Metacat

/**

 *  '$RCSfile$'

 *    Purpose: A class that gets Accession Number, check for uniqueness

 *             and register it into db

 *  Copyright: 2000 Regents of the University of California and the

 *             National Center for Ecological Analysis and Synthesis

 *    Authors: Jivka Bojilova, Matt Jones

 *

 *   '$Author: leinfelder $'

 *     '$Date: 2011-11-02 20:40:12 -0700 (Wed, 02 Nov 2011) $'

 * '$Revision: 6595 $'

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program 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 General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

 */

package edu.ucsb.nceas.metacat.index.resourcemap;

import java.io.IOException;

import java.util.ArrayList;

import java.util.HashMap;

import java.util.List;

import java.util.Map;

import java.util.Set;

import javax.xml.parsers.ParserConfigurationException;

import javax.xml.xpath.XPathExpressionException;

import org.apache.commons.codec.EncoderException;

import org.apache.commons.logging.Log;

import org.apache.commons.logging.LogFactory;

import org.apache.solr.client.solrj.SolrServer;

import org.apache.solr.client.solrj.SolrServerException;

import org.apache.solr.client.solrj.response.QueryResponse;

import org.apache.solr.common.SolrDocument;

import org.apache.solr.common.SolrDocumentList;

import org.apache.solr.common.params.SolrParams;

import org.apache.solr.servlet.SolrRequestParsers;

import org.dataone.cn.indexer.parser.AbstractDocumentSubprocessor;

import org.dataone.cn.indexer.parser.IDocumentSubprocessor;

import org.dataone.cn.indexer.resourcemap.ResourceMap;

import org.dataone.cn.indexer.solrhttp.HTTPService;

import org.dataone.cn.indexer.solrhttp.SolrDoc;

import org.dataone.cn.indexer.solrhttp.SolrElementField;

import org.w3c.dom.Document;

import org.xml.sax.SAXException;

import edu.ucsb.nceas.metacat.common.SolrServerFactory;

import edu.ucsb.nceas.metacat.index.SolrIndex;

/**

 * A solr index parser for the ResourceMap file.

 * The solr doc of the ResourceMap self only has the system metadata information.

 * The solr docs of the science metadata doc and data file have the resource map package information.

 */

public class ResourceMapSubprocessor extends AbstractDocumentSubprocessor implements IDocumentSubprocessor {

    private static final String QUERY ="q=id:";

    private static Log log = LogFactory.getLog(SolrIndex.class);

    private static SolrServer solrServer =  null;

    static {

        try {

            solrServer = SolrServerFactory.createSolrServer();

        } catch (Exception e) {

            log.error("ResourceMapSubprocessor - can't generate the SolrServer since - "+e.getMessage());

        }

    }

    @Override

    public Map<String, SolrDoc> processDocument(String identifier, Map<String, SolrDoc> docs,

    Document doc) throws IOException, EncoderException, SAXException,

    XPathExpressionException, ParserConfigurationException, SolrServerException {

        SolrDoc resourceMapDoc = docs.get(identifier);

        List<SolrDoc> processedDocs = processResourceMap(resourceMapDoc, doc);

        Map<String, SolrDoc> processedDocsMap = new HashMap<String, SolrDoc>();

        for (SolrDoc processedDoc : processedDocs) {

            processedDocsMap.put(processedDoc.getIdentifier(), processedDoc);

        }

        return processedDocsMap;

    }

    private List<SolrDoc> processResourceMap(SolrDoc indexDocument, Document resourceMapDocument)

                    throws XPathExpressionException, IOException, SAXException, ParserConfigurationException, EncoderException, SolrServerException{

        ResourceMap resourceMap = new ResourceMap(resourceMapDocument);

        List<String> documentIds = resourceMap.getAllDocumentIDs();

        //List<SolrDoc> updateDocuments = getHttpService().getDocuments(getSolrQueryUri(), documentIds);

        List<SolrDoc> updateDocuments = getSolrDocs(documentIds);

        List<SolrDoc> mergedDocuments = resourceMap.mergeIndexedDocuments(updateDocuments);

        mergedDocuments.add(indexDocument);

        return mergedDocuments;

    }

    /*

     * Get the SolrDoc list for the list of the ids.

     */

    private List<SolrDoc> getSolrDocs(List<String> ids) throws SolrServerException {

        List<SolrDoc> list = new ArrayList<SolrDoc>();

        if(ids != null) {

            for(String id : ids) {

                SolrDoc doc = getSolrDoc(id);

                if(doc != null) {

                    list.add(doc);

                }

            }

        }

        return list;

    }

    /*

     * Get the SolrDoc for the specified id 

     */

    private SolrDoc getSolrDoc(String id) throws SolrServerException {

        SolrDoc solrDoc = null;

        if(solrServer != null) {

           String query = QUERY+"\""+id+"\"";

           SolrParams solrParams = SolrRequestParsers.parseQueryString(query);

           QueryResponse response = solrServer.query(solrParams);

           solrDoc = transformQueryResponseToSolrDoc(response);

        }

        return solrDoc;

    }

    /**

     * Transform a Solr QueryReponse to a SolrDoc. The QueryReponse contains a list of

     * SolrDocuments. This method will transform the first SolrDocuments (Solr lib) to

     * the SolrDoc (d1_cn_index_processor lib).

     * @param reponse

     * @return

     */

    public static SolrDoc transformQueryResponseToSolrDoc(QueryResponse reponse) {

        SolrDoc solrDoc = new SolrDoc();

        if(reponse != null) {

            SolrDocumentList list = reponse.getResults();

            if(list != null && !list.isEmpty()) {

                SolrDocument document = list.get(0);

                if(document != null) {

                    List<SolrElementField> elementFieldList = new ArrayList<SolrElementField>();

                    Set<String> keys = document.keySet();

                    for(String key :keys) {

                        Object value = document.get(key);

                        SolrElementField solrElement = new SolrElementField(key, value.toString());

                        elementFieldList.add(solrElement);

                    }

                    solrDoc.setFieldList(elementFieldList);

                }

            }

        }

        return solrDoc;

    }

}