In this program, you will see complete steps to extract XML file content and metadata by using XMLParser.

Sample File

Complete Example

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.xml.XMLParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class TikaXmlParserExample {

	public static void main(final String[] args) throws IOException, SAXException, TikaException {

		// detecting the file type
		BodyContentHandler handler = new BodyContentHandler();
		Metadata metadata = new Metadata();
		FileInputStream inputstream = new FileInputStream(new File("C:\\Users\\Saurabh Gupta\\Desktop\\TIKA\\EmployeeData.xml"));
		ParseContext pcontext = new ParseContext();

		// Xml parser
		XMLParser xmlparser = new XMLParser();
		xmlparser.parse(inputstream, handler, metadata, pcontext);
		System.out.println("Contents of the XML document:" + handler.toString());
		System.out.println("Metadata of the XML document:");
		String[] metadataNames = metadata.names();

		for (String name : metadataNames) {
			System.out.println(name + ": " + metadata.get(name));
		}
	}
}

Output

Contents of the XML document: 
     
         Saurabh
         Gupta
         13-Jun-1980
    
     
         Gaurav
         Kumar
         12-Dec-1987
    
     
         Rajesh
         Gupta
         10-Jan-1999
    
     
         Raghvendra
         Prasad
         14-Mar-1985
    
     
         Rahul
         Jain
         11-May-1981
    


Metadata of the XML document:
Content-Type: application/xml