#
#  This file is part of Documancer (http://documancer.sf.net)
#
#  Copyright (C) 2004-2005 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: pylucene_impl.py,v 1.4 2005/02/04 13:29:51 vaclavslavik Exp $
#
#  Fulltext indexer using PyLucene -- implementation

import sys
import PyLucene

from __init__ import FulltextIndexer # ugly, I admit

class PyLuceneIndexer(FulltextIndexer):
    """PyLucene-based fulltext indexer - the meal."""

    def __init__(self):
        self.writer = None
    
    def getNameAndVersion(self):
        return 'PyLucene %s using Lucene %s' % (
                    PyLucene.VERSION, PyLucene.LUCENE_VERSION)
    
    def search(self, directory, query):
        dir = PyLucene.FSDirectory.getDirectory(directory, False)
        searcher = PyLucene.IndexSearcher(dir)
        analyzer = PyLucene.StandardAnalyzer()
        queryobj = PyLucene.QueryParser.parse(query, 'contents', analyzer)
        hits = searcher.search(queryobj)
        
        results = []
        for hit in xrange(hits.length()):
            doc = hits.doc(hit)
            results.append(FulltextIndexer.Result(
                            doc.get('title'), doc.get('url'), hits.score(hit)))
        return results
 
    def startIndexing(self, directory):
        store = PyLucene.FSDirectory.getDirectory(directory, True)
        self.writer = PyLucene.IndexWriter(store,
                                           PyLucene.StandardAnalyzer(),
                                           True)

    def indexDocument(self, url, data):
        doc = PyLucene.Document()
        doc.add(PyLucene.Field('url', url, True, True, True))
        for field in data:
            doc.add(PyLucene.Field(field, data[field], True, True, True))
        self.writer.addDocument(doc)

    def stopIndexing(self):
        self.writer.optimize()
        self.writer.close()
        self.writer = None