In this program, you will see the complete example to parse content and metadata of text file by using TIKA TXTParser.

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.sax.BodyContentHandler;
import org.apache.tika.parser.txt.TXTParser;

import org.xml.sax.SAXException;

public class TikaTextParserExample {

   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\\TEXT-FILE.txt"));
      ParseContext pcontext=new ParseContext();

      //Text document parser
      TXTParser  TexTParser = new TXTParser();
      TexTParser.parse(inputstream, handler, metadata,pcontext);
      System.out.println("Contents of the text document:" + handler.toString());
      System.out.println("Metadata of the text document:");
      String[] metadataNames = metadata.names();

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

Output

Contents of the text document:You are in FacingIssuesOnIT.

Learn from Others Experience.

Metadata of the text document:
Content-Encoding : windows-1252
Content-Type : text/plain; charset=windows-1252