Wednesday, 10 September 2014

Lucene Indexing and Searching with MySQL data

        While working with my recent project I need to work with Lucene indexing. I tried Google, but I was not able to find any example with Lucene API latest version (i.e. 4.10.0). So here I am giving very simple example for indexing and then searching the particular data using Lucene API.

➟ About the Example

     I am giving brief explanation here about this example. This example will retrieve some information from database using simple JDBC connection. After that it will index that data and we can search indexed data very fast using Lucene API.

➟ Pre-requirements

    To run this example successfully you need to manage these requirements.

     ➤ Any SQL Database
         You can any driver name according to database. I have used MySQL for this example. Create one database named solr_test and one table named student_details with fields id INT, name varchar(10), address varchar(50) and details varchar(500).

        You can see about it This is maven based project. So to run it successfully you need to configure any Java IDE with maven plugin or maven must installed externally

➟ Download demo

➟ Code Snap

package com.lucene.test;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.util.Version;

 * This is test example file to explore Lucene API
 * @author vishal.zanzrukia
 * @version 1.0
public class LuceneTest
  * this is index directory path where all index file will be stored which lucene uses internally.
 public static final File INDEX_DIRECTORY = new File("IndexDirectory");

  * to create index on simple database table
 public void createIndex()

  System.out.println("-- Indexing --");

   /** JDBC Section */

   /** Assuming database solr_test exists */
   Connection conn = DriverManager.getConnection("jdbc:mysql://localhost:3306/solr_test", "root", "P@ssw0rd@123");
   Statement stmt = conn.createStatement();
   String sql = "select id,name,address,details from student_details";
   ResultSet rs = stmt.executeQuery(sql);

   /** Lucene Section */
   Directory directory =;

   /** defining Analyzer */
   Analyzer keywordAnalyzer = new KeywordAnalyzer();

   /** preparing config for indexWriter */
   IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LATEST, keywordAnalyzer);
   /** Create a new index in the directory, removing any previously indexed documents */
    * Optional: for better indexing performance, if you are indexing many documents,
* increase the RAM buffer. But if you do this, increase the max heap size to the JVM (eg add -Xmx512m or -Xmx1g): */ // writerConfig.setRAMBufferSizeMB(256.0); IndexWriter iWriter = new IndexWriter(directory, writerConfig); int count = 0; Document doc = null; Field field = null; /** declaring string type */ FieldType stringType = new FieldType(); stringType.setTokenized(true); stringType.setIndexed(true); /** Looping through resultset and adding data to index file */ while ( { doc = new Document(); /** adding id in document */ field = new IntField("id", rs.getInt("id"), Field.Store.YES); doc.add(field); /** adding name in document */ field = new StringField("name", rs.getString("name"), Field.Store.YES); doc.add(field); /** adding address in document */ field = new StringField("address", rs.getString("address"), Field.Store.YES); doc.add(field); /** adding details in document */ field = new StringField("details", rs.getString("details"), Field.Store.YES); doc.add(field); /** Adding doc to iWriter */ iWriter.addDocument(doc); count++; } System.out.println(count + " record indexed"); /** Closing iWriter */ iWriter.commit(); iWriter.close(); /** Closing JDBC connection */ rs.close(); stmt.close(); conn.close(); } catch (Exception e) { e.printStackTrace(); } } /** * to search the keywords * * @param keyword */ public void search(String keyword) { System.out.println("-- Seaching --"); try { /** Searching */ IndexReader directoryReader =; IndexSearcher searcher = new IndexSearcher(directoryReader); Analyzer keywordAnalyzer = new KeywordAnalyzer(); /** MultiFieldQueryParser is used to search multiple fields */ String[] filesToSearch = { "id", "name", "address", "details" }; MultiFieldQueryParser mqp = new MultiFieldQueryParser(filesToSearch, keywordAnalyzer); /** search the given keyword */ Query query = mqp.parse(keyword); System.out.println("query >> " + query); /** run the query */ TopDocs hits =, 100); System.out.println("Results found >> " + hits.totalHits); Document doc = null; for (int i = 0; i < hits.totalHits; i++) { /** get the next document */ doc = searcher.doc(hits.scoreDocs[i].doc); System.out.println("==========" + (i + 1) + " : Start Record=========\nId :: " + doc.get("id") + "\nName :: " + doc.get("name") + "\nDetails :: " + doc.get("details") + "\n==========End Record=========\n"); } } catch (Exception e) { e.printStackTrace(); } } /** * main method to check the output * * @param args */ public static void main(String[] args) { LuceneTest obj = new LuceneTest(); /** creating index */ obj.createIndex(); /** searching simple keyword */ System.out.println("==================searching simple keyword===========================");"vishal"); /** searching using wild card */ System.out.println("==================searching using wild card===========================");"neh*"); /** searching using logical OR operator */ System.out.println("==================searching using logical OR operator===========================");"vishal OR neha"); /** searching using logical AND operator */ System.out.println("==================searching using logical AND operator===========================");"vishal AND neha"); } }


keyur ardeshana said...

Nice article. worth reading and also provided easy to understand example. Thanks Vishal.

Vishal Zanzrukia said...

Thanks Keyur for your nice words :)

Neha Ghetia said...

really very useful article. must read.

Vishal Zanzrukia said...

Thanks Neha for your nice words :)

nishita sharma said...

Very helpful tutorial. Helped me set up my first lucene based search.

Vishal Zanzrukia said...

Thanks Nishita for your nice words :)

Numan G. Ayanoğlu said...

thanx for article

Vishal Zanzrukia said...

Thanks for your nice words :)

芈云落 said...

Thanks Vishal, offer easy example for me to understand lucene:-)

Vishal Zanzrukia said...

Thanks for your nice words :)