001/*
002 * This library is part of OpenCms -
003 * the Open Source Content Management System
004 *
005 * Copyright (c) Alkacon Software GmbH & Co. KG (http://www.alkacon.com)
006 *
007 * This library is free software; you can redistribute it and/or
008 * modify it under the terms of the GNU Lesser General Public
009 * License as published by the Free Software Foundation; either
010 * version 2.1 of the License, or (at your option) any later version.
011 *
012 * This library is distributed in the hope that it will be useful,
013 * but WITHOUT ANY WARRANTY; without even the implied warranty of
014 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
015 * Lesser General Public License for more details.
016 *
017 * For further information about Alkacon Software GmbH & Co. KG, please see the
018 * company website: http://www.alkacon.com
019 *
020 * For further information about OpenCms, please see the
021 * project website: http://www.opencms.org
022 *
023 * You should have received a copy of the GNU Lesser General Public
024 * License along with this library; if not, write to the Free Software
025 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
026 */
027
028package org.opencms.search.documents;
029
030import org.opencms.file.CmsFile;
031import org.opencms.file.CmsObject;
032import org.opencms.file.CmsResource;
033import org.opencms.main.CmsException;
034import org.opencms.search.CmsIndexException;
035import org.opencms.search.I_CmsSearchIndex;
036import org.opencms.search.extractors.CmsExtractorOpenOffice;
037import org.opencms.search.extractors.I_CmsExtractionResult;
038
039/**
040 * Lucene document factory class to extract index data from a cms resource
041 * containing Open Document Format data.<p>
042 *
043 * @since 7.0.4
044 */
045public class CmsDocumentOpenOffice extends A_CmsVfsDocument {
046
047    /**
048     * Creates a new instance of this lucene document factory.<p>
049     *
050     * @param name name of the document type
051     */
052    public CmsDocumentOpenOffice(String name) {
053
054        super(name);
055    }
056
057    /**
058     * Returns the raw text content of a given vfs resource containing MS Word data.<p>
059     *
060     * @see org.opencms.search.documents.I_CmsSearchExtractor#extractContent(CmsObject, CmsResource, I_CmsSearchIndex)
061     */
062    public I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, I_CmsSearchIndex index)
063    throws CmsIndexException, CmsException {
064
065        logContentExtraction(resource, index);
066        CmsFile file = readFile(cms, resource);
067        try {
068            return CmsExtractorOpenOffice.getExtractor().extractText(file.getContents());
069        } catch (Exception e) {
070            throw new CmsIndexException(
071                Messages.get().container(Messages.ERR_TEXT_EXTRACTION_1, resource.getRootPath()),
072                e);
073        }
074    }
075
076    /**
077     * @see org.opencms.search.documents.I_CmsDocumentFactory#isLocaleDependend()
078     */
079    public boolean isLocaleDependend() {
080
081        return false;
082    }
083
084    /**
085     * @see org.opencms.search.documents.I_CmsDocumentFactory#isUsingCache()
086     */
087    public boolean isUsingCache() {
088
089        return true;
090    }
091}