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.CmsProperty;
033import org.opencms.file.CmsPropertyDefinition;
034import org.opencms.file.CmsResource;
035import org.opencms.main.CmsException;
036import org.opencms.main.OpenCms;
037import org.opencms.search.CmsIndexException;
038import org.opencms.search.I_CmsSearchIndex;
039import org.opencms.search.extractors.CmsExtractorHtml;
040import org.opencms.search.extractors.I_CmsExtractionResult;
041
042/**
043 * Lucene document factory class to extract index data from a cms resource
044 * containing plain html data.<p>
045 *
046 * @since 6.0.0
047 */
048public class CmsDocumentHtml extends A_CmsVfsDocument {
049
050    /**
051     * Creates a new instance of this lucene document factory.<p>
052     *
053     * @param name name of the documenttype
054     */
055    public CmsDocumentHtml(String name) {
056
057        super(name);
058    }
059
060    /**
061     * Returns the raw text content of a given VFS resource containing HTML data.<p>
062     *
063     * @see org.opencms.search.documents.I_CmsSearchExtractor#extractContent(CmsObject, CmsResource, I_CmsSearchIndex)
064     */
065    public I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, I_CmsSearchIndex index)
066    throws CmsIndexException, CmsException {
067
068        logContentExtraction(resource, index);
069        CmsFile file = readFile(cms, resource);
070        try {
071            CmsProperty encProp = cms.readPropertyObject(
072                resource,
073                CmsPropertyDefinition.PROPERTY_CONTENT_ENCODING,
074                true);
075            String encoding = encProp.getValue(OpenCms.getSystemInfo().getDefaultEncoding());
076            return CmsExtractorHtml.getExtractor().extractText(file.getContents(), encoding);
077        } catch (Exception e) {
078            throw new CmsIndexException(
079                Messages.get().container(Messages.ERR_TEXT_EXTRACTION_1, resource.getRootPath()),
080                e);
081        }
082    }
083
084    /**
085     * @see org.opencms.search.documents.I_CmsDocumentFactory#isLocaleDependend()
086     */
087    public boolean isLocaleDependend() {
088
089        return false;
090    }
091
092    /**
093     * @see org.opencms.search.documents.I_CmsDocumentFactory#isUsingCache()
094     */
095    public boolean isUsingCache() {
096
097        return true;
098    }
099}