1
|
/**
|
2
|
* Copyright (C) 2008 EDIT
|
3
|
* European Distributed Institute of Taxonomy
|
4
|
* http://www.e-taxonomy.eu
|
5
|
*
|
6
|
* The contents of this file are subject to the Mozilla Public License Version 1.1
|
7
|
* See LICENSE.TXT at the top of this package for the full license terms.
|
8
|
*/
|
9
|
|
10
|
package eu.etaxonomy.cdm.io.jaxb;
|
11
|
|
12
|
import java.io.ByteArrayOutputStream;
|
13
|
import java.io.File;
|
14
|
import java.io.FileNotFoundException;
|
15
|
import java.io.FileOutputStream;
|
16
|
import java.io.OutputStreamWriter;
|
17
|
import java.io.PrintWriter;
|
18
|
import java.io.UnsupportedEncodingException;
|
19
|
import java.util.ArrayList;
|
20
|
import java.util.List;
|
21
|
|
22
|
import javax.xml.transform.stream.StreamResult;
|
23
|
|
24
|
import org.apache.log4j.Logger;
|
25
|
import org.springframework.stereotype.Component;
|
26
|
import org.springframework.transaction.TransactionStatus;
|
27
|
|
28
|
import eu.etaxonomy.cdm.hibernate.HibernateProxyHelper;
|
29
|
import eu.etaxonomy.cdm.io.common.CdmExportBase;
|
30
|
import eu.etaxonomy.cdm.io.common.ICdmExport;
|
31
|
import eu.etaxonomy.cdm.io.common.IExportConfigurator;
|
32
|
import eu.etaxonomy.cdm.io.common.mapping.out.IExportTransformer;
|
33
|
import eu.etaxonomy.cdm.model.agent.AgentBase;
|
34
|
import eu.etaxonomy.cdm.model.common.User;
|
35
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
36
|
import eu.etaxonomy.cdm.model.occurrence.SpecimenOrObservationBase;
|
37
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
38
|
import eu.etaxonomy.cdm.model.taxon.Classification;
|
39
|
import eu.etaxonomy.cdm.model.taxon.TaxonBase;
|
40
|
import eu.etaxonomy.cdm.model.taxon.TaxonNode;
|
41
|
import eu.etaxonomy.cdm.model.term.DefinedTermBase;
|
42
|
import eu.etaxonomy.cdm.model.term.FeatureTree;
|
43
|
|
44
|
/**
|
45
|
* @author a.babadshanjan
|
46
|
* @since 25.09.2008
|
47
|
*/
|
48
|
@Component
|
49
|
public class JaxbExport
|
50
|
extends CdmExportBase<JaxbExportConfigurator, JaxbExportState, IExportTransformer, File>
|
51
|
implements ICdmExport<JaxbExportConfigurator, JaxbExportState> {
|
52
|
|
53
|
private static final long serialVersionUID = -525533131708894145L;
|
54
|
|
55
|
private static final Logger logger = Logger.getLogger(JaxbExport.class);
|
56
|
|
57
|
private DataSet dataSet;
|
58
|
|
59
|
/**
|
60
|
*
|
61
|
*/
|
62
|
public JaxbExport() {
|
63
|
super();
|
64
|
}
|
65
|
|
66
|
/**
|
67
|
* {@inheritDoc}
|
68
|
*
|
69
|
* .<BR>Retrieves data from a CDM DB and serializes them CDM to XML.
|
70
|
* Starts with root taxa and traverses the classification to retrieve children taxa, synonyms and relationships.
|
71
|
* Taxa that are not part of the classification are not found.
|
72
|
*/
|
73
|
@Override
|
74
|
protected void doInvoke(JaxbExportState state) {
|
75
|
|
76
|
JaxbExportConfigurator jaxbExpConfig = state.getConfig();
|
77
|
// String dbname = jaxbExpConfig.getSource().getName();
|
78
|
File file = jaxbExpConfig.getDestination();
|
79
|
// logger.info("Serializing DB " + dbname + " to file " + fileName);
|
80
|
// logger.debug("DbSchemaValidation = " + jaxbExpConfig.getDbSchemaValidation());
|
81
|
|
82
|
TransactionStatus txStatus = null;
|
83
|
|
84
|
txStatus = startTransaction(true);
|
85
|
|
86
|
dataSet = new DataSet();
|
87
|
|
88
|
// get data from DB
|
89
|
|
90
|
try {
|
91
|
logger.info("Retrieving data from DB");
|
92
|
|
93
|
retrieveData(jaxbExpConfig, dataSet);
|
94
|
|
95
|
} catch (Exception e) {
|
96
|
logger.error("Error retrieving data");
|
97
|
e.printStackTrace();
|
98
|
}
|
99
|
|
100
|
logger.info("All data retrieved");
|
101
|
|
102
|
try {
|
103
|
switch(jaxbExpConfig.getTarget()) {
|
104
|
case FILE:
|
105
|
writeToFile(file, dataSet);
|
106
|
break;
|
107
|
case EXPORT_DATA:
|
108
|
CdmDocumentBuilder cdmDocumentBuilder = new CdmDocumentBuilder();
|
109
|
exportStream = new ByteArrayOutputStream();
|
110
|
cdmDocumentBuilder.marshal(dataSet, new StreamResult(exportStream));
|
111
|
state.getResult().addExportData((byte[])this.createExportData().getExportData());
|
112
|
|
113
|
break;
|
114
|
default:
|
115
|
break;
|
116
|
}
|
117
|
} catch (Exception e) {
|
118
|
logger.error("Marshalling error");
|
119
|
e.printStackTrace();
|
120
|
}
|
121
|
|
122
|
commitTransaction(txStatus);
|
123
|
|
124
|
return;
|
125
|
|
126
|
}
|
127
|
|
128
|
public static void writeToFile(File file, DataSet dataSet) throws UnsupportedEncodingException, FileNotFoundException {
|
129
|
CdmDocumentBuilder cdmDocumentBuilder = new CdmDocumentBuilder();
|
130
|
PrintWriter writer = new PrintWriter(new OutputStreamWriter(new FileOutputStream(file), "UTF8"), true);
|
131
|
cdmDocumentBuilder.marshal(dataSet, writer);
|
132
|
|
133
|
// TODO: Split into one file per data set member to see whether performance improves?
|
134
|
|
135
|
logger.info("XML file written");
|
136
|
logger.info("Filename is: " + file.getAbsolutePath());
|
137
|
}
|
138
|
|
139
|
private void retrieveData (IExportConfigurator config, DataSet dataSet) {
|
140
|
|
141
|
JaxbExportConfigurator jaxbExpConfig = (JaxbExportConfigurator)config;
|
142
|
final int MAX_ROWS = 50000;
|
143
|
int numberOfRows = jaxbExpConfig.getMaxRows();
|
144
|
|
145
|
int agentRows = numberOfRows;
|
146
|
int definedTermBaseRows = numberOfRows;
|
147
|
int referenceBaseRows = numberOfRows;
|
148
|
int taxonNameRows = numberOfRows;
|
149
|
int taxonBaseRows = numberOfRows;
|
150
|
int taxonNodeRows = numberOfRows;
|
151
|
int relationshipRows = numberOfRows;
|
152
|
int occurrencesRows = numberOfRows;
|
153
|
int mediaRows = numberOfRows;
|
154
|
int featureDataRows = numberOfRows;
|
155
|
int classificationDataRows = numberOfRows;
|
156
|
int languageDataRows = numberOfRows;
|
157
|
int termVocabularyRows = numberOfRows;
|
158
|
int homotypicalGroupRows = numberOfRows;
|
159
|
int UserRows= numberOfRows;
|
160
|
|
161
|
if (jaxbExpConfig.isDoUsers() == true) {
|
162
|
|
163
|
if (UserRows == 0) { UserRows = MAX_ROWS; }
|
164
|
logger.info("# User");
|
165
|
List<User> users = getUserService().list(null, UserRows, 0, null, null);
|
166
|
|
167
|
|
168
|
for (User user: users){
|
169
|
dataSet.addUser(HibernateProxyHelper.deproxy(user));
|
170
|
}
|
171
|
|
172
|
}
|
173
|
if (jaxbExpConfig.isDoTermVocabularies() == true) {
|
174
|
if (termVocabularyRows == 0) { termVocabularyRows = MAX_ROWS; }
|
175
|
logger.info("# TermVocabulary");
|
176
|
dataSet.setTermVocabularies((List)getVocabularyService().list(null,termVocabularyRows, 0, null, null));
|
177
|
}
|
178
|
|
179
|
|
180
|
|
181
|
// if (jaxbExpConfig.isDoLanguageData() == true) {
|
182
|
// if (languageDataRows == 0) { languageDataRows = MAX_ROWS; }
|
183
|
// logger.info("# Representation, Language String");
|
184
|
// dataSet.setLanguageData(getTermService().getAllRepresentations(MAX_ROWS, 0));
|
185
|
//TODO!!!
|
186
|
dataSet.setLanguageStrings(getTermService().getAllLanguageStrings(MAX_ROWS, 0));
|
187
|
// }
|
188
|
|
189
|
if (jaxbExpConfig.isDoTerms() == true) {
|
190
|
if (definedTermBaseRows == 0) { definedTermBaseRows = getTermService().count(DefinedTermBase.class); }
|
191
|
logger.info("# DefinedTermBase: " + definedTermBaseRows);
|
192
|
dataSet.setTerms(getTermService().list(null,definedTermBaseRows, 0,null,null));
|
193
|
}
|
194
|
|
195
|
if (jaxbExpConfig.isDoAuthors() == true) {
|
196
|
if (agentRows == 0) { agentRows = getAgentService().count(AgentBase.class); }
|
197
|
logger.info("# Agents: " + agentRows);
|
198
|
//logger.info(" # Team: " + appCtr.getAgentService().count(Team.class));
|
199
|
dataSet.setAgents(getAgentService().list(null,agentRows, 0,null,null));
|
200
|
}
|
201
|
|
202
|
|
203
|
|
204
|
if (jaxbExpConfig.getDoReferences() != IExportConfigurator.DO_REFERENCES.NONE) {
|
205
|
if (referenceBaseRows == 0) { referenceBaseRows = getReferenceService().count(Reference.class); }
|
206
|
logger.info("# Reference: " + referenceBaseRows);
|
207
|
dataSet.setReferences(getReferenceService().list(null,referenceBaseRows, 0,null,null));
|
208
|
}
|
209
|
|
210
|
if (jaxbExpConfig.isDoHomotypicalGroups() == true) {
|
211
|
if (homotypicalGroupRows == 0) { homotypicalGroupRows = MAX_ROWS; }
|
212
|
logger.info("# Homotypical Groups");
|
213
|
dataSet.setHomotypicalGroups(getNameService().getAllHomotypicalGroups(homotypicalGroupRows, 0));
|
214
|
}
|
215
|
|
216
|
if (jaxbExpConfig.isDoTaxonNames() == true) {
|
217
|
if (taxonNameRows == 0) { taxonNameRows = getNameService().count(TaxonName.class); }
|
218
|
logger.info("# TaxonName: " + taxonNameRows);
|
219
|
//logger.info(" # Taxon: " + getNameService().count(BotanicalName.class));
|
220
|
dataSet.setTaxonomicNames(getNameService().list(null,taxonNameRows, 0,null,null));
|
221
|
}
|
222
|
|
223
|
|
224
|
|
225
|
if (jaxbExpConfig.isDoTaxa() == true) {
|
226
|
if (taxonBaseRows == 0) { taxonBaseRows = getTaxonService().count(TaxonBase.class); }
|
227
|
logger.info("# TaxonBase: " + taxonBaseRows);
|
228
|
// dataSet.setTaxa(new ArrayList<Taxon>());
|
229
|
// dataSet.setSynonyms(new ArrayList<Synonym>());
|
230
|
List<TaxonBase> tb = getTaxonService().list(null,taxonBaseRows, 0,null,null);
|
231
|
for (TaxonBase taxonBase : tb) {
|
232
|
dataSet.addTaxonBase(HibernateProxyHelper.deproxy(taxonBase));
|
233
|
}
|
234
|
}
|
235
|
|
236
|
// TODO:
|
237
|
// retrieve taxa and synonyms separately
|
238
|
// need correct count for taxa and synonyms
|
239
|
// if (taxonBaseRows == 0) { taxonBaseRows = getTaxonService().count(TaxonBase.class); }
|
240
|
// logger.info("# Synonym: " + taxonBaseRows);
|
241
|
// dataSet.setSynonyms(new ArrayList<Synonym>());
|
242
|
// dataSet.setSynonyms(getTaxonService().getAllSynonyms(taxonBaseRows, 0));
|
243
|
|
244
|
// if (jaxbExpConfig.isDoRelTaxa() == true) {
|
245
|
// if (relationshipRows == 0) { relationshipRows = MAX_ROWS; }
|
246
|
// logger.info("# Relationships");
|
247
|
// List<RelationshipBase> relationList = getTaxonService().getAllRelationships(relationshipRows, 0);
|
248
|
// Set<RelationshipBase> relationSet = new HashSet<RelationshipBase>(relationList);
|
249
|
// dataSet.setRelationships(relationSet);
|
250
|
// }
|
251
|
if (jaxbExpConfig.isDoOccurrence() == true) {
|
252
|
if (occurrencesRows == 0) { occurrencesRows = getOccurrenceService().count(SpecimenOrObservationBase.class); }
|
253
|
logger.info("# SpecimenOrObservationBase: " + occurrencesRows);
|
254
|
List<SpecimenOrObservationBase> occurrenceList = getOccurrenceService().list(null,occurrencesRows, 0,null,null);
|
255
|
/*List<SpecimenOrObservationBase> noProxyList = new ArrayList<SpecimenOrObservationBase>();
|
256
|
for (SpecimenOrObservationBase specimen : occurrenceList){
|
257
|
specimen = (SpecimenOrObservationBase)HibernateProxyHelper.deproxy(specimen);
|
258
|
noProxyList.add(specimen);
|
259
|
}*/
|
260
|
dataSet.setOccurrences(occurrenceList);
|
261
|
}
|
262
|
|
263
|
if (jaxbExpConfig.isDoTypeDesignations() == true) {
|
264
|
logger.info("# TypeDesignations");
|
265
|
dataSet.addTypeDesignations(getNameService().getAllTypeDesignations(MAX_ROWS, 0));
|
266
|
}
|
267
|
|
268
|
|
269
|
|
270
|
if (jaxbExpConfig.isDoMedia() == true) {
|
271
|
if (mediaRows == 0) { mediaRows = MAX_ROWS; }
|
272
|
logger.info("# Media");
|
273
|
dataSet.setMedia(getMediaService().list(null,mediaRows, 0,null,null));
|
274
|
// dataSet.addMedia(getMediaService().getAllMediaRepresentations(mediaRows, 0));
|
275
|
// dataSet.addMedia(getMediaService().getAllMediaRepresentationParts(mediaRows, 0));
|
276
|
}
|
277
|
|
278
|
if (jaxbExpConfig.isDoFeatureData() == true) {
|
279
|
if (featureDataRows == 0) { featureDataRows = MAX_ROWS; }
|
280
|
logger.info("# Feature Tree, Feature Node");
|
281
|
List<FeatureTree> featureTrees = new ArrayList<FeatureTree>();
|
282
|
featureTrees= getFeatureTreeService().list(null,featureDataRows, 0, null, null);
|
283
|
List<FeatureTree> taxTreesdeproxy = new ArrayList<FeatureTree>();
|
284
|
for (FeatureTree featureTree : featureTrees){
|
285
|
HibernateProxyHelper.deproxy(featureTree);
|
286
|
taxTreesdeproxy.add(featureTree);
|
287
|
}
|
288
|
|
289
|
dataSet.setFeatureTrees(getFeatureTreeService().list(null,null,null,null,null));
|
290
|
}
|
291
|
if (jaxbExpConfig.isDoClassificationData() == true) {
|
292
|
if (classificationDataRows == 0) { classificationDataRows = MAX_ROWS; }
|
293
|
logger.info("# Classification");
|
294
|
|
295
|
|
296
|
List<Classification> taxTrees = new ArrayList<Classification>();
|
297
|
taxTrees= getClassificationService().list(null,classificationDataRows, 0, null, null);
|
298
|
|
299
|
List<Classification> taxTreesdeproxy = new ArrayList<Classification>();
|
300
|
for (Classification taxTree : taxTrees){
|
301
|
HibernateProxyHelper.deproxy(taxTree);
|
302
|
taxTreesdeproxy.add(taxTree);
|
303
|
}
|
304
|
List<TaxonNode> taxNodes = new ArrayList<TaxonNode>();
|
305
|
taxNodes= getClassificationService().getAllNodes();
|
306
|
List<TaxonNode> taxNodesdeproxy = new ArrayList<TaxonNode>();
|
307
|
for (TaxonNode taxNode : taxNodes){
|
308
|
HibernateProxyHelper.deproxy(taxNode);
|
309
|
taxNodesdeproxy.add(taxNode);
|
310
|
}
|
311
|
|
312
|
dataSet.setTaxonNodes(taxNodesdeproxy);
|
313
|
dataSet.setClassifications(taxTreesdeproxy );
|
314
|
}
|
315
|
//TODO: FIXME!!!!!
|
316
|
dataSet.setLanguageStrings(null);
|
317
|
}
|
318
|
|
319
|
|
320
|
@Override
|
321
|
protected boolean doCheck(JaxbExportState state) {
|
322
|
boolean result = true;
|
323
|
logger.warn("No check implemented for Jaxb export");
|
324
|
return result;
|
325
|
}
|
326
|
|
327
|
|
328
|
@Override
|
329
|
protected boolean isIgnore(JaxbExportState state) {
|
330
|
return false;
|
331
|
}
|
332
|
|
333
|
|
334
|
|
335
|
}
|