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.CmsObject;
031import org.opencms.file.CmsResource;
032import org.opencms.main.CmsException;
033import org.opencms.search.I_CmsSearchIndex;
034import org.opencms.search.extractors.I_CmsExtractionResult;
035
036/**
037 * Defines a text extractor for the integrated search engine.<p>
038 *
039 * The job of a search extractor is to extract indexable plain text from
040 * a resource in the OpenCms VFS. This may be from the resource content, for example
041 * from a PDF file, or from the resource properties, for example the Title, Keywords and
042 * Description properties.<p>
043 *
044 * @since 6.0.0
045 */
046public interface I_CmsSearchExtractor {
047
048    /**
049     * Extracts the content of a given index resource according to the resource file type and the
050     * configuration of the given index.<p>
051     *
052     * @param cms the cms object
053     * @param resource the resource to extract the content from
054     * @param index the index to extract the content for
055     *
056     * @return the extracted content of the resource
057     *
058     * @throws CmsException if something goes wrong
059     */
060    I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, I_CmsSearchIndex index)
061    throws CmsException;
062
063}