/*
 * This file is part of Documancer (http://documancer.sf.net)
 *
 * Copyright (C) 2005 Vaclav Slavik
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * $Id: IndexerService.java,v 1.1 2005/02/05 10:38:15 vaclavslavik Exp $
 *
 * Fulltext indexer using Lucene
 *
 */

import java.util.Vector;
import java.util.Hashtable;
import java.util.Enumeration;
import java.io.IOException;

import org.apache.xmlrpc.WebServer;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.*;
import org.apache.lucene.search.*;
import org.apache.lucene.store.FSDirectory;

/**
    Implementation of Lucene fulltext indexing for Documancer.
 */
public class IndexerService
{
    private static final String LUCENE_VERSION = "1.4.3";
    
    public IndexerService(WebServer server)
    {
        m_server = server;
    }
    
    /// Stops the server.
    public boolean kill()
    {
        m_server.shutdown();
        return true;
    }

    /// Returns server status (evrything except "OK" means failure).
    public String getStatus()
    {
        return "OK";
    }

    /// Returns human readable version of the indexer
    public String getNameAndVersion()
    {
        return "Lucene " + LUCENE_VERSION + " using " +
               System.getProperty("java.vm.name") + " " + 
               System.getProperty("java.vm.version");
    }

    /// Search index in given directory
    public Vector search(String directory, String query)
        throws IOException, ParseException
    {
        FSDirectory dir = FSDirectory.getDirectory(directory, false);
        StandardAnalyzer analyzer = new StandardAnalyzer();
        Query queryobj = QueryParser.parse(query, "contents", analyzer);
        
        IndexSearcher searcher = new IndexSearcher(dir);
        Hits hits = searcher.search(queryobj);

        Vector results = new Vector();

        for (int i = 0; i < hits.length(); i++)
        {
            Document doc = hits.doc(i);
            Hashtable h = new Hashtable();
            h.put("title", doc.get("title"));
            h.put("url",   doc.get("url"));
            h.put("score", new Float(hits.score(i)));
            results.add(h);
        }

        return results;
    }
    
    /// Starts indexing, creates new index in given directory
    public boolean startIndexing(String directory) throws IOException
    {
        FSDirectory store = FSDirectory.getDirectory(directory, true);
        m_writer = new IndexWriter(store, new StandardAnalyzer(), true);
        
        return true;
    }

    /// Indexes single document; startIndexing must be called before
    public boolean indexDocument(String url, Hashtable data) throws IOException
    {
        Document doc = new Document();
        doc.add(new Field("url", url, true, true, true));

        for (Enumeration e = data.keys(); e.hasMoreElements() ;)
        {
            String field = e.nextElement().toString();
            doc.add(new Field(field,
                              data.get(field).toString(),
                              true, true, true));
        }
        
        m_writer.addDocument(doc);
        
        return true;
    }

    /// Stops indexing and writes out finished index
    public boolean stopIndexing() throws IOException
    {
        m_writer.optimize();
        m_writer.close();
        m_writer = null;
        
        return true;
    }
    
    // active index writer for indexDocument and friends:
    private IndexWriter m_writer;
        
    // our XML-RPC server:
    private WebServer m_server;
}