1
|
/**
|
2
|
* '$RCSfile$'
|
3
|
* Purpose: A class that gets Accession Number, check for uniqueness
|
4
|
* and register it into db
|
5
|
* Copyright: 2000 Regents of the University of California and the
|
6
|
* National Center for Ecological Analysis and Synthesis
|
7
|
* Authors: Jivka Bojilova, Matt Jones
|
8
|
*
|
9
|
* '$Author: leinfelder $'
|
10
|
* '$Date: 2011-11-02 20:40:12 -0700 (Wed, 02 Nov 2011) $'
|
11
|
* '$Revision: 6595 $'
|
12
|
*
|
13
|
* This program is free software; you can redistribute it and/or modify
|
14
|
* it under the terms of the GNU General Public License as published by
|
15
|
* the Free Software Foundation; either version 2 of the License, or
|
16
|
* (at your option) any later version.
|
17
|
*
|
18
|
* This program is distributed in the hope that it will be useful,
|
19
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
21
|
* GNU General Public License for more details.
|
22
|
*
|
23
|
* You should have received a copy of the GNU General Public License
|
24
|
* along with this program; if not, write to the Free Software
|
25
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
26
|
*/
|
27
|
package edu.ucsb.nceas.metacat.index.resourcemap;
|
28
|
|
29
|
import java.io.ByteArrayInputStream;
|
30
|
import java.io.ByteArrayOutputStream;
|
31
|
import java.io.IOException;
|
32
|
import java.io.InputStream;
|
33
|
import java.io.StringWriter;
|
34
|
import java.io.Writer;
|
35
|
import java.net.MalformedURLException;
|
36
|
import java.util.ArrayList;
|
37
|
import java.util.Collections;
|
38
|
import java.util.Date;
|
39
|
import java.util.HashMap;
|
40
|
import java.util.List;
|
41
|
import java.util.Map;
|
42
|
import java.util.Set;
|
43
|
|
44
|
import javax.xml.parsers.DocumentBuilder;
|
45
|
import javax.xml.parsers.DocumentBuilderFactory;
|
46
|
import javax.xml.parsers.ParserConfigurationException;
|
47
|
import javax.xml.xpath.XPathConstants;
|
48
|
import javax.xml.xpath.XPathExpressionException;
|
49
|
import javax.xml.xpath.XPathFactory;
|
50
|
|
51
|
import org.apache.commons.codec.EncoderException;
|
52
|
import org.apache.commons.logging.Log;
|
53
|
import org.apache.commons.logging.LogFactory;
|
54
|
import org.apache.solr.client.solrj.SolrServer;
|
55
|
import org.apache.solr.client.solrj.SolrServerException;
|
56
|
import org.apache.solr.client.solrj.response.QueryResponse;
|
57
|
import org.apache.solr.common.SolrDocument;
|
58
|
import org.apache.solr.common.SolrDocumentList;
|
59
|
import org.apache.solr.common.params.SolrParams;
|
60
|
import org.apache.solr.core.CoreContainer;
|
61
|
import org.apache.solr.core.SolrCore;
|
62
|
import org.apache.solr.request.LocalSolrQueryRequest;
|
63
|
import org.apache.solr.response.QueryResponseWriter;
|
64
|
import org.apache.solr.response.SolrQueryResponse;
|
65
|
import org.apache.solr.schema.DateField;
|
66
|
import org.apache.solr.schema.IndexSchema;
|
67
|
import org.apache.solr.schema.SchemaField;
|
68
|
import org.apache.solr.servlet.SolrRequestParsers;
|
69
|
import org.dataone.cn.indexer.parser.AbstractDocumentSubprocessor;
|
70
|
import org.dataone.cn.indexer.parser.IDocumentSubprocessor;
|
71
|
import org.dataone.cn.indexer.resourcemap.ResourceMap;
|
72
|
import org.dataone.cn.indexer.solrhttp.SolrDoc;
|
73
|
import org.dataone.cn.indexer.solrhttp.SolrElementField;
|
74
|
import org.dataone.service.exceptions.NotFound;
|
75
|
import org.dataone.service.exceptions.NotImplemented;
|
76
|
import org.dataone.service.exceptions.UnsupportedType;
|
77
|
import org.dataone.service.types.v1.Subject;
|
78
|
import org.w3c.dom.Document;
|
79
|
import org.w3c.dom.Element;
|
80
|
import org.w3c.dom.NodeList;
|
81
|
import org.xml.sax.SAXException;
|
82
|
|
83
|
import edu.ucsb.nceas.metacat.common.query.SolrQueryResponseTransformer;
|
84
|
import edu.ucsb.nceas.metacat.common.query.SolrQueryResponseWriterFactory;
|
85
|
import edu.ucsb.nceas.metacat.common.query.SolrQueryServiceController;
|
86
|
import edu.ucsb.nceas.metacat.common.SolrServerFactory;
|
87
|
import edu.ucsb.nceas.metacat.index.SolrIndex;
|
88
|
|
89
|
|
90
|
/**
|
91
|
* A solr index parser for the ResourceMap file.
|
92
|
* The solr doc of the ResourceMap self only has the system metadata information.
|
93
|
* The solr docs of the science metadata doc and data file have the resource map package information.
|
94
|
*/
|
95
|
public class ResourceMapSubprocessor extends AbstractDocumentSubprocessor implements IDocumentSubprocessor {
|
96
|
|
97
|
private static final String QUERY ="q=id:";
|
98
|
private static Log log = LogFactory.getLog(SolrIndex.class);
|
99
|
private static SolrServer solrServer = null;
|
100
|
private static SolrCore solrCore = null;
|
101
|
private static CoreContainer solrCoreContainer = null;
|
102
|
static {
|
103
|
try {
|
104
|
solrServer = SolrServerFactory.createSolrServer();
|
105
|
CoreContainer solrCoreContainer = SolrServerFactory.getCoreContainer();
|
106
|
String coreName = SolrServerFactory.getCollectionName();
|
107
|
solrCore = solrCoreContainer.getCore(coreName);
|
108
|
} catch (Exception e) {
|
109
|
log.error("ResourceMapSubprocessor - can't generate the SolrServer since - "+e.getMessage());
|
110
|
}
|
111
|
}
|
112
|
|
113
|
@Override
|
114
|
public Map<String, SolrDoc> processDocument(String identifier, Map<String, SolrDoc> docs,
|
115
|
Document doc) throws IOException, EncoderException, SAXException,
|
116
|
XPathExpressionException, ParserConfigurationException, SolrServerException, NotImplemented, NotFound, UnsupportedType {
|
117
|
SolrDoc resourceMapDoc = docs.get(identifier);
|
118
|
List<SolrDoc> processedDocs = processResourceMap(resourceMapDoc, doc);
|
119
|
Map<String, SolrDoc> processedDocsMap = new HashMap<String, SolrDoc>();
|
120
|
for (SolrDoc processedDoc : processedDocs) {
|
121
|
processedDocsMap.put(processedDoc.getIdentifier(), processedDoc);
|
122
|
}
|
123
|
return processedDocsMap;
|
124
|
}
|
125
|
|
126
|
private List<SolrDoc> processResourceMap(SolrDoc indexDocument, Document resourceMapDocument)
|
127
|
throws XPathExpressionException, IOException, SAXException, ParserConfigurationException, EncoderException, SolrServerException, NotImplemented, NotFound, UnsupportedType{
|
128
|
ResourceMap resourceMap = new ResourceMap(resourceMapDocument);
|
129
|
List<String> documentIds = resourceMap.getAllDocumentIDs();//this list includes the resourceMap id itself.
|
130
|
//List<SolrDoc> updateDocuments = getHttpService().getDocuments(getSolrQueryUri(), documentIds);
|
131
|
List<SolrDoc> updateDocuments = getSolrDocs(resourceMap.getIdentifier(), documentIds);
|
132
|
List<SolrDoc> mergedDocuments = resourceMap.mergeIndexedDocuments(updateDocuments);
|
133
|
/*if(mergedDocuments != null) {
|
134
|
for(SolrDoc doc : mergedDocuments) {
|
135
|
ByteArrayOutputStream out = new ByteArrayOutputStream();
|
136
|
doc.serialize(out, "UTF-8");
|
137
|
String result = new String(out.toByteArray(), "UTF-8");
|
138
|
System.out.println("after updated document===========================");
|
139
|
System.out.println(result);
|
140
|
}
|
141
|
}*/
|
142
|
mergedDocuments.add(indexDocument);
|
143
|
return mergedDocuments;
|
144
|
}
|
145
|
|
146
|
private List<SolrDoc> getSolrDocs(String resourceMapId, List<String> ids) throws SolrServerException, IOException, ParserConfigurationException, SAXException, XPathExpressionException, NotImplemented, NotFound, UnsupportedType {
|
147
|
List<SolrDoc> list = new ArrayList<SolrDoc>();
|
148
|
if(ids != null) {
|
149
|
for(String id : ids) {
|
150
|
SolrDoc doc = getSolrDoc(id);
|
151
|
if(doc != null) {
|
152
|
list.add(doc);
|
153
|
} else if ( !id.equals(resourceMapId)) {
|
154
|
throw new SolrServerException("Solr index doesn't have the information about the id "+id+" which is a component in the resource map "+resourceMapId+". Metacat-Index can't process the resource map prior to its components.");
|
155
|
}
|
156
|
}
|
157
|
}
|
158
|
return list;
|
159
|
}
|
160
|
|
161
|
/*
|
162
|
* Get the SolrDoc list for the list of the ids.
|
163
|
*/
|
164
|
public static List<SolrDoc> getSolrDocs(List<String> ids) throws SolrServerException, IOException, ParserConfigurationException, SAXException, XPathExpressionException, NotImplemented, NotFound, UnsupportedType {
|
165
|
List<SolrDoc> list = new ArrayList<SolrDoc>();
|
166
|
if(ids != null) {
|
167
|
for(String id : ids) {
|
168
|
SolrDoc doc = getSolrDoc(id);
|
169
|
if(doc != null) {
|
170
|
list.add(doc);
|
171
|
}
|
172
|
}
|
173
|
}
|
174
|
return list;
|
175
|
}
|
176
|
|
177
|
/*
|
178
|
* Get the SolrDoc for the specified id
|
179
|
*/
|
180
|
public static SolrDoc getSolrDoc(String id) throws SolrServerException, IOException, ParserConfigurationException, SAXException, XPathExpressionException, NotImplemented, NotFound, UnsupportedType {
|
181
|
SolrDoc solrDoc = null;
|
182
|
if(solrServer != null) {
|
183
|
String query = QUERY+"\""+id+"\"";
|
184
|
SolrParams solrParams = SolrRequestParsers.parseQueryString(query);
|
185
|
Set<Subject>subjects = null;//when subjects are null, there will not be any access rules.
|
186
|
InputStream response = SolrQueryServiceController.getInstance().query(solrParams, subjects);
|
187
|
solrDoc = transformQueryResponseToSolrDoc(solrParams, response);
|
188
|
|
189
|
/*if(solrDoc != null) {
|
190
|
ByteArrayOutputStream out = new ByteArrayOutputStream();
|
191
|
solrDoc.serialize(out, "UTF-8");
|
192
|
String result = new String(out.toByteArray(), "UTF-8");
|
193
|
System.out.println("need to be updated document ===========================");
|
194
|
System.out.println(result);
|
195
|
}*/
|
196
|
|
197
|
}
|
198
|
return solrDoc;
|
199
|
}
|
200
|
|
201
|
/*
|
202
|
* Transform a Solr QueryReponse to a SolrDoc. The QueryReponse contains a list of
|
203
|
* SolrDocuments. This method will transform the first SolrDocuments (in the Solr lib) to
|
204
|
* the SolrDoc (in the d1_cn_index_processor lib).
|
205
|
* @param reponse
|
206
|
* @return
|
207
|
*/
|
208
|
private static SolrDoc transformQueryResponseToSolrDoc(SolrParams solrParams, InputStream response) throws SolrServerException, IOException, ParserConfigurationException, SAXException, XPathExpressionException, UnsupportedType, NotFound {
|
209
|
SolrDoc solrDoc = null;
|
210
|
if(response != null) {
|
211
|
DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
|
212
|
DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
|
213
|
Document doc = dBuilder.parse(response);
|
214
|
solrDoc = parseResults(doc);
|
215
|
}
|
216
|
return solrDoc;
|
217
|
}
|
218
|
|
219
|
|
220
|
|
221
|
/*
|
222
|
* Parse the query result document. This method only choose the first one from a list.
|
223
|
*/
|
224
|
private static SolrDoc parseResults(Document document) throws XPathExpressionException, MalformedURLException, UnsupportedType, NotFound, ParserConfigurationException, IOException, SAXException {
|
225
|
SolrDoc solrDoc = null;
|
226
|
NodeList nodeList = (NodeList) XPathFactory.newInstance().newXPath()
|
227
|
.evaluate("/response/result/doc", document, XPathConstants.NODESET);
|
228
|
if(nodeList != null && nodeList.getLength() >0) {
|
229
|
Element docElement = (Element) nodeList.item(0);
|
230
|
solrDoc = parseDoc(docElement);
|
231
|
}
|
232
|
return solrDoc;
|
233
|
}
|
234
|
|
235
|
|
236
|
/*
|
237
|
* Parse an element
|
238
|
*/
|
239
|
private static SolrDoc parseDoc(Element docElement) throws MalformedURLException, UnsupportedType, NotFound, ParserConfigurationException, IOException, SAXException {
|
240
|
List<String> validSolrFieldNames = SolrQueryServiceController.getInstance().getValidSchemaFields();
|
241
|
SolrDoc doc = new SolrDoc();
|
242
|
doc.LoadFromElement(docElement, validSolrFieldNames);
|
243
|
return doc;
|
244
|
}
|
245
|
|
246
|
|
247
|
/**
|
248
|
* Get the valid schema fields from the solr server.
|
249
|
* @return
|
250
|
*/
|
251
|
/*private static List<String> getValidSchemaField() {
|
252
|
List<String> validSolrFieldNames = new ArrayList<String>();
|
253
|
IndexSchema schema = solrCore.getSchema();
|
254
|
Map<String, SchemaField> fieldMap = schema.getFields();
|
255
|
Set<String> fieldNames = fieldMap.keySet();
|
256
|
for(String fieldName : fieldNames) {
|
257
|
SchemaField field = fieldMap.get(fieldName);
|
258
|
//remove the field which is the target field of a CopyField.
|
259
|
if(field != null && !schema.isCopyFieldTarget(field)) {
|
260
|
validSolrFieldNames.add(fieldName);
|
261
|
}
|
262
|
}
|
263
|
//System.out.println("the valid file name is\n"+validSolrFieldNames);
|
264
|
return validSolrFieldNames;
|
265
|
}*/
|
266
|
|
267
|
}
|