.println(ioe.getMessage());
        }
    } catch (ParserConfigurationException pce) {
        System.out.println("UsersXML: Error trying to instantiate DocumentBuilder " + pce);
    }
}

getTextValue is here:

private String getTextValue(String def, Element doc, String tag) {
    String value = def;
    NodeList nl;
    nl = doc.getElementsByTagName(tag);
    if (nl.getLength() > 0 && nl.item(0).hasChildNodes()) {
        value = nl.item(0).getFirstChild().getNodeValue();
    }
    return value;
}

Add a few accessors and mutators and you are done!

Writing XML using JAXB (Java Architecture for XML Binding):

http://www.mkyong.com/java/jaxb-hello-world-example/

package com.mkyong.core;

import javax.xml.bind.annotation.XmlAttribute;
import javax.xml.bind.annotation.XmlElement;
import javax.xml.bind.annotation.XmlRootElement;

@XmlRootElement
public class Customer {

    String name;
    int age;
    int id;

    public String getName() {
        return name;
    }

    @XmlElement
    public void setName(String name) {
        this.name = name;
    }

    public int getAge() {
        return age;
    }

    @XmlElement
    public void setAge(int age) {
        this.age = age;
    }

    public int getId() {
        return id;
    }

    @XmlAttribute
    public void setId(int id) {
        this.id = id;
    }

} 

package com.mkyong.core;

import java.io.File;
import javax.xml.bind.JAXBContext;
import javax.xml.bind.JAXBException;
import javax.xml.bind.Marshaller;

public class JAXBExample {
    public static void main(String[] args) {

      Customer customer = new Customer();
      customer.setId(100);
      customer.setName("mkyong");
      customer.setAge(29);

      try {

        File file = new File("C:\\file.xml");
        JAXBContext jaxbContext = JAXBContext.newInstance(Customer.class);
        Marshaller jaxbMarshaller = jaxbContext.createMarshaller();

        // output pretty printed
        jaxbMarshaller.setProperty(Marshaller.JAXB_FORMATTED_OUTPUT, true);

        jaxbMarshaller.marshal(customer, file);
        jaxbMarshaller.marshal(customer, System.out);

          } catch (JAXBException e) {
        e.printStackTrace();
          }

    }
}

The above answer only deal with DOM parser (that normally reads the entire file in memory and parse it, what for a big file is a problem), you could use a SAX parser that uses less memory and is faster (anyway that depends on your code).

SAX parser callback some functions when it find a start of element, end of element, attribute, text between elements, etc, so it can parse the document and at the same time you get what you need.

Some example code:

http://www.mkyong.com/java/how-to-read-xml-file-in-java-sax-parser/

The answers only cover DOM / SAX and a copy paste implementation of a JAXB example.

However, one big area of when you are using XML is missing. In many projects / programs there is a need to store / retrieve some basic data structures. Your program has already a classes for your nice and shiny business objects / data structures, you just want a comfortable way to convert this data to a XML structure so you can do more magic on it (store, load, send, manipulate with XSLT).

This is where XStream shines. You simply annotate the classes holding your data, or if you do not want to change those classes, you configure a XStream instance for marshalling (objects -> xml) or unmarshalling (xml -> objects).

Internally XStream uses reflection, the readObject and readResolve methods of standard Java object serialization.

You get a good and speedy tutorial here:

To give a short overview of how it works, I also provide some sample code which marshalls and unmarshalls a data structure. The marshalling / unmarshalling happens all in the main method, the rest is just code to generate some test objects and populate some data to them. It is super simple to configure the xStream instance and marshalling / unmarshalling is done with one line of code each.

import java.math.BigDecimal;
import java.util.ArrayList;
import java.util.List;

import com.thoughtworks.xstream.XStream;

public class XStreamIsGreat {

  public static void main(String[] args) {
    XStream xStream = new XStream();
    xStream.alias("good", Good.class);
    xStream.alias("pRoDuCeR", Producer.class);
    xStream.alias("customer", Customer.class);

    Producer a = new Producer("Apple");
    Producer s = new Producer("Samsung");
    Customer c = new Customer("Someone").add(new Good("S4", 10, new BigDecimal(600), s))
        .add(new Good("S4 mini", 5, new BigDecimal(450), s)).add(new Good("I5S", 3, new BigDecimal(875), a));
    String xml = xStream.toXML(c); // objects -> xml
    System.out.println("Marshalled:\n" + xml);
    Customer unmarshalledCustomer = (Customer)xStream.fromXML(xml); // xml -> objects
  }

  static class Good {
    Producer producer;

    String name;

    int quantity;

    BigDecimal price;

    Good(String name, int quantity, BigDecimal price, Producer p) {
      this.producer = p;
      this.name = name;
      this.quantity = quantity;
      this.price = price;
    }

  }

  static class Producer {
    String name;

    public Producer(String name) {
      this.name = name;
    }
  }

  static class Customer {
    String name;

    public Customer(String name) {
      this.name = name;
    }

    List<Good> stock = new ArrayList<Good>();

    Customer add(Good g) {
      stock.add(g);
      return this;
    }
  }
}

Ok, already having DOM, JaxB and XStream in the list of answers, there is still a complete different way to read and write XML: Data projection You can decouple the XML structure and the Java structure by using a library that provides read and writeable views to the XML Data as Java interfaces. From the tutorials:

Given some real world XML:

<weatherdata>
  <weather
    ... 
    degreetype="F"
    lat="50.5520210266113" lon="6.24060010910034" 
    searchlocation="Monschau, Stadt Aachen, NW, Germany" 
            ... >
    <current ... skytext="Clear" temperature="46"/>
  </weather>
</weatherdata>

With data projection you can define a projection interface:

public interface WeatherData {

@XBRead("/weatherdata/weather/@searchlocation")   
String getLocation();

@XBRead("/weatherdata/weather/current/@temperature")
int getTemperature();

@XBRead("/weatherdata/weather/@degreetype")
String getDegreeType();

@XBRead("/weatherdata/weather/current/@skytext")
String getSkytext();

/**
 * This would be our "sub projection". A structure grouping two attribute
 * values in one object.
 */
interface Coordinates {
    @XBRead("@lon")
    double getLongitude();

    @XBRead("@lat")
    double getLatitude();
}

@XBRead("/weatherdata/weather")
Coordinates getCoordinates();
}

And use instances of this interface just like POJOs:

private void printWeatherData(String location) throws IOException {
 
final String BaseURL = "http://weather.service.msn.com/find.aspx?outputview=search&weasearchstr=";
 
// We let the projector fetch the data for us
WeatherData weatherData = new XBProjector().io().url(BaseURL + location).read(WeatherData.class);
 
// Print some values
System.out.println("The weather in " + weatherData.getLocation() + ":");
System.out.println(weatherData.getSkytext());
System.out.println("Temperature: " + weatherData.getTemperature() + "°"
                                   + weatherData.getDegreeType());
 
// Access our sub projection
Coordinates coordinates = weatherData.getCoordinates();
System.out.println("The place is located at " + coordinates.getLatitude() + ","
                                              + coordinates.getLongitude());
}

This works even for creating XML, the XPath expressions can be writable.

SAX parser is working differently with a DOM parser, it neither load any XML document into memory nor create any object representation of the XML document. Instead, the SAX parser use callback function org.xml.sax.helpers.DefaultHandler to informs clients of the XML document structure.

SAX Parser is faster and uses less memory than DOM parser. See following SAX callback methods :

startDocument() and endDocument() – Method called at the start and end of an XML document. startElement() and endElement() – Method called at the start and end of a document element. characters() – Method called with the text contents in between the start and end tags of an XML document element.

1. XML file

Create a simple XML file.

<?xml version="1.0"?>
<company>
	<staff>
		<firstname>yong</firstname>
		<lastname>mook kim</lastname>
		<nickname>mkyong</nickname>
		<salary>100000</salary>
	</staff>
	<staff>
		<firstname>low</firstname>
		<lastname>yin fong</lastname>
		<nickname>fong fong</nickname>
		<salary>200000</salary>
	</staff>
</company>

2. XML parser:

Java file Use SAX parser to parse the XML file.

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

public class ReadXMLFile {
	public static void main(String argv[]) {

		try {
			SAXParserFactory factory = SAXParserFactory.newInstance();
			SAXParser saxParser = factory.newSAXParser();

			DefaultHandler handler = new DefaultHandler() {
				boolean bfname = false;
				boolean blname = false;
				boolean bnname = false;
				boolean bsalary = false;

				public void startElement(String uri, String localName,String qName, 
							Attributes attributes) throws SAXException {

					System.out.println("Start Element :" + qName);

					if (qName.equalsIgnoreCase("FIRSTNAME")) {
						bfname = true;
					}

					if (qName.equalsIgnoreCase("LASTNAME")) {
						blname = true;
					}

					if (qName.equalsIgnoreCase("NICKNAME")) {
						bnname = true;
					}

					if (qName.equalsIgnoreCase("SALARY")) {
						bsalary = true;
					}

				}

				public void endElement(String uri, String localName,
					String qName) throws SAXException {

					System.out.println("End Element :" + qName);

				}

				public void characters(char ch[], int start, int length) throws SAXException {

					if (bfname) {
						System.out.println("First Name : " + new String(ch, start, length));
						bfname = false;
					}

					if (blname) {
						System.out.println("Last Name : " + new String(ch, start, length));
						blname = false;
					}

					if (bnname) {
						System.out.println("Nick Name : " + new String(ch, start, length));
						bnname = false;
					}

					if (bsalary) {
						System.out.println("Salary : " + new String(ch, start, length));
						bsalary = false;
					}

				}

			};

			saxParser.parse("c:\\file.xml", handler);

		} catch (Exception e) {
		   e.printStackTrace();
		}

	}

}

Result

Start Element :company
Start Element :staff
Start Element :firstname
First Name : yong
End Element :firstname
Start Element :lastname
Last Name : mook kim
End Element :lastname
Start Element :nickname
Nick Name : mkyong
End Element :nickname
and so on...

Source(MyKong) - http://www.mkyong.com/java/how-to-read-xml-file-in-java-sax-parser/