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.extractors;
029
030import java.io.InputStream;
031
032import org.apache.tika.parser.pdf.PDFParser;
033
034/**
035 * Extracts the text from a PDF document.<p>
036 *
037 * @since 6.0.0
038 */
039public final class CmsExtractorPdf extends A_CmsTextExtractor {
040
041    /** Static member instance of the extractor. */
042    private static final CmsExtractorPdf INSTANCE = new CmsExtractorPdf();
043
044    /**
045     * Hide the public constructor.<p>
046     */
047    private CmsExtractorPdf() {
048
049        // noop
050    }
051
052    /**
053     * Returns an instance of this text extractor.<p>
054     *
055     * @return an instance of this text extractor
056     */
057    public static I_CmsTextExtractor getExtractor() {
058
059        return INSTANCE;
060    }
061
062    /**
063     * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
064     */
065    @Override
066    public I_CmsExtractionResult extractText(InputStream in) throws Exception {
067
068        return extractText(in, new PDFParser());
069    }
070}