Lucene 2.3 – working example of Indexer and Searcher

/**
 * This code was originally written for Erik's Lucene intro java.net article
 */
public class Indexer
{

// open an index and start file directory traversal
    /**
     * Index all the Stuff for searching
     *
     * @since $Release$
     *
     */
    public static int index(File indexDir, File dataDir) throws IOException
    {

        if (!dataDir.exists() || !dataDir.isDirectory())
        {
            throw new IOException(
                dataDir + " does not exist or is not a directory"
                );
        }

        IndexWriter writer =
            new IndexWriter(indexDir, new StandardAnalyzer(), true);
        writer.setUseCompoundFile(false);
        indexDirectory(writer, dataDir);

        int numIndexed = writer.docCount();
        writer.optimize();
        writer.close();

        return numIndexed;
    }

    /**
     * Main Program
     *
     * @since $Release$
     *
     * @param args DOCUMENT ME!
     *
     * @throws Exception DOCUMENT ME!
     */
    public static void main(String[] args) throws Exception
    {

        if (args.length != 2)
        {
            throw new Exception(
                "Usage: java " + Indexer.class.getName() +
                " <index dir> <data dir>"
                );
        }

        File indexDir = new File(args[0]);
        File dataDir = new File(args[1]);
        long start = new Date().getTime();
        int numIndexed = index(indexDir, dataDir);
        long end = new Date().getTime();
        System.out.println(
            "Indexing " + numIndexed + " files took " + (end – start) +
            " milliseconds"
            );
    }

//       recursive method that calls itself when it finds a directory
    /**
     * DOCUMENT ME!
     *
     * @since $Release$
     */
    private static void indexDirectory(IndexWriter writer, File dir)
        throws IOException
    {

        File[] files = dir.listFiles();

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

            File f = files[i];

            if (f.isDirectory())
            {
                indexDirectory(writer, f);
            }
            else if (f.getName()
                    .endsWith(".txt"))
            {
                indexFile(writer, f);
            }
        }
    }

//       method to actually index a file using Lucene
    /**
     * DOCUMENT ME!
     *
     * @since $Release$
     */
    private static void indexFile(IndexWriter writer, File f) throws IOException
    {

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

            return;
        }

        System.out.println("Indexing " + 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.UN_TOKENIZED
                )
            );

        //doc.add(Field.Text("contents", new FileReader(f)));
        //doc.add(Field.Keyword("filename", f.getCanonicalPath()));
        writer.addDocument(doc);
    }
}

/**
 * This code was originally written for Erik's Lucene intro java.net article
 */
public class Searcher
{

    /**
     * Search Using Lucene
     *
     * @since $Release$
     */
    public static void main(String[] args) throws Exception
    {

        if (args.length != 2)
        {
            throw new Exception(
                "Usage: java " + Searcher.class.getName() +
                " <index dir> <query>"
                );
        }

        File indexDir = new File(args[0]);
        String q = args[1];

        if (!indexDir.exists() || !indexDir.isDirectory())
        {
            throw new Exception(
                indexDir + " does not exist or is not a directory."
                );
        }

        search(indexDir, q);
    }

    /**
     * Search Function
     *
     * @since $Release$
     */
    public static void search(File indexDir, String q) throws Exception
    {

        Directory fsDir = FSDirectory.getDirectory(indexDir, false);
        IndexSearcher is = new IndexSearcher(fsDir);

        QueryParser qp = new QueryParser("contents", new StandardAnalyzer());
        Query query = qp.parse(q);

        long start = new Date().getTime();
        Hits hits = is.search(query);
        long end = new Date().getTime();
        System.err.println(
            "Found " + hits.length() + " document(s) (in " + (end – start) +
            " milliseconds) that matched query '" + q + "':"
            );

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

            Document doc = hits.doc(i);
            System.out.println(doc.get("filename"));
        }
    }
}