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;

import java.io.InputStream;

import java.util.ArrayList;

import java.util.HashMap;

import java.util.Iterator;

import java.util.Set;

import javax.xml.parsers.DocumentBuilder;

import javax.xml.parsers.DocumentBuilderFactory;

import org.apache.commons.io.output.ByteArrayOutputStream;

import org.apache.commons.logging.Log;

import org.apache.commons.logging.LogFactory;

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

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

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

import org.dataone.service.util.TypeMarshaller;

import org.jibx.runtime.JiBXException;

import org.xml.sax.SAXException;

/**

 * A class does insert, update and remove indexes to a SOLR server

 * @author tao

 *

 */

public class SolrIndex {

    private static final String SOLRHOME = "solr.solr.home";

    private static final String SOLRSERVERNAME = "metacat-core";

    private SolrServer solrServer = null;

    private XMLNamespaceConfig xmlNamespaceConfig = null;

    private static DocumentBuilderFactory documentBuilderFactory = null;

    private static DocumentBuilder builder = null;

    private static XPathFactory xpathFactory = null;

    private static XPath xpath = null;

        documentBuilderFactory = DocumentBuilderFactory.newInstance();

        documentBuilderFactory.setNamespaceAware(true);

        try {

            builder = documentBuilderFactory.newDocumentBuilder();

        } catch (ParserConfigurationException e) {

            e.printStackTrace();

        }

        xpathFactory = XPathFactory.newInstance();

        xpath = xpathFactory.newXPath();

    }

     * Constructor

     * @throws IOException

         this.xmlNamespaceConfig = xmlNamespaceConfig;

         this.sysmetaSolrFields = sysmetaSolrFields;

         initSolrServer();

         init();

        System.setProperty(SOLRHOME, SOLRHOMEPATH);

        CoreContainer.Initializer init = new CoreContainer.Initializer();

        CoreContainer c = init.initialize();

        solrServer = new EmbeddedSolrServer(c, "collection1");

    }

        xpath.setNamespaceContext(xmlNamespaceConfig);

        initExpressions();

    }

    private void initExpressions() throws XPathExpressionException {

        for (SolrField field : sysmetaSolrFields) {

            field.initExpression(xpath);

        }

    }

     * Get the list of the Subprocessors in this index.

     * @return the list of the Subprocessors.

     */

    public List<IDocumentSubprocessor> getSubprocessors() {

        return subprocessors;

    }

    /**

     * Set the list of Subprocessors.

     * @param subprocessorList  the list will be set.

     */

    public void setSubprocessors(List<IDocumentSubprocessor> subprocessorList) {

    }

    /**

     * Generate the index for the given information

     * @param id

     * @return

     * @throws IOException

     * @throws SAXException

     * @throws ParserConfigurationException

     * @throws XPathExpressionException

     */

        // Load the System Metadata document

        TypeMarshaller.marshalTypeToOutputStream(systemMetadata, systemMetadataOutputStream);

        ByteArrayInputStream systemMetadataStream = new ByteArrayInputStream(systemMetadataOutputStream.toByteArray());

        Document sysMetaDoc = generateXmlDocument(systemMetadataStream);

            log.error("Could not load System metadata for ID: " + id);

            return null;

        }

        // Extract the field values from the System Metadata

        List<SolrElementField> sysSolrFields = processSysmetaFields(sysMetaDoc, id);

        SolrDoc indexDocument = new SolrDoc(sysSolrFields);

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

        docs.put(id, indexDocument);

        // Determine if subprocessors are available for this ID

        if (subprocessors != null) {

                    // for each subprocessor loaded from the spring config

                    for (IDocumentSubprocessor subprocessor : subprocessors) {

                        // Does this subprocessor apply?

                        if (subprocessor.canProcess(sysMetaDoc)) {

                            // if so, then extract the additional information from the

                            // document.

                            try {

                                // docObject = the resource map document or science

                                // metadata document.

                                // note that resource map processing touches all objects

                                // referenced by the resource map.

                                Document docObject = generateXmlDocument(dataStream);

                                if (docObject == null) {

                                    log.error("Could not load OBJECT for ID " + id );

                                } else {

                                    docs = subprocessor.processDocument(id, docs, docObject);

                                }

                            } catch (Exception e) {

                                log.error(e.getStackTrace().toString());

                            }

                        }

                    }

       }

       // TODO: in the XPathDocumentParser class in d1_cn_index_process module,

       // merge is only for resource map. We need more work here.

       for (SolrDoc mergeDoc : docs.values()) {

           if (!mergeDoc.isMerged()) {

                 //mergeWithIndexedDocument(mergeDoc);

           }

       }

       //SolrElementAdd addCommand = getAddCommand(new ArrayList<SolrDoc>(docs.values()));

       return docs;

    }

    /*

     * Generate a Document from the InputStream

     */

    private Document generateXmlDocument(InputStream smdStream) throws SAXException {

        Document doc = null;

        try {

            doc = builder.parse(smdStream);

        } catch (IOException e) {

            log.error(e.getMessage(), e);

        }

        return doc;

    }

    /*

     * Index the fields of the system metadata

     */

    private List<SolrElementField> processSysmetaFields(Document doc, String identifier) {

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

        // solrFields is the list of fields defined in the application context

        for (SolrField field : sysmetaSolrFields) {

            try {

                // the field.getFields method can return a single value or

                // multiple values for multi-valued fields

                // or can return multiple SOLR document fields.

                fieldList.addAll(field.getFields(doc, identifier));

            } catch (Exception e) {

                e.printStackTrace();

            }

        }

        return fieldList;

    }

    /**

     * Generate indexes for a newly inserted document.

     * @param pid  the id of this document

     * @param systemMetadata  the system metadata associated with the data object

     * @param data  the data object itself

     * @throws SolrServerException

        //transform the Map to the SolrInputDocument which can be used by the solr server

        if(docs != null) {

            Set<String> ids = docs.keySet();

            for(String id : ids) {

                SolrInputDocument solrDoc = new SolrInputDocument();

                if(id != null) {

                    SolrDoc doc = docs.get(id);

                    if(doc != null) {

                        List<SolrElementField> list = doc.getFieldList();

                        if(list != null) {

                            while (iterator.hasNext()) {

                                SolrElementField field = iterator.next();

                                if(field != null) {

                                    String value = field.getValue();

                                    String name = field.getName();

                                }

                            }

                        }

                    }

                }

                if(!solrDoc.isEmpty()) {

                    solrServer.commit();

            }

        }

    }

    /**

     * Remove the indexed associated with specified pid.

     * @param pid  the pid which the indexes are associated with

     * @throws IOException

     * @throws SolrServerException

     */

    public void remove(String pid) throws IOException, SolrServerException {

        solrServer.commit();

    }