/* * This library is part of OpenCms - * the Open Source Content Management System * * Copyright (c) Alkacon Software GmbH (http://www.alkacon.com) * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * For further information about Alkacon Software GmbH, please see the * company website: http://www.alkacon.com * * For further information about OpenCms, please see the * project website: http://www.opencms.org * * You should have received a copy of the GNU Lesser General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ package org.opencms.search.documents; import org.opencms.file.CmsFile; import org.opencms.file.CmsObject; import org.opencms.file.CmsResource; import org.opencms.main.CmsException; import org.opencms.search.CmsIndexException; import org.opencms.search.CmsSearchIndex; import org.opencms.search.extractors.CmsExtractionResult; import org.opencms.search.extractors.I_CmsExtractionResult; import org.opencms.util.CmsHtmlExtractor; import org.opencms.util.CmsStringUtil; import org.opencms.xml.page.CmsXmlPage; import org.opencms.xml.page.CmsXmlPageFactory; import java.util.HashMap; import java.util.Iterator; import java.util.List; import java.util.Locale; import java.util.Map; /** * Lucene document factory class to extract index data from a cms resource * of type <code>CmsResourceTypeXmlPage</code>.<p> * * @since 6.0.0 */ public class CmsDocumentXmlPage extends A_CmsVfsDocument { /** * Creates a new instance of this lucene document factory.<p> * * @param name name of the documenttype */ public CmsDocumentXmlPage(String name) { super(name); } /** * Returns the raw text content of a given vfs resource of type <code>CmsResourceTypeXmlPage</code>.<p> * * @see org.opencms.search.documents.I_CmsSearchExtractor#extractContent(CmsObject, CmsResource, CmsSearchIndex) */ public I_CmsExtractionResult extractContent(CmsObject cms, CmsResource resource, CmsSearchIndex index) throws CmsException { logContentExtraction(resource, index); try { CmsFile file = readFile(cms, resource); CmsXmlPage page = CmsXmlPageFactory.unmarshal(cms, file); Locale locale = index.getLocaleForResource(cms, resource, page.getLocales()); List<String> elements = page.getNames(locale); StringBuffer content = new StringBuffer(); Map<String, String> items = new HashMap<String, String>(); for (Iterator<String> i = elements.iterator(); i.hasNext();) { String elementName = i.next(); String value = page.getStringValue(cms, elementName, locale); String extracted = CmsHtmlExtractor.extractText(value, page.getEncoding()); if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(extracted)) { items.put(elementName, extracted); content.append(extracted); content.append('\n'); } } return new CmsExtractionResult(content.toString(), items); } catch (Exception e) { throw new CmsIndexException( Messages.get().container(Messages.ERR_TEXT_EXTRACTION_1, resource.getRootPath()), e); } } /** * @see org.opencms.search.documents.I_CmsDocumentFactory#isLocaleDependend() */ public boolean isLocaleDependend() { return true; } /** * @see org.opencms.search.documents.I_CmsDocumentFactory#isUsingCache() */ public boolean isUsingCache() { return true; } }