LuceneFilterBean.java

/*
 * To change this template, choose Tools | Templates
 * and open the template in the editor.
 */

package nl.kabisa.mgl.rssninja.beans;

import java.io.IOException;
import java.util.Date;
import java.util.logging.Level;
import java.util.logging.Logger;
import javax.ejb.ActivationConfigProperty;
import javax.ejb.MessageDriven;
import javax.jms.JMSException;
import javax.jms.Message;
import javax.jms.MessageListener;
import javax.jms.TextMessage;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

/**
 *
 * @author ariejan
 */
@MessageDriven(mappedName = "jms/filterQueue", activationConfig =  {
        @ActivationConfigProperty(propertyName = "acknowledgeMode", propertyValue = "Auto-acknowledge"),
        @ActivationConfigProperty(propertyName = "destinationType", propertyValue = "javax.jms.Queue")
    })
public class LuceneFilterBean implements MessageListener {


    /**
     * Make a Document object with an un-indexed title field and an
     * indexed content field.
     */
    private static Document createDocument(String title, String content) {
        Document doc = new Document();

        doc.add(new Field("title", title, Field.Store.YES, Field.Index.NO));
        doc.add(new Field("content", content, Field.Store.YES, Field.Index.ANALYZED));

        return doc;
    }

    @Override
    public void onMessage(Message message) {
        // Construct a RAMDirectory to hold the in-memory representation
        // of the index.
        long start = System.currentTimeMillis();

        RAMDirectory idx = new RAMDirectory();

        TextMessage text = (TextMessage) message;

        try {
            // Make an writer to create the index
            IndexWriter writer = new IndexWriter(idx,
                    new StandardAnalyzer(Version.LUCENE_30),
                    true,
                    IndexWriter.MaxFieldLength.UNLIMITED);

            // Add some Document objects containing quotes
            writer.addDocument(createDocument("Theodore Roosevelt",
                "It behooves every man to remember that the work of the " +
                "critic, is of altogether secondary importance, and that, " +
                "in the end, progress is accomplished by the man who does " +
                "things."));
            writer.addDocument(createDocument("Friedrich Hayek",
                "The case for individual freedom rests largely on the " +
                "recognition of the inevitable and universal ignorance " +
                "of all of us concerning a great many of the factors on " +
                "which the achievements of our ends and welfare depend."));
            writer.addDocument(createDocument("Ayn Rand",
                "There is nothing to take a man's freedom away from " +
                "him, save other men. To be free, a man must be free " +
                "of his brothers."));
            writer.addDocument(createDocument("Mohandas Gandhi",
                "Freedom is not worth having if it does not connote " +
                "freedom to err."));
            writer.addDocument(createDocument("Incoming message", text.getText()));

            // Optimize and close the writer to finish building the index
            writer.optimize();
            writer.close();

            System.out.println("== Indexed in: " + (System.currentTimeMillis() - start) + "ms.");

            // Build an IndexSearcher using the in-memory index
            Searcher searcher = new IndexSearcher(idx);
            
            search(searcher, "freedom");
            search(searcher, "free");
            search(searcher, "progress or achievements");

            searcher.close();

            Date endTime = new Date();

            System.out.println("== Total elapsed: " + (System.currentTimeMillis() - start) + "ms.");
        } catch (JMSException ex) {
            Logger.getLogger(LuceneFilterBean.class.getName()).log(Level.SEVERE, null, ex);
        }
        catch (ParseException ex) {
                Logger.getLogger(LuceneFilterBean.class.getName()).log(Level.SEVERE, null, ex);
        }
        catch (CorruptIndexException ex) {
                Logger.getLogger(LuceneFilterBean.class.getName()).log(Level.SEVERE, null, ex);
        }
        catch (LockObtainFailedException ex) {
            Logger.getLogger(LuceneFilterBean.class.getName()).log(Level.SEVERE, null, ex);
        }
        catch (IOException ex) {
            Logger.getLogger(LuceneFilterBean.class.getName()).log(Level.SEVERE, null, ex);
        }
        finally {
           // Stuffs
        }
    }

    private static void search(Searcher searcher, String queryString)
        throws ParseException, IOException {

        // Build a Query object
        QueryParser parser = new QueryParser(Version.LUCENE_30, "content", new StandardAnalyzer(Version.LUCENE_30));
        Query query = parser.parse(queryString);
        
        // Search for the query
        // Hits hits = searcher.search(query);
        TopDocs hits = searcher.search(query, 10);

        // Examine the Hits object to see if there were any matches
        int hitCount = hits.totalHits;
        if (hitCount == 0) {
            System.out.println(
                "No matches were found for \"" + queryString + "\"");
        }
        else {
            System.out.println("Hits for \"" +
                queryString + "\" were found in quotes by:");

            // Iterate over the Documents in the Hits object
            for (int i = 0; i < hitCount; i++) {
                ScoreDoc doc = hits.scoreDocs[i];

                // Print the value that we stored in the "title" field. Note
                // that this Field was not indexed, but (unlike the
                // "contents" field) was stored verbatim and can be
                // retrieved.
                System.out.println("  " + (i + 1) + ". " + doc.toString());
            }
        }
        System.out.println();
    }
}

output.txt

INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 233ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 346ms.

-- Obviously, the first run is slow.

INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 3ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.

-- Next runs are pretty fast :)

INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 3ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.
INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 4ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 7ms.
INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 4ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.
INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 3ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.
INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 3ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.
INFO: Sending message: Shields up! Rrred Alert!
INFO: == Indexed in: 3ms.
INFO: Hits for "freedom" were found in quotes by:
INFO:   1. doc=3 score=0.64866984
INFO:   2. doc=2 score=0.3057859
INFO:   3. doc=1 score=0.22933942
INFO: Hits for "free" were found in quotes by:
INFO:   1. doc=2 score=0.6775111
INFO: Hits for "progress or achievements" were found in quotes by:
INFO:   1. doc=0 score=0.16937779
INFO:   2. doc=1 score=0.12703334
INFO: == Total elapsed: 6ms.