001/*
002 * This library is part of OpenCms -
003 * the Open Source Content Management System
004 *
005 * Copyright (c) Alkacon Software GmbH & Co. KG (https://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: https://www.alkacon.com
019 *
020 * For further information about OpenCms, please see the
021 * project website: https://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_METADATA = new CmsExtractorPdf(true);
043
044    /** Static member instance of the extractor. */
045    private static final CmsExtractorPdf INSTANCE_NO_METADATA = new CmsExtractorPdf(false);
046
047    /** Flag, indicating if metadata should be extracted. */
048    private boolean m_extractMetaData;
049
050    /**
051     * Hide the public constructor.<p>
052     *
053     * @param extractMetaData flag, indicating if metadata should be extracted.
054     */
055    private CmsExtractorPdf(boolean extractMetaData) {
056
057        m_extractMetaData = extractMetaData;
058    }
059
060    /**
061     * Returns an instance of this text extractor.<p>
062     *
063     * @return an instance of this text extractor
064     */
065    public static I_CmsTextExtractor getExtractor() {
066
067        return INSTANCE_METADATA;
068    }
069
070    /**
071     * Returns an instance of this text extractor.<p>
072     *
073     * @param extractMetaData flag, indicating if metadata should be extracted.
074     *
075     * @return an instance of this text extractor
076     */
077    public static I_CmsTextExtractor getExtractor(boolean extractMetaData) {
078
079        return extractMetaData ? INSTANCE_METADATA : INSTANCE_NO_METADATA;
080    }
081
082    /**
083     * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
084     */
085    @Override
086    public I_CmsExtractionResult extractText(InputStream in) throws Exception {
087
088        return extractText(in, new PDFParser(), m_extractMetaData);
089    }
090}