Read UTF-8 XML File in Java using SAX parser example

Nikos MaravitsasMarch 14th, 2013Last Updated: March 14th, 2013

0 193 2 minutes read

In the previous SAX parser tutorial we saw how to parse and read a simple XML File. If your file had UTF-8 encoding, there is a chance that the client produced a MalformedByteSequenceException. In order to solve this you have to set the InputSource encoding to UTF-8.

You can do this with the following code :

InputStream inputStream= new FileInputStream(xmlFile);
InputStreamReader inputReader = new InputStreamReader(inputStream,"UTF-8");
InputSource inputSource = new InputSource(inputReader);
InputSource.setEncoding("UTF-8");

Here is the XML File we are going to use for our demo. We have the special UTF-8 character ©.

testFile.xml:

<?xml version="1.0" encoding="UTF-8" standalone="no"?><company>

	<employee id="10">
		<firstname>Jeremy</firstname>
		<lastname>Harley</lastname>
        <email>james@example.org</email>
		<department>Human Resources</department>
		<salary>2000000</salary>
	    <address>34 Stanley St.©</address>

	</employee>

	<employee id="2">
		<firstname>John</firstname>
		<lastname>May</lastname>
		<email>john@example.org</email>
		<department>Logistics</department>
		<salary>400</salary>
	    <address>123 Stanley St.</address>
	</employee>

</company>

MyHandler.java:

package com.javacodegeeks.java.core;

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

public class MyHandler extends DefaultHandler {

	boolean tagFname = false;
	boolean tagLname = false;
	boolean tagEmail = false;
	boolean tagDep = false;
	boolean tagSalary = false;
	boolean tagAddress = false;

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

		if (attributes.getLength() > 0) {

			String tag = "<" + qName;
			for (int i = 0; i < attributes.getLength(); i++) {

				tag += " " + attributes.getLocalName(i) + "="
						+ attributes.getValue(i);
			}

			tag += ">";
			System.out.println(tag);

		} else {

			System.out.println("<" + qName + ">");
		}

		if (qName.equalsIgnoreCase("firstname")) {
			tagFname = true;
		}

		if (qName.equalsIgnoreCase("lastname")) {
			tagLname = true;
		}

		if (qName.equalsIgnoreCase("email")) {
			tagEmail = true;
		}

		if (qName.equalsIgnoreCase("department")) {
			tagDep = true;
		}

		if (qName.equalsIgnoreCase("salary")) {
			tagSalary = true;
		}

		if (qName.equalsIgnoreCase("address")) {
			tagAddress = true;
		}

	}

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

		if (tagFname) {
			System.out.println(new String(ch, start, length));
			tagFname = false;
		}

		if (tagLname) {
			System.out.println(new String(ch, start, length));
			tagLname = false;
		}

		if (tagEmail) {
			System.out.println(new String(ch, start, length));
			tagEmail = false;
		}

		if (tagDep) {
			System.out.println(new String(ch, start, length));
			tagDep = false;
		}

		if (tagSalary) {
			System.out.println(new String(ch, start, length));
			tagSalary = false;
		}

		if (tagAddress) {
			System.out.println(new String(ch, start, length));
			tagAddress = false;
		}

	}

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

		System.out.println("</" + qName + ">");

	}

}

ParseUTF8XMLFileWithSAX.java:

package com.javacodegeeks.java.core;

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.InputSource;

public class ParseUTF8XMLFileWithSAX {

	private static final String xmlFilePath = "C:\\Users\\nikos7\\Desktop\\filesForExamples\\testFile.xml";

	public static void main(String argv[]) {

		try {

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

			File xmlFile = new File(xmlFilePath);

			InputStream inputStream= new FileInputStream(xmlFile);

			InputStreamReader inputReader = new InputStreamReader(inputStream,"UTF-8");

			InputSource inputSource = new InputSource(inputReader);
			inputSource.setEncoding("UTF-8");

			saxParser.parse(inputSource, new MyHandler());

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

Output:

<company>
<employee id=10>
<firstname>
Jeremy
</firstname>
<lastname>
Harley
</lastname>
<email>
james@example.org
</email>
<department>
Human Resources
</department>
<salary>
2000000
</salary>
<address>
34 Stanley St.©
</address>
</employee>
<employee id=2>
<firstname>
John
</firstname>
<lastname>
May
</lastname>
<email>
john@example.org
</email>
<department>
Logistics
</department>
<salary>
400
</salary>
<address>
123 Stanley St.
</address>
</employee>
</company>

This was an example on how to read UTF-8 XML File in Java using SAX parser.