Saturday, May 9, 2015

Unknown XML Structure Parsing Using SAX Parser

We learn how to parse a XML file using SAX parser previously but there we know the XML file structure means node structure.

Now we concentrate how to parse a XML file when we not aware of the structure of a XML file using SAX parser.

It can be possible if we do some modification on DefaultHandler part.

Here we parse a xml in such a manner where we find only the child element at last depth means, this node does not contains any child element .We also retrive attributes of this element.
So logic is that if we find that start element name follows the end element name  then we print the value of this node and attribute value.

Example code given below:


package SAXParser;


import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import javax.xml.parsers.ParserConfigurationException;
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 SAXParserExample {
    public static void main(String[] args) throws ParserConfigurationException, SAXException, IOException, VerifyError {

        /**
         * We can pass the class name of the XML parser
         * to the SAXParserFactory.newInstance().
         */


        //SAXParserFactory saxDoc = SAXParserFactory.newInstance("com.sun.org.apache.xerces.internal.jaxp.SAXParserFactoryImpl", null);

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

        DefaultHandler handler = new DefaultHandler() {
            String tmpElementName = null;
            String tmpElementValue = null;
            Map<String,String> tmpAtrb=null;

            @Override
            public void startElement(String uri, String localName, String qName, 

                                                                Attributes attributes) throws SAXException {
                tmpElementValue = "";
                tmpElementName = qName;
                tmpAtrb=new HashMap();
                //System.out.println("Start Element :" + qName);

                /**
                 * Store attributes in HashMap
                 */

                for (int i=0; i<attributes.getLength(); i++) {
                    String aname = attributes.getLocalName(i);
                    String value = attributes.getValue(i);
                    tmpAtrb.put(aname, value);
                }

            }

            @Override
            public void endElement(String uri, String localName, String qName) 

                                                        throws SAXException {
              
                if(tmpElementName.equals(qName)){
                    System.out.println("Element Name :"+tmpElementName);


                /**
                 * Retrive attributes from HashMap
                 */
                    for (Map.Entry<String, String> entrySet : tmpAtrb.entrySet()) {
                        System.out.println("Attribute Name :"+ entrySet.getKey() + "Attribute Value :"+ entrySet.getValue());
                    }
                    System.out.println("Element Value :"+tmpElementValue);
                }
            }

            @Override
            public void characters(char ch[], int start, int length) throws SAXException {
                tmpElementValue = new String(ch, start, length) ;
              
            }
        };
      
        /**
         * Below two line used if we use SAX 2.0
         * Then last line not needed.
         */

      
        //saxParser.setContentHandler(handler);
        //saxParser.parse(new InputSource("c:/file.xml"));


        saxParser.parse(new File("c:/file.xml"), handler);
    }
}

1 comment:

  1. Hey!
    Thank you for this great article!!!

    Greetings from Germany!

    ReplyDelete