import java.io.File;

import java.io.FileReader;

import java.io.Reader;

import java.io.FileFilter;

import java.util.Date;

import org.apache.lucene.analysis.*;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.index.IndexWriter;



public class TxtFileIndex

{

       public static void main(String[] args) throws Exception

       {

          File dataDir = new File("C:\\IR\\IR_TEST");

          File indexDir = new File("C:\\IR\\IR_index");



          Analyzer luceneAnalyzer = new StandardAnalyzer();

          File[] dataFiles = dataDir.listFiles();



          IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);



          long startTime = new Date().getTime();

          for (int i=0;i<dataFiles.length;i++)

          {

              if(dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".txt"))

              {

                    System.out.println("Idx"+dataFiles[i].getCanonicalPath());



                    Document document = Document();

                    Reader txtReader = new FileReader(dataFiles[i]);

                    document.add(new Field("path", dataFiles[i].getCanonicalPath(), Field.Store.YES, Field.Index.UN_TOKENIZED));

                    document.add(new Field("contents, txtReader"));

              }

          }

          indexWriter.optimize();

          indexWriter.close();

          long endTime = new Date().getTime();



          System.out.println("It take "+ (endTime - startTime) + "milliseconds to create index for the files in directory." + dataDir.getPath());



       }

}