lucene

Create Lucene Index

package com.javacodegeeks.lucene;
 
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
 
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
 
public class SimpleFileIndexer {
    
    public static void main(String[] args) throws Exception {

  

  File indexDir = new File("C:/index/");

  File dataDir = new File("C:/programs/eclipse/workspace/");

  String suffix = "java";

  

  SimpleFileIndexer indexer = new SimpleFileIndexer();

  

  int numIndex = indexer.index(indexDir, dataDir, suffix);

  

  System.out.println("Total files indexed " + numIndex);

  
    }
    
    private int index(File indexDir, File dataDir, String suffix) throws Exception {

  

  IndexWriter indexWriter = new IndexWriter(


    FSDirectory.open(indexDir), 


    new SimpleAnalyzer(),


    true,


    IndexWriter.MaxFieldLength.LIMITED);

  indexWriter.setUseCompoundFile(false);

  

  indexDirectory(indexWriter, dataDir, suffix);

  

  int numIndexed = indexWriter.maxDoc();

  indexWriter.optimize();

  indexWriter.close();

  

  return numIndexed;

  
    }
    
    private void indexDirectory(IndexWriter indexWriter, File dataDir, 

     String suffix) throws IOException {
 

  File[] files = dataDir.listFiles();

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


File f = files[i];


if (f.isDirectory()) {


    indexDirectory(indexWriter, f, suffix);


}


else {


    indexFileWithIndexWriter(indexWriter, f, suffix);


}

  }
 
    }
    
    private void indexFileWithIndexWriter(IndexWriter indexWriter, File f, 


String suffix) throws IOException {
 

  if (f.isHidden() || f.isDirectory() || !f.canRead() || !f.exists()) {


return;

  }

  if (suffix!=null && !f.getName().endsWith(suffix)) {


return;

  }

  System.out.println("Indexing file " + f.getCanonicalPath());

  

  Document doc = new Document();

  doc.add(new Field("contents", new FileReader(f)));
  

  doc.add(new Field("filename", f.getCanonicalPath(), 

     Field.Store.YES, Field.Index.ANALYZED));

  

  indexWriter.addDocument(doc);
 
    }
 
}

Related Article:

Byron Kiourtzoglou

Byron is a master software engineer working in the IT and Telecom domains. He is an applications developer in a wide variety of applications/services. He is currently acting as the team leader and technical architect for a proprietary service creation and integration platform for both the IT and Telecom industries in addition to a in-house big data real-time analytics solution. He is always fascinated by SOA, middleware services and mobile development. Byron is co-founder and Executive Editor at Java Code Geeks.
Subscribe
Notify of
guest

This site uses Akismet to reduce spam. Learn how your comment data is processed.

0 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
Back to top button