|
1
|
/**
|
|
2
|
* Copyright (C) 2017 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
|
package eu.etaxonomy.cdm.io.cdmLightWord;
|
|
10
|
|
|
11
|
import java.io.File;
|
|
12
|
import java.util.ArrayList;
|
|
13
|
import java.util.Collection;
|
|
14
|
import java.util.Collections;
|
|
15
|
import java.util.Comparator;
|
|
16
|
import java.util.HashMap;
|
|
17
|
import java.util.HashSet;
|
|
18
|
import java.util.Iterator;
|
|
19
|
import java.util.List;
|
|
20
|
import java.util.Map;
|
|
21
|
import java.util.Set;
|
|
22
|
import java.util.UUID;
|
|
23
|
|
|
24
|
import org.apache.commons.lang3.StringUtils;
|
|
25
|
import org.springframework.beans.factory.annotation.Autowired;
|
|
26
|
import org.springframework.stereotype.Component;
|
|
27
|
|
|
28
|
import eu.etaxonomy.cdm.api.service.dto.CondensedDistribution;
|
|
29
|
import eu.etaxonomy.cdm.api.service.name.TypeDesignationSetComparator;
|
|
30
|
import eu.etaxonomy.cdm.api.service.name.TypeDesignationSetContainer;
|
|
31
|
import eu.etaxonomy.cdm.api.service.name.TypeDesignationSetFormatter;
|
|
32
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
|
33
|
import eu.etaxonomy.cdm.common.monitor.IProgressMonitor;
|
|
34
|
import eu.etaxonomy.cdm.compare.name.TypeComparator;
|
|
35
|
import eu.etaxonomy.cdm.compare.taxon.HomotypicGroupTaxonComparator;
|
|
36
|
import eu.etaxonomy.cdm.ext.geo.IEditGeoService;
|
|
37
|
import eu.etaxonomy.cdm.filter.TaxonNodeFilter;
|
|
38
|
import eu.etaxonomy.cdm.format.reference.OriginalSourceFormatter;
|
|
39
|
import eu.etaxonomy.cdm.hibernate.HibernateProxyHelper;
|
|
40
|
import eu.etaxonomy.cdm.io.cdmLight.OrderHelper;
|
|
41
|
import eu.etaxonomy.cdm.io.common.CdmExportBase;
|
|
42
|
import eu.etaxonomy.cdm.io.common.ExportResult.ExportResultState;
|
|
43
|
import eu.etaxonomy.cdm.io.common.TaxonNodeOutStreamPartitioner;
|
|
44
|
import eu.etaxonomy.cdm.io.common.XmlExportState;
|
|
45
|
import eu.etaxonomy.cdm.io.common.mapping.out.IExportTransformer;
|
|
46
|
import eu.etaxonomy.cdm.model.agent.AgentBase;
|
|
47
|
import eu.etaxonomy.cdm.model.agent.Person;
|
|
48
|
import eu.etaxonomy.cdm.model.agent.Team;
|
|
49
|
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
|
|
50
|
import eu.etaxonomy.cdm.model.common.Annotation;
|
|
51
|
import eu.etaxonomy.cdm.model.common.AnnotationType;
|
|
52
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
|
53
|
import eu.etaxonomy.cdm.model.common.ICdmBase;
|
|
54
|
import eu.etaxonomy.cdm.model.common.IIdentifiableEntity;
|
|
55
|
import eu.etaxonomy.cdm.model.common.IdentifiableEntity;
|
|
56
|
import eu.etaxonomy.cdm.model.common.IdentifiableSource;
|
|
57
|
import eu.etaxonomy.cdm.model.common.Identifier;
|
|
58
|
import eu.etaxonomy.cdm.model.common.Language;
|
|
59
|
import eu.etaxonomy.cdm.model.common.LanguageString;
|
|
60
|
import eu.etaxonomy.cdm.model.description.CommonTaxonName;
|
|
61
|
import eu.etaxonomy.cdm.model.description.DescriptionBase;
|
|
62
|
import eu.etaxonomy.cdm.model.description.DescriptionElementBase;
|
|
63
|
import eu.etaxonomy.cdm.model.description.DescriptionElementSource;
|
|
64
|
import eu.etaxonomy.cdm.model.description.Distribution;
|
|
65
|
import eu.etaxonomy.cdm.model.description.Feature;
|
|
66
|
import eu.etaxonomy.cdm.model.description.IndividualsAssociation;
|
|
67
|
import eu.etaxonomy.cdm.model.description.TaxonDescription;
|
|
68
|
import eu.etaxonomy.cdm.model.description.TaxonInteraction;
|
|
69
|
import eu.etaxonomy.cdm.model.description.TaxonNameDescription;
|
|
70
|
import eu.etaxonomy.cdm.model.description.TextData;
|
|
71
|
import eu.etaxonomy.cdm.model.location.NamedArea;
|
|
72
|
import eu.etaxonomy.cdm.model.media.ExternalLink;
|
|
73
|
import eu.etaxonomy.cdm.model.media.Media;
|
|
74
|
import eu.etaxonomy.cdm.model.media.MediaRepresentation;
|
|
75
|
import eu.etaxonomy.cdm.model.media.MediaRepresentationPart;
|
|
76
|
import eu.etaxonomy.cdm.model.name.HomotypicalGroup;
|
|
77
|
import eu.etaxonomy.cdm.model.name.NameRelationship;
|
|
78
|
import eu.etaxonomy.cdm.model.name.NameRelationshipType;
|
|
79
|
import eu.etaxonomy.cdm.model.name.NameTypeDesignation;
|
|
80
|
import eu.etaxonomy.cdm.model.name.NomenclaturalSource;
|
|
81
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
|
|
82
|
import eu.etaxonomy.cdm.model.name.Rank;
|
|
83
|
import eu.etaxonomy.cdm.model.name.SpecimenTypeDesignation;
|
|
84
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
|
85
|
import eu.etaxonomy.cdm.model.name.TextualTypeDesignation;
|
|
86
|
import eu.etaxonomy.cdm.model.name.TypeDesignationBase;
|
|
87
|
import eu.etaxonomy.cdm.model.occurrence.DerivedUnit;
|
|
88
|
import eu.etaxonomy.cdm.model.occurrence.FieldUnit;
|
|
89
|
import eu.etaxonomy.cdm.model.occurrence.GatheringEvent;
|
|
90
|
import eu.etaxonomy.cdm.model.occurrence.MediaSpecimen;
|
|
91
|
import eu.etaxonomy.cdm.model.occurrence.SpecimenOrObservationBase;
|
|
92
|
import eu.etaxonomy.cdm.model.reference.NamedSource;
|
|
93
|
import eu.etaxonomy.cdm.model.reference.OriginalSourceType;
|
|
94
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
|
95
|
import eu.etaxonomy.cdm.model.reference.ReferenceType;
|
|
96
|
import eu.etaxonomy.cdm.model.taxon.Classification;
|
|
97
|
import eu.etaxonomy.cdm.model.taxon.Synonym;
|
|
98
|
import eu.etaxonomy.cdm.model.taxon.Taxon;
|
|
99
|
import eu.etaxonomy.cdm.model.taxon.TaxonBase;
|
|
100
|
import eu.etaxonomy.cdm.model.taxon.TaxonNode;
|
|
101
|
import eu.etaxonomy.cdm.model.taxon.TaxonRelationship;
|
|
102
|
import eu.etaxonomy.cdm.model.term.DefinedTerm;
|
|
103
|
import eu.etaxonomy.cdm.persistence.dto.TaxonNodeDto;
|
|
104
|
import eu.etaxonomy.cdm.persistence.dto.TaxonNodeDtoByRankAndNameComparator;
|
|
105
|
import eu.etaxonomy.cdm.strategy.cache.HTMLTagRules;
|
|
106
|
import eu.etaxonomy.cdm.strategy.cache.TagEnum;
|
|
107
|
import eu.etaxonomy.cdm.strategy.cache.TaggedText;
|
|
108
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
|
109
|
|
|
110
|
/**
|
|
111
|
* @author a.mueller
|
|
112
|
* @date 29.06.2022
|
|
113
|
*/
|
|
114
|
@Component
|
|
115
|
public class WordClassificationExport
|
|
116
|
extends CdmExportBase<WordClassificationExportConfigurator, WordClassificationExportState, IExportTransformer, File>{
|
|
117
|
|
|
118
|
private static final long serialVersionUID = 5373475508269756045L;
|
|
119
|
|
|
120
|
@Autowired
|
|
121
|
private IEditGeoService geoService;
|
|
122
|
|
|
123
|
public WordClassificationExport() {
|
|
124
|
this.ioName = this.getClass().getSimpleName();
|
|
125
|
}
|
|
126
|
|
|
127
|
@Override
|
|
128
|
public long countSteps(WordClassificationExportState state) {
|
|
129
|
TaxonNodeFilter filter = state.getConfig().getTaxonNodeFilter();
|
|
130
|
return getTaxonNodeService().count(filter);
|
|
131
|
}
|
|
132
|
|
|
133
|
@Override
|
|
134
|
protected void doInvoke(WordClassificationExportState state) {
|
|
135
|
try {
|
|
136
|
|
|
137
|
IProgressMonitor monitor = state.getConfig().getProgressMonitor();
|
|
138
|
WordClassificationExportConfigurator config = state.getConfig();
|
|
139
|
if (config.getTaxonNodeFilter().hasClassificationFilter()) {
|
|
140
|
Classification classification = getClassificationService()
|
|
141
|
.load(config.getTaxonNodeFilter().getClassificationFilter().get(0).getUuid());
|
|
142
|
state.setRootId(classification.getRootNode().getUuid());
|
|
143
|
|
|
144
|
} else if (config.getTaxonNodeFilter().hasSubtreeFilter()) {
|
|
145
|
state.setRootId(config.getTaxonNodeFilter().getSubtreeFilter().get(0).getUuid());
|
|
146
|
}
|
|
147
|
@SuppressWarnings("unchecked")
|
|
148
|
TaxonNodeOutStreamPartitioner<XmlExportState> partitioner = TaxonNodeOutStreamPartitioner.NewInstance(this,
|
|
149
|
state, state.getConfig().getTaxonNodeFilter(), 100, monitor, null);
|
|
150
|
|
|
151
|
// handleMetaData(state);
|
|
152
|
monitor.subTask("Start partitioning");
|
|
153
|
|
|
154
|
TaxonNode node = partitioner.next();
|
|
155
|
while (node != null) {
|
|
156
|
handleTaxonNode(state, node);
|
|
157
|
node = partitioner.next();
|
|
158
|
}
|
|
159
|
// get rootNode and create helperObjects
|
|
160
|
if (state.getRootId() != null) {
|
|
161
|
List<TaxonNodeDto> childrenOfRoot = state.getNodeChildrenMap().get(state.getRootId());
|
|
162
|
|
|
163
|
Comparator<TaxonNodeDto> comp = state.getConfig().getComparator();
|
|
164
|
if (comp == null) {
|
|
165
|
comp = new TaxonNodeDtoByRankAndNameComparator();
|
|
166
|
}
|
|
167
|
if (childrenOfRoot != null) {
|
|
168
|
Collections.sort(childrenOfRoot, comp);
|
|
169
|
OrderHelper helper = new OrderHelper(state.getRootId());
|
|
170
|
helper.setOrderIndex(state.getActualOrderIndexAndUpdate());
|
|
171
|
state.getOrderHelperMap().put(state.getRootId(), helper);
|
|
172
|
|
|
173
|
for (TaxonNodeDto child : childrenOfRoot) {
|
|
174
|
OrderHelper childHelper = new OrderHelper(child.getTaxonUuid());
|
|
175
|
helper.addChild(childHelper);
|
|
176
|
childHelper.setOrderIndex(state.getActualOrderIndexAndUpdate());
|
|
177
|
childHelper.addChildren(
|
|
178
|
createOrderHelper(state.getNodeChildrenMap().get(child.getUuid()), state));
|
|
179
|
}
|
|
180
|
}
|
|
181
|
|
|
182
|
state.getNodeChildrenMap().clear();
|
|
183
|
for (OrderHelper order : state.getOrderHelperMap().values()) {
|
|
184
|
setOrderIndex(state, order);
|
|
185
|
}
|
|
186
|
}
|
|
187
|
|
|
188
|
state.getProcessor().createFinalResult(state);
|
|
189
|
} catch (Exception e) {
|
|
190
|
state.getResult().addException(e,
|
|
191
|
"An unexpected error occurred in main method doInvoke() " + e.getMessage());
|
|
192
|
e.printStackTrace();
|
|
193
|
}
|
|
194
|
}
|
|
195
|
|
|
196
|
private void setOrderIndex(WordClassificationExportState state, OrderHelper order) {
|
|
197
|
|
|
198
|
if (order.getTaxonUuid() != null
|
|
199
|
&& state.getProcessor().hasRecord(WordClassificationExportTable.TAXON, order.getTaxonUuid().toString())) {
|
|
200
|
String[] csvLine = state.getProcessor().getRecord(WordClassificationExportTable.TAXON,
|
|
201
|
order.getTaxonUuid().toString());
|
|
202
|
csvLine[WordClassificationExportTable.TAXON.getIndex(WordClassificationExportTable.SORT_INDEX)] = String
|
|
203
|
.valueOf(order.getOrderIndex());
|
|
204
|
}
|
|
205
|
|
|
206
|
if (order.getChildren() == null) {
|
|
207
|
return;
|
|
208
|
}
|
|
209
|
for (OrderHelper helper : order.getChildren()) {
|
|
210
|
setOrderIndex(state, helper);
|
|
211
|
}
|
|
212
|
}
|
|
213
|
|
|
214
|
private List<OrderHelper> createOrderHelper(List<TaxonNodeDto> nodes, WordClassificationExportState state) {
|
|
215
|
List<TaxonNodeDto> children = nodes;
|
|
216
|
// alreadySortedNodes.add(parentUuid);
|
|
217
|
if (children == null) {
|
|
218
|
return null;
|
|
219
|
}
|
|
220
|
Comparator<TaxonNodeDto> comp = state.getConfig().getComparator();
|
|
221
|
if (comp == null) {
|
|
222
|
comp = new TaxonNodeDtoByRankAndNameComparator();
|
|
223
|
}
|
|
224
|
Collections.sort(children, comp);
|
|
225
|
// TODO: nochmal checken!!!
|
|
226
|
OrderHelper helperChild;
|
|
227
|
List<OrderHelper> childrenHelper = new ArrayList<>();
|
|
228
|
for (TaxonNodeDto child : children) {
|
|
229
|
helperChild = new OrderHelper(child.getTaxonUuid());
|
|
230
|
helperChild.setOrderIndex(state.getActualOrderIndexAndUpdate());
|
|
231
|
|
|
232
|
if (state.getNodeChildrenMap().get(child.getUuid()) != null) {
|
|
233
|
children = state.getNodeChildrenMap().get(child.getUuid());
|
|
234
|
helperChild.addChildren(createOrderHelper(children, state));
|
|
235
|
}
|
|
236
|
childrenHelper.add(helperChild);
|
|
237
|
}
|
|
238
|
return childrenHelper;
|
|
239
|
}
|
|
240
|
|
|
241
|
private void handleTaxonNode(WordClassificationExportState state, TaxonNode taxonNode) {
|
|
242
|
|
|
243
|
if (taxonNode == null) {
|
|
244
|
String message = "TaxonNode for given taxon node UUID not found. ";
|
|
245
|
// TODO
|
|
246
|
state.getResult().addWarning(message);
|
|
247
|
} else {
|
|
248
|
try {
|
|
249
|
TaxonNode root = taxonNode;
|
|
250
|
List<TaxonNodeDto> childNodes;
|
|
251
|
if (root.hasChildNodes()) {
|
|
252
|
childNodes = new ArrayList<>();
|
|
253
|
for (TaxonNode child : root.getChildNodes()) {
|
|
254
|
if (child != null) {
|
|
255
|
childNodes.add(new TaxonNodeDto(child));
|
|
256
|
}
|
|
257
|
}
|
|
258
|
state.getNodeChildrenMap().put(root.getUuid(), childNodes);
|
|
259
|
|
|
260
|
// add root to node map
|
|
261
|
|
|
262
|
}
|
|
263
|
TaxonNodeDto rootDto = new TaxonNodeDto(root);
|
|
264
|
UUID parentUuid = root.getParent() != null ? root.getParent().getUuid()
|
|
265
|
: state.getClassificationUUID(root);
|
|
266
|
List<TaxonNodeDto> children = state.getNodeChildrenMap().get(parentUuid);
|
|
267
|
if (children != null && !children.contains(rootDto)) {
|
|
268
|
state.getNodeChildrenMap().get(parentUuid).add(rootDto);
|
|
269
|
} else if (state.getNodeChildrenMap().get(parentUuid) == null) {
|
|
270
|
List<TaxonNodeDto> rootList = new ArrayList<>();
|
|
271
|
rootList.add(rootDto);
|
|
272
|
state.getNodeChildrenMap().put(parentUuid, rootList);
|
|
273
|
|
|
274
|
}
|
|
275
|
if (root.hasTaxon()) {
|
|
276
|
handleTaxon(state, root);
|
|
277
|
|
|
278
|
}
|
|
279
|
} catch (Exception e) {
|
|
280
|
state.getResult().addException(e, "An unexpected error occurred when handling taxonNode "
|
|
281
|
+ taxonNode.getUuid() + ": " + e.getMessage() + e.getStackTrace());
|
|
282
|
}
|
|
283
|
}
|
|
284
|
}
|
|
285
|
|
|
286
|
private void handleTaxon(WordClassificationExportState state, TaxonNode taxonNode) {
|
|
287
|
try {
|
|
288
|
|
|
289
|
if (taxonNode == null) {
|
|
290
|
state.getResult().addError("The taxonNode was null.", "handleTaxon");
|
|
291
|
state.getResult().setState(ExportResultState.INCOMPLETE_WITH_ERROR);
|
|
292
|
return;
|
|
293
|
}
|
|
294
|
if (taxonNode.getTaxon() == null) {
|
|
295
|
state.getResult().addError("There was a taxon node without a taxon: " + taxonNode.getUuid(),
|
|
296
|
"handleTaxon");
|
|
297
|
state.getResult().setState(ExportResultState.INCOMPLETE_WITH_ERROR);
|
|
298
|
} else {
|
|
299
|
Taxon taxon = CdmBase.deproxy(taxonNode.getTaxon());
|
|
300
|
|
|
301
|
try {
|
|
302
|
TaxonName name = taxon.getName();
|
|
303
|
handleName(state, name, taxon, true);
|
|
304
|
HomotypicalGroup homotypicGroup = taxon.getHomotypicGroup();
|
|
305
|
int index = 0;
|
|
306
|
int homotypicGroupIndex = 0;
|
|
307
|
handleHomotypicalGroup(state, homotypicGroup, taxon, homotypicGroupIndex);
|
|
308
|
homotypicGroupIndex++;
|
|
309
|
for (Synonym syn : taxon.getSynonymsInGroup(homotypicGroup)) {
|
|
310
|
handleSynonym(state, syn, index);
|
|
311
|
index++;
|
|
312
|
}
|
|
313
|
List<HomotypicalGroup> heterotypicHomotypicGroups = taxon.getHeterotypicSynonymyGroups();
|
|
314
|
for (HomotypicalGroup group: heterotypicHomotypicGroups){
|
|
315
|
handleHomotypicalGroup(state, group, taxon, homotypicGroupIndex);
|
|
316
|
for (Synonym syn : taxon.getSynonymsInGroup(group)) {
|
|
317
|
handleSynonym(state, syn, index);
|
|
318
|
index++;
|
|
319
|
}
|
|
320
|
homotypicGroupIndex++;
|
|
321
|
}
|
|
322
|
|
|
323
|
index = 0;
|
|
324
|
for (Taxon tax : taxon.getAllProParteSynonyms()) {
|
|
325
|
handleProPartePartialMisapplied(state, tax, taxon, true, false, index);
|
|
326
|
index++;
|
|
327
|
}
|
|
328
|
|
|
329
|
|
|
330
|
for (Taxon tax : taxon.getAllMisappliedNames()) {
|
|
331
|
handleProPartePartialMisapplied(state, tax, taxon, false, true, index);
|
|
332
|
index++;
|
|
333
|
}
|
|
334
|
|
|
335
|
// state.getProcessor().put(table, taxon, csvLine);
|
|
336
|
handleDescriptions(state, taxon);
|
|
337
|
} catch (Exception e) {
|
|
338
|
state.getResult().addException(e,
|
|
339
|
"An unexpected problem occurred when trying to export taxon with id " + taxon.getId() + " " + taxon.getTitleCache());
|
|
340
|
state.getResult().setState(ExportResultState.INCOMPLETE_WITH_ERROR);
|
|
341
|
}
|
|
342
|
}
|
|
343
|
|
|
344
|
} catch (Exception e) {
|
|
345
|
state.getResult().addException(e, "An unexpected error occurred when handling the taxon node of "
|
|
346
|
+ cdmBaseStr(taxonNode.getTaxon()) + ", titleCache:"+ taxonNode.getTaxon().getTitleCache()+": " + e.getMessage());
|
|
347
|
}
|
|
348
|
}
|
|
349
|
|
|
350
|
private void handleDescriptions(WordClassificationExportState state, CdmBase cdmBase) {
|
|
351
|
String titleCache = null;
|
|
352
|
try {
|
|
353
|
|
|
354
|
if (cdmBase instanceof Taxon) {
|
|
355
|
Taxon taxon = HibernateProxyHelper.deproxy(cdmBase, Taxon.class);
|
|
356
|
titleCache = taxon.getTitleCache();
|
|
357
|
Set<TaxonDescription> descriptions = taxon.getDescriptions();
|
|
358
|
List<DescriptionElementBase> simpleFacts = new ArrayList<>();
|
|
359
|
List<DescriptionElementBase> specimenFacts = new ArrayList<>();
|
|
360
|
List<DescriptionElementBase> distributionFacts = new ArrayList<>();
|
|
361
|
List<DescriptionElementBase> taxonInteractionsFacts = new ArrayList<>();
|
|
362
|
List<DescriptionElementBase> commonNameFacts = new ArrayList<>();
|
|
363
|
List<DescriptionElementBase> usageFacts = new ArrayList<>();
|
|
364
|
for (TaxonDescription description : descriptions) {
|
|
365
|
if (description.getElements() != null) {
|
|
366
|
for (DescriptionElementBase element : description.getElements()) {
|
|
367
|
element = CdmBase.deproxy(element);
|
|
368
|
handleAnnotations(element);
|
|
369
|
if (element.getFeature().equals(Feature.COMMON_NAME())) {
|
|
370
|
commonNameFacts.add(element);
|
|
371
|
} else if (element.getFeature().equals(Feature.DISTRIBUTION())) {
|
|
372
|
distributionFacts.add(element);
|
|
373
|
} else if (element instanceof IndividualsAssociation
|
|
374
|
|| isSpecimenFeature(element.getFeature())) {
|
|
375
|
specimenFacts.add(element);
|
|
376
|
} else if (element.getFeature().isSupportsTaxonInteraction()) {
|
|
377
|
taxonInteractionsFacts.add(element);
|
|
378
|
} else {
|
|
379
|
simpleFacts.add(element);
|
|
380
|
}
|
|
381
|
}
|
|
382
|
}
|
|
383
|
}
|
|
384
|
if (!commonNameFacts.isEmpty()) {
|
|
385
|
handleCommonNameFacts(state, taxon, commonNameFacts);
|
|
386
|
}
|
|
387
|
if (!distributionFacts.isEmpty()) {
|
|
388
|
handleDistributionFacts(state, taxon, distributionFacts);
|
|
389
|
}
|
|
390
|
if (!specimenFacts.isEmpty()) {
|
|
391
|
handleSpecimenFacts(state, taxon, specimenFacts);
|
|
392
|
}
|
|
393
|
if (!simpleFacts.isEmpty()) {
|
|
394
|
handleSimpleFacts(state, taxon, simpleFacts);
|
|
395
|
}
|
|
396
|
if (!taxonInteractionsFacts.isEmpty()) {
|
|
397
|
handleTaxonInteractionsFacts(state, taxon, taxonInteractionsFacts);
|
|
398
|
}
|
|
399
|
} else if (cdmBase instanceof TaxonName) {
|
|
400
|
TaxonName name = CdmBase.deproxy(cdmBase, TaxonName.class);
|
|
401
|
titleCache = name.getTitleCache();
|
|
402
|
Set<TaxonNameDescription> descriptions = name.getDescriptions();
|
|
403
|
List<DescriptionElementBase> simpleFacts = new ArrayList<>();
|
|
404
|
for (TaxonNameDescription description : descriptions) {
|
|
405
|
if (description.getElements() != null) {
|
|
406
|
for (DescriptionElementBase element : description.getElements()) {
|
|
407
|
simpleFacts.add(element);
|
|
408
|
}
|
|
409
|
}
|
|
410
|
}
|
|
411
|
if (!simpleFacts.isEmpty()) {
|
|
412
|
handleSimpleFacts(state, name, simpleFacts);
|
|
413
|
}
|
|
414
|
}
|
|
415
|
} catch (Exception e) {
|
|
416
|
state.getResult().addException(e, "An unexpected error occurred when handling description of "
|
|
417
|
+ cdmBaseStr(cdmBase) + (titleCache != null? (" " +titleCache) : "")+": " + e.getMessage());
|
|
418
|
}
|
|
419
|
}
|
|
420
|
|
|
421
|
private void handleAnnotations(DescriptionElementBase element) {
|
|
422
|
// TODO Auto-generated method stub
|
|
423
|
}
|
|
424
|
|
|
425
|
private void handleMetaData(WordClassificationExportState state) {
|
|
426
|
WordClassificationExportTable table = WordClassificationExportTable.METADATA;
|
|
427
|
String[] csvLine = new String[table.getSize()];
|
|
428
|
// csvLine[table.getIndex(CdmLightExportTable.INSTANCE_ID)] = state.getConfig().getInctanceId();
|
|
429
|
// csvLine[table.getIndex(CdmLightExportTable.INSTANCE_NAME)] = state.getConfig().getInstanceName();
|
|
430
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_BASE_URL)] = state.getConfig().getBase_url();
|
|
431
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_CONTRIBUTOR)] = state.getConfig().getContributor();
|
|
432
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_CREATOR)] = state.getConfig().getCreator();
|
|
433
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_DESCRIPTION)] = state.getConfig().getDescription();
|
|
434
|
// csvLine[table.getIndex(WordClassificationExportTable.DATASET_DOWNLOAD_LINK)] = state.getConfig().getDataset_download_link();
|
|
435
|
// csvLine[table.getIndex(WordClassificationExportTable.DATASET_KEYWORDS)] = state.getConfig().getKeywords();
|
|
436
|
// csvLine[table.getIndex(WordClassificationExportTable.DATASET_LANDINGPAGE)] = state.getConfig().getDataSet_landing_page();
|
|
437
|
|
|
438
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_LANGUAGE)] = state.getConfig().getLanguage() != null? state.getConfig().getLanguage().getLabel(): null;
|
|
439
|
// csvLine[table.getIndex(WordClassificationExportTable.DATASET_LICENCE)] = state.getConfig().getLicence();
|
|
440
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_LOCATION)] = state.getConfig().getLocation();
|
|
441
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_RECOMMENDED_CITATTION)] = state.getConfig().getRecommended_citation();
|
|
442
|
csvLine[table.getIndex(WordClassificationExportTable.DATASET_TITLE)] = state.getConfig().getTitle();
|
|
443
|
state.getProcessor().put(table, "", csvLine);
|
|
444
|
}
|
|
445
|
|
|
446
|
private boolean isSpecimenFeature(Feature feature) {
|
|
447
|
// TODO allow user defined specimen features
|
|
448
|
if (feature == null) {
|
|
449
|
return false;
|
|
450
|
} else if (feature.isSupportsIndividualAssociation()) {
|
|
451
|
return true;
|
|
452
|
} else {
|
|
453
|
return feature.equals(Feature.SPECIMEN()) || feature.equals(Feature.INDIVIDUALS_ASSOCIATION())
|
|
454
|
|| feature.equals(Feature.MATERIALS_EXAMINED()) || feature.equals(Feature.OBSERVATION())
|
|
455
|
|| feature.equals(Feature.OCCURRENCE());
|
|
456
|
}
|
|
457
|
}
|
|
458
|
|
|
459
|
private void handleSimpleFacts(WordClassificationExportState state, CdmBase cdmBase,
|
|
460
|
List<DescriptionElementBase> simpleFacts) {
|
|
461
|
String titleCache = null;
|
|
462
|
try {
|
|
463
|
WordClassificationExportTable table;
|
|
464
|
if (cdmBase instanceof TaxonName) {
|
|
465
|
titleCache = ((TaxonName)cdmBase).getTitleCache();
|
|
466
|
table = WordClassificationExportTable.NAME_FACT;
|
|
467
|
} else {
|
|
468
|
if (cdmBase instanceof Taxon){
|
|
469
|
titleCache = ((Taxon)cdmBase).getTitleCache();
|
|
470
|
}
|
|
471
|
table = WordClassificationExportTable.SIMPLE_FACT;
|
|
472
|
}
|
|
473
|
WordClassificationExportTable tableMedia = WordClassificationExportTable.MEDIA;
|
|
474
|
for (DescriptionElementBase element : simpleFacts) {
|
|
475
|
if (element.getModifyingText().isEmpty() && !element.getMedia().isEmpty()) {
|
|
476
|
handleSimpleMediaFact(state, cdmBase, tableMedia, element);
|
|
477
|
} else {
|
|
478
|
handleSingleSimpleFact(state, cdmBase, table, element);
|
|
479
|
}
|
|
480
|
}
|
|
481
|
} catch (Exception e) {
|
|
482
|
state.getResult().addException(e, "An unexpected error occurred when handling simple facts for "
|
|
483
|
+ cdmBaseStr(cdmBase) + (titleCache != null? (" " +titleCache) : "")+ ": " + e.getMessage());
|
|
484
|
}
|
|
485
|
}
|
|
486
|
|
|
487
|
private void handleTaxonInteractionsFacts(WordClassificationExportState state, CdmBase cdmBase,
|
|
488
|
List<DescriptionElementBase> taxonInteractionsFacts) {
|
|
489
|
WordClassificationExportTable table = WordClassificationExportTable.TAXON_INTERACTION_FACT;
|
|
490
|
String titleCache = null;
|
|
491
|
if (cdmBase instanceof TaxonBase){
|
|
492
|
titleCache = ((TaxonBase)cdmBase).getTitleCache();
|
|
493
|
}
|
|
494
|
for (DescriptionElementBase element : taxonInteractionsFacts) {
|
|
495
|
|
|
496
|
try {
|
|
497
|
|
|
498
|
String[] csvLine = new String[table.getSize()];
|
|
499
|
|
|
500
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
501
|
handleSource(state, element, table);
|
|
502
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, cdmBase);
|
|
503
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON2_FK)] = getId(state,
|
|
504
|
((TaxonInteraction) element).getTaxon2());
|
|
505
|
csvLine[table.getIndex(WordClassificationExportTable.DESCRIPTION)] = createMultilanguageString(
|
|
506
|
((TaxonInteraction) element).getDescription());
|
|
507
|
state.getProcessor().put(table, element, csvLine);
|
|
508
|
|
|
509
|
} catch (Exception e) {
|
|
510
|
state.getResult().addException(e, "An unexpected error occurred when handling taxon interaction"
|
|
511
|
+ cdmBaseStr(element) + (titleCache != null? (" " +titleCache) : "")+ ": " + e.getMessage());
|
|
512
|
}
|
|
513
|
}
|
|
514
|
}
|
|
515
|
|
|
516
|
private void handleSimpleMediaFact(WordClassificationExportState state, CdmBase cdmBase, WordClassificationExportTable table,
|
|
517
|
DescriptionElementBase element) {
|
|
518
|
try {
|
|
519
|
String[] csvLine;
|
|
520
|
handleSource(state, element, WordClassificationExportTable.MEDIA);
|
|
521
|
|
|
522
|
if (element instanceof TextData) {
|
|
523
|
TextData textData = (TextData) element;
|
|
524
|
csvLine = new String[table.getSize()];
|
|
525
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
526
|
if (cdmBase instanceof Taxon) {
|
|
527
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, cdmBase);
|
|
528
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_FK)] = "";
|
|
529
|
} else if (cdmBase instanceof TaxonName) {
|
|
530
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = "";
|
|
531
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_FK)] = getId(state, cdmBase);
|
|
532
|
}
|
|
533
|
|
|
534
|
String mediaUris = "";
|
|
535
|
for (Media media : textData.getMedia()) {
|
|
536
|
String mediaString = extractMediaUris(media.getRepresentations().iterator());
|
|
537
|
if (!StringUtils.isBlank(mediaString)) {
|
|
538
|
mediaUris += mediaString + ";";
|
|
539
|
} else {
|
|
540
|
state.getResult().addWarning("Empty Media object for " + cdmBase.getUserFriendlyTypeName() + " "
|
|
541
|
+ cdmBase.getUuid() + " (media: " + media.getUuid() + ")");
|
|
542
|
}
|
|
543
|
}
|
|
544
|
csvLine[table.getIndex(WordClassificationExportTable.MEDIA_URI)] = mediaUris;
|
|
545
|
|
|
546
|
}
|
|
547
|
} catch (Exception e) {
|
|
548
|
state.getResult().addException(e, "An unexpected error occurred when handling single simple fact "
|
|
549
|
+ cdmBaseStr(element) + ": " + e.getMessage());
|
|
550
|
}
|
|
551
|
|
|
552
|
}
|
|
553
|
|
|
554
|
private void handleSingleSimpleFact(WordClassificationExportState state, CdmBase cdmBase, WordClassificationExportTable table,
|
|
555
|
DescriptionElementBase element) {
|
|
556
|
try {
|
|
557
|
String[] csvLine;
|
|
558
|
handleSource(state, element, WordClassificationExportTable.SIMPLE_FACT);
|
|
559
|
|
|
560
|
if (element instanceof TextData) {
|
|
561
|
TextData textData = (TextData) element;
|
|
562
|
csvLine = new String[table.getSize()];
|
|
563
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
564
|
if (cdmBase instanceof Taxon) {
|
|
565
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, cdmBase);
|
|
566
|
} else if (cdmBase instanceof TaxonName) {
|
|
567
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_FK)] = getId(state, cdmBase);
|
|
568
|
}
|
|
569
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_CATEGORY)] = textData.getFeature().getLabel();
|
|
570
|
|
|
571
|
String mediaUris = "";
|
|
572
|
for (Media media : textData.getMedia()) {
|
|
573
|
String mediaString = extractMediaUris(media.getRepresentations().iterator());
|
|
574
|
if (!StringUtils.isBlank(mediaString)) {
|
|
575
|
mediaUris += mediaString + ";";
|
|
576
|
} else {
|
|
577
|
state.getResult().addWarning("Empty Media object for uuid: " + cdmBase.getUuid()
|
|
578
|
+ " uuid of media: " + media.getUuid());
|
|
579
|
}
|
|
580
|
}
|
|
581
|
csvLine[table.getIndex(WordClassificationExportTable.MEDIA_URI)] = mediaUris;
|
|
582
|
if (textData.getFeature().equals(Feature.CITATION())) {
|
|
583
|
state.getProcessor().put(table, textData, csvLine);
|
|
584
|
} else if (!textData.getMultilanguageText().isEmpty()) {
|
|
585
|
for (Language language : textData.getMultilanguageText().keySet()) {
|
|
586
|
String[] csvLineLanguage = csvLine.clone();
|
|
587
|
LanguageString langString = textData.getLanguageText(language);
|
|
588
|
String text = langString.getText();
|
|
589
|
if (state.getConfig().isFilterIntextReferences()) {
|
|
590
|
text = filterIntextReferences(langString.getText());
|
|
591
|
}
|
|
592
|
csvLineLanguage[table.getIndex(WordClassificationExportTable.FACT_TEXT)] = text;
|
|
593
|
csvLineLanguage[table.getIndex(WordClassificationExportTable.LANGUAGE)] = language.getLabel();
|
|
594
|
state.getProcessor().put(table, textData, csvLineLanguage);
|
|
595
|
}
|
|
596
|
} else {
|
|
597
|
state.getProcessor().put(table, textData, csvLine);
|
|
598
|
}
|
|
599
|
}
|
|
600
|
} catch (Exception e) {
|
|
601
|
state.getResult().addException(e, "An unexpected error occurred when handling single simple fact "
|
|
602
|
+ cdmBaseStr(element) + ": " + e.getMessage());
|
|
603
|
}
|
|
604
|
}
|
|
605
|
|
|
606
|
private String filterIntextReferences(String text) {
|
|
607
|
/*
|
|
608
|
* (<cdm:reference cdmId='fbd19251-efee-4ded-b780-915000f66d41'
|
|
609
|
* intextId='1352d42c-e201-4155-a02a-55360d3b563e'>Ridley in Fl. Malay
|
|
610
|
* Pen. 3 (1924) 22</cdm:reference>)
|
|
611
|
*/
|
|
612
|
String newText = text.replaceAll("<cdm:reference cdmId='[a-z0-9\\-]*' intextId='[a-z0-9\\-]*'>", "");
|
|
613
|
newText = newText.replaceAll("</cdm:reference>", "");
|
|
614
|
|
|
615
|
newText = newText.replaceAll("<cdm:key cdmId='[a-z0-9\\-]*' intextId='[a-z0-9\\-]*'>", "");
|
|
616
|
newText = newText.replaceAll("</cdm:key>", "");
|
|
617
|
return newText;
|
|
618
|
}
|
|
619
|
|
|
620
|
private void handleSpecimenFacts(WordClassificationExportState state, Taxon taxon,
|
|
621
|
List<DescriptionElementBase> specimenFacts) {
|
|
622
|
WordClassificationExportTable table = WordClassificationExportTable.SPECIMEN_FACT;
|
|
623
|
|
|
624
|
for (DescriptionElementBase element : specimenFacts) {
|
|
625
|
try {
|
|
626
|
String[] csvLine = new String[table.getSize()];
|
|
627
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
628
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, taxon);
|
|
629
|
handleSource(state, element, table);
|
|
630
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_NOTES)] = createAnnotationsString(
|
|
631
|
element.getAnnotations());
|
|
632
|
|
|
633
|
if (element instanceof IndividualsAssociation) {
|
|
634
|
|
|
635
|
IndividualsAssociation indAssociation = (IndividualsAssociation) element;
|
|
636
|
if (indAssociation.getAssociatedSpecimenOrObservation() == null) {
|
|
637
|
state.getResult()
|
|
638
|
.addWarning("There is an individual association with no specimen associated (Taxon "
|
|
639
|
+ taxon.getTitleCache() + "(" + taxon.getUuid() + "). Could not be exported.");
|
|
640
|
continue;
|
|
641
|
} else {
|
|
642
|
if (!state.getSpecimenStore()
|
|
643
|
.contains((indAssociation.getAssociatedSpecimenOrObservation().getUuid()))) {
|
|
644
|
SpecimenOrObservationBase<?> specimenBase = HibernateProxyHelper.deproxy(
|
|
645
|
indAssociation.getAssociatedSpecimenOrObservation(),
|
|
646
|
SpecimenOrObservationBase.class);
|
|
647
|
|
|
648
|
handleSpecimen(state, specimenBase);
|
|
649
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_FK)] = getId(state,
|
|
650
|
indAssociation.getAssociatedSpecimenOrObservation());
|
|
651
|
}
|
|
652
|
}
|
|
653
|
} else if (element instanceof TextData) {
|
|
654
|
TextData textData = HibernateProxyHelper.deproxy(element, TextData.class);
|
|
655
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_DESCRIPTION)] = createMultilanguageString(
|
|
656
|
textData.getMultilanguageText());
|
|
657
|
}
|
|
658
|
state.getProcessor().put(table, element, csvLine);
|
|
659
|
} catch (Exception e) {
|
|
660
|
state.getResult().addException(e, "An unexpected error occurred when handling single specimen fact "
|
|
661
|
+ cdmBaseStr(element) + ": " + e.getMessage());
|
|
662
|
}
|
|
663
|
}
|
|
664
|
}
|
|
665
|
|
|
666
|
private String createMultilanguageString(Map<Language, LanguageString> multilanguageText) {
|
|
667
|
String text = "";
|
|
668
|
int index = multilanguageText.size();
|
|
669
|
for (LanguageString langString : multilanguageText.values()) {
|
|
670
|
text += langString.getText();
|
|
671
|
if (index > 1) {
|
|
672
|
text += "; ";
|
|
673
|
}
|
|
674
|
index--;
|
|
675
|
}
|
|
676
|
return text;
|
|
677
|
}
|
|
678
|
|
|
679
|
private String createAnnotationsString(Set<Annotation> annotations) {
|
|
680
|
StringBuffer strBuff = new StringBuffer();
|
|
681
|
|
|
682
|
for (Annotation ann : annotations) {
|
|
683
|
if (ann.getAnnotationType() == null || !ann.getAnnotationType().equals(AnnotationType.TECHNICAL())) {
|
|
684
|
strBuff.append(ann.getText());
|
|
685
|
strBuff.append("; ");
|
|
686
|
}
|
|
687
|
}
|
|
688
|
|
|
689
|
if (strBuff.length() > 2) {
|
|
690
|
return strBuff.substring(0, strBuff.length() - 2);
|
|
691
|
} else {
|
|
692
|
return null;
|
|
693
|
}
|
|
694
|
}
|
|
695
|
|
|
696
|
private void handleSource(WordClassificationExportState state, DescriptionElementBase element,
|
|
697
|
WordClassificationExportTable factsTable) {
|
|
698
|
WordClassificationExportTable table = WordClassificationExportTable.FACT_SOURCES;
|
|
699
|
try {
|
|
700
|
Set<DescriptionElementSource> sources = element.getSources();
|
|
701
|
|
|
702
|
for (DescriptionElementSource source : sources) {
|
|
703
|
if (!(source.getType().equals(OriginalSourceType.Import)
|
|
704
|
&& state.getConfig().isExcludeImportSources())) {
|
|
705
|
String[] csvLine = new String[table.getSize()];
|
|
706
|
Reference ref = source.getCitation();
|
|
707
|
if ((ref == null) && (source.getNameUsedInSource() == null)) {
|
|
708
|
continue;
|
|
709
|
}
|
|
710
|
if (ref != null) {
|
|
711
|
if (!state.getReferenceStore().contains(ref.getUuid())) {
|
|
712
|
handleReference(state, ref);
|
|
713
|
|
|
714
|
}
|
|
715
|
csvLine[table.getIndex(WordClassificationExportTable.REFERENCE_FK)] = getId(state, ref);
|
|
716
|
}
|
|
717
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_FK)] = getId(state, element);
|
|
718
|
|
|
719
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_IN_SOURCE_FK)] = getId(state,
|
|
720
|
source.getNameUsedInSource());
|
|
721
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_TYPE)] = factsTable.getTableName();
|
|
722
|
if (StringUtils.isBlank(csvLine[table.getIndex(WordClassificationExportTable.REFERENCE_FK)])
|
|
723
|
&& StringUtils.isBlank(csvLine[table.getIndex(WordClassificationExportTable.NAME_IN_SOURCE_FK)])) {
|
|
724
|
continue;
|
|
725
|
}
|
|
726
|
state.getProcessor().put(table, source, csvLine);
|
|
727
|
}
|
|
728
|
|
|
729
|
}
|
|
730
|
} catch (Exception e) {
|
|
731
|
state.getResult().addException(e, "An unexpected error occurred when handling single source "
|
|
732
|
+ cdmBaseStr(element) + ": " + e.getMessage());
|
|
733
|
}
|
|
734
|
|
|
735
|
}
|
|
736
|
|
|
737
|
private void handleDistributionFacts(WordClassificationExportState state, Taxon taxon,
|
|
738
|
List<DescriptionElementBase> distributionFacts) {
|
|
739
|
|
|
740
|
WordClassificationExportTable table = WordClassificationExportTable.GEOGRAPHIC_AREA_FACT;
|
|
741
|
Set<Distribution> distributions = new HashSet<>();
|
|
742
|
for (DescriptionElementBase element : distributionFacts) {
|
|
743
|
try {
|
|
744
|
if (element instanceof Distribution) {
|
|
745
|
String[] csvLine = new String[table.getSize()];
|
|
746
|
Distribution distribution = (Distribution) element;
|
|
747
|
distributions.add(distribution);
|
|
748
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
749
|
handleSource(state, element, table);
|
|
750
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, taxon);
|
|
751
|
if (distribution.getArea() != null) {
|
|
752
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_LABEL)] = distribution.getArea().getLabel();
|
|
753
|
}
|
|
754
|
if (distribution.getStatus() != null) {
|
|
755
|
csvLine[table.getIndex(WordClassificationExportTable.STATUS_LABEL)] = distribution.getStatus().getLabel();
|
|
756
|
}
|
|
757
|
state.getProcessor().put(table, distribution, csvLine);
|
|
758
|
} else {
|
|
759
|
state.getResult()
|
|
760
|
.addError("The distribution description for the taxon " + taxon.getUuid()
|
|
761
|
+ " is not of type distribution. Could not be exported. UUID of the description element: "
|
|
762
|
+ element.getUuid());
|
|
763
|
}
|
|
764
|
} catch (Exception e) {
|
|
765
|
state.getResult().addException(e, "An unexpected error occurred when handling single distribution "
|
|
766
|
+ cdmBaseStr(element) + ": " + e.getMessage());
|
|
767
|
}
|
|
768
|
}
|
|
769
|
if(state.getConfig().isCreateCondensedDistributionString()){
|
|
770
|
List<Language> langs = new ArrayList<>();
|
|
771
|
langs.add(Language.ENGLISH());
|
|
772
|
|
|
773
|
CondensedDistribution conDis = geoService.getCondensedDistribution(
|
|
774
|
//TODO add CondensedDistributionConfiguration to export configuration
|
|
775
|
distributions, true, null, state.getConfig().getCondensedDistributionConfiguration(), langs);
|
|
776
|
WordClassificationExportTable tableCondensed =
|
|
777
|
WordClassificationExportTable.SIMPLE_FACT;
|
|
778
|
String[] csvLine = new String[tableCondensed.getSize()];
|
|
779
|
//the computed fact has no uuid, TODO: remember the uuid for later reference assignment
|
|
780
|
UUID randomUuid = UUID.randomUUID();
|
|
781
|
csvLine[tableCondensed.getIndex(WordClassificationExportTable.FACT_ID)] =
|
|
782
|
randomUuid.toString();
|
|
783
|
csvLine[tableCondensed.getIndex(WordClassificationExportTable.TAXON_FK)] =
|
|
784
|
getId(state, taxon);
|
|
785
|
csvLine[tableCondensed.getIndex(WordClassificationExportTable.FACT_TEXT)] =
|
|
786
|
conDis.toString();
|
|
787
|
csvLine[tableCondensed.getIndex(WordClassificationExportTable.LANGUAGE)] =Language.ENGLISH().toString();
|
|
788
|
|
|
789
|
csvLine[tableCondensed.getIndex(WordClassificationExportTable.FACT_CATEGORY)] =
|
|
790
|
"CondensedDistribution";
|
|
791
|
|
|
792
|
state.getProcessor().put(tableCondensed, taxon, csvLine);
|
|
793
|
}
|
|
794
|
}
|
|
795
|
|
|
796
|
private void handleCommonNameFacts(WordClassificationExportState state, Taxon taxon,
|
|
797
|
List<DescriptionElementBase> commonNameFacts) {
|
|
798
|
WordClassificationExportTable table = WordClassificationExportTable.COMMON_NAME_FACT;
|
|
799
|
|
|
800
|
for (DescriptionElementBase element : commonNameFacts) {
|
|
801
|
try {
|
|
802
|
if (element instanceof CommonTaxonName) {
|
|
803
|
String[] csvLine = new String[table.getSize()];
|
|
804
|
CommonTaxonName commonName = (CommonTaxonName) element;
|
|
805
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
806
|
handleSource(state, element, table);
|
|
807
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, taxon);
|
|
808
|
if (commonName.getName() != null) {
|
|
809
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_TEXT)] = commonName.getName();
|
|
810
|
}
|
|
811
|
if (commonName.getLanguage() != null) {
|
|
812
|
csvLine[table.getIndex(WordClassificationExportTable.LANGUAGE)] = commonName.getLanguage().getLabel();
|
|
813
|
}
|
|
814
|
if (commonName.getArea() != null) {
|
|
815
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_LABEL)] = commonName.getArea().getLabel();
|
|
816
|
}
|
|
817
|
state.getProcessor().put(table, commonName, csvLine);
|
|
818
|
} else if (element instanceof TextData){
|
|
819
|
String[] csvLine = new String[table.getSize()];
|
|
820
|
TextData commonName = (TextData) element;
|
|
821
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_ID)] = getId(state, element);
|
|
822
|
handleSource(state, element, table);
|
|
823
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, taxon);
|
|
824
|
if (commonName.getMultilanguageText() != null) {
|
|
825
|
csvLine[table.getIndex(WordClassificationExportTable.FACT_TEXT)] = createMultilanguageString(commonName.getMultilanguageText());
|
|
826
|
}
|
|
827
|
state.getProcessor().put(table, commonName, csvLine);
|
|
828
|
} else {
|
|
829
|
state.getResult()
|
|
830
|
.addError("The common name description for the taxon " + taxon.getUuid()
|
|
831
|
+ " is not of type common name. Could not be exported. UUID of the description element: "
|
|
832
|
+ element.getUuid());
|
|
833
|
}
|
|
834
|
} catch (Exception e) {
|
|
835
|
state.getResult().addException(e, "An unexpected error occurred when handling single common name "
|
|
836
|
+ cdmBaseStr(element) + " - "+taxon.getTitleCache()+ ": " + e.getMessage());
|
|
837
|
}
|
|
838
|
}
|
|
839
|
}
|
|
840
|
|
|
841
|
private String getTitleCache(IIdentifiableEntity identEntity) {
|
|
842
|
if (identEntity == null) {
|
|
843
|
return "";
|
|
844
|
}
|
|
845
|
// TODO refresh?
|
|
846
|
return identEntity.getTitleCache();
|
|
847
|
}
|
|
848
|
|
|
849
|
private String getId(WordClassificationExportState state, ICdmBase cdmBase) {
|
|
850
|
if (cdmBase == null) {
|
|
851
|
return "";
|
|
852
|
}
|
|
853
|
// TODO make configurable
|
|
854
|
return cdmBase.getUuid().toString();
|
|
855
|
}
|
|
856
|
|
|
857
|
private void handleSynonym(WordClassificationExportState state, Synonym synonym, int index) {
|
|
858
|
try {
|
|
859
|
if (isUnpublished(state.getConfig(), synonym)) {
|
|
860
|
return;
|
|
861
|
}
|
|
862
|
TaxonName name = synonym.getName();
|
|
863
|
handleName(state, name, synonym.getAcceptedTaxon());
|
|
864
|
|
|
865
|
WordClassificationExportTable table = WordClassificationExportTable.SYNONYM;
|
|
866
|
String[] csvLine = new String[table.getSize()];
|
|
867
|
|
|
868
|
csvLine[table.getIndex(WordClassificationExportTable.SYNONYM_ID)] = getId(state, synonym);
|
|
869
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, synonym.getAcceptedTaxon());
|
|
870
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_FK)] = getId(state, name);
|
|
871
|
if (synonym.getSec() != null && !state.getReferenceStore().contains(synonym.getSec().getUuid())) {
|
|
872
|
handleReference(state, synonym.getSec());
|
|
873
|
}
|
|
874
|
csvLine[table.getIndex(WordClassificationExportTable.APPENDED_PHRASE)] = synonym.getAppendedPhrase();
|
|
875
|
csvLine[table.getIndex(WordClassificationExportTable.SYN_SEC_REFERENCE_FK)] = getId(state, synonym.getSec());
|
|
876
|
csvLine[table.getIndex(WordClassificationExportTable.SYN_SEC_REFERENCE)] = getTitleCache(synonym.getSec());
|
|
877
|
csvLine[table.getIndex(WordClassificationExportTable.PUBLISHED)] = synonym.isPublish() ? "1" : "0";
|
|
878
|
csvLine[table.getIndex(WordClassificationExportTable.IS_PRO_PARTE)] = "0";
|
|
879
|
csvLine[table.getIndex(WordClassificationExportTable.IS_PARTIAL)] = "0";
|
|
880
|
csvLine[table.getIndex(WordClassificationExportTable.IS_MISAPPLIED)] = "0";
|
|
881
|
csvLine[table.getIndex(WordClassificationExportTable.SORT_INDEX)] = String.valueOf(index);
|
|
882
|
state.getProcessor().put(table, synonym, csvLine);
|
|
883
|
} catch (Exception e) {
|
|
884
|
state.getResult().addException(e, "An unexpected error occurred when handling synonym "
|
|
885
|
+ cdmBaseStr(synonym) + ": " + e.getMessage());
|
|
886
|
}
|
|
887
|
}
|
|
888
|
|
|
889
|
/**
|
|
890
|
* Handles misapplied names (including pro parte and partial as well as pro
|
|
891
|
* parte and partial synonyms
|
|
892
|
*/
|
|
893
|
private void handleProPartePartialMisapplied(WordClassificationExportState state, Taxon taxon, Taxon accepted, boolean isProParte, boolean isMisapplied, int index) {
|
|
894
|
try {
|
|
895
|
Taxon ppSyonym = taxon;
|
|
896
|
if (isUnpublished(state.getConfig(), ppSyonym)) {
|
|
897
|
return;
|
|
898
|
}
|
|
899
|
TaxonName name = ppSyonym.getName();
|
|
900
|
handleName(state, name, accepted);
|
|
901
|
|
|
902
|
WordClassificationExportTable table = WordClassificationExportTable.SYNONYM;
|
|
903
|
String[] csvLine = new String[table.getSize()];
|
|
904
|
|
|
905
|
csvLine[table.getIndex(WordClassificationExportTable.SYNONYM_ID)] = getId(state, ppSyonym);
|
|
906
|
csvLine[table.getIndex(WordClassificationExportTable.TAXON_FK)] = getId(state, accepted);
|
|
907
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_FK)] = getId(state, name);
|
|
908
|
|
|
909
|
Reference secRef = ppSyonym.getSec();
|
|
910
|
|
|
911
|
if (secRef != null && !state.getReferenceStore().contains(secRef.getUuid())) {
|
|
912
|
handleReference(state, secRef);
|
|
913
|
}
|
|
914
|
csvLine[table.getIndex(WordClassificationExportTable.SEC_REFERENCE_FK)] = getId(state, secRef);
|
|
915
|
csvLine[table.getIndex(WordClassificationExportTable.SEC_REFERENCE)] = getTitleCache(secRef);
|
|
916
|
Set<TaxonRelationship> rels = accepted.getTaxonRelations(ppSyonym);
|
|
917
|
TaxonRelationship rel = null;
|
|
918
|
boolean isPartial = false;
|
|
919
|
if (rels.size() == 1){
|
|
920
|
rel = rels.iterator().next();
|
|
921
|
|
|
922
|
}else if (rels.size() > 1){
|
|
923
|
Iterator<TaxonRelationship> iterator = rels.iterator();
|
|
924
|
while (iterator.hasNext()){
|
|
925
|
rel = iterator.next();
|
|
926
|
if (isProParte && rel.getType().isAnySynonym()){
|
|
927
|
break;
|
|
928
|
} else if (isMisapplied && rel.getType().isAnyMisappliedName()){
|
|
929
|
break;
|
|
930
|
}else{
|
|
931
|
rel = null;
|
|
932
|
}
|
|
933
|
}
|
|
934
|
}
|
|
935
|
if (rel != null){
|
|
936
|
Reference synSecRef = rel.getCitation();
|
|
937
|
if (synSecRef != null && !state.getReferenceStore().contains(synSecRef.getUuid())) {
|
|
938
|
handleReference(state, synSecRef);
|
|
939
|
}
|
|
940
|
csvLine[table.getIndex(WordClassificationExportTable.SYN_SEC_REFERENCE_FK)] = getId(state, synSecRef);
|
|
941
|
csvLine[table.getIndex(WordClassificationExportTable.SYN_SEC_REFERENCE)] = getTitleCache(synSecRef);
|
|
942
|
isProParte = rel.getType().isProParte();
|
|
943
|
isPartial = rel.getType().isPartial();
|
|
944
|
|
|
945
|
}else{
|
|
946
|
state.getResult().addWarning("An unexpected error occurred when handling "
|
|
947
|
+ "pro parte/partial synonym or misapplied name " + cdmBaseStr(taxon) );
|
|
948
|
}
|
|
949
|
|
|
950
|
// pro parte type
|
|
951
|
|
|
952
|
csvLine[table.getIndex(WordClassificationExportTable.IS_PRO_PARTE)] = isProParte ? "1" : "0";
|
|
953
|
csvLine[table.getIndex(WordClassificationExportTable.IS_PARTIAL)] = isPartial ? "1" : "0";
|
|
954
|
csvLine[table.getIndex(WordClassificationExportTable.IS_MISAPPLIED)] = isMisapplied ? "1" : "0";
|
|
955
|
csvLine[table.getIndex(WordClassificationExportTable.SORT_INDEX)] = String.valueOf(index);
|
|
956
|
state.getProcessor().put(table, ppSyonym, csvLine);
|
|
957
|
} catch (Exception e) {
|
|
958
|
state.getResult().addException(e, "An unexpected error occurred when handling "
|
|
959
|
+ "pro parte/partial synonym or misapplied name " + cdmBaseStr(taxon) + ": " + e.getMessage());
|
|
960
|
}
|
|
961
|
|
|
962
|
}
|
|
963
|
|
|
964
|
private void handleName(WordClassificationExportState state, TaxonName name, Taxon acceptedTaxon){
|
|
965
|
handleName(state, name, acceptedTaxon, false);
|
|
966
|
}
|
|
967
|
|
|
968
|
private void handleName(WordClassificationExportState state, TaxonName name, Taxon acceptedTaxon, boolean acceptedName) {
|
|
969
|
if (name == null || state.getNameStore().containsKey(name.getId())) {
|
|
970
|
return;
|
|
971
|
}
|
|
972
|
try {
|
|
973
|
Rank rank = name.getRank();
|
|
974
|
WordClassificationExportTable table = WordClassificationExportTable.SCIENTIFIC_NAME;
|
|
975
|
name = HibernateProxyHelper.deproxy(name);
|
|
976
|
state.getNameStore().put(name.getId(), name.getUuid());
|
|
977
|
String[] csvLine = new String[table.getSize()];
|
|
978
|
|
|
979
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_ID)] = getId(state, name);
|
|
980
|
if (name.getLsid() != null) {
|
|
981
|
csvLine[table.getIndex(WordClassificationExportTable.LSID)] = name.getLsid().getLsid();
|
|
982
|
} else {
|
|
983
|
csvLine[table.getIndex(WordClassificationExportTable.LSID)] = "";
|
|
984
|
}
|
|
985
|
|
|
986
|
handleIdentifier(state, name);
|
|
987
|
handleDescriptions(state, name);
|
|
988
|
|
|
989
|
csvLine[table.getIndex(WordClassificationExportTable.RANK)] = getTitleCache(rank);
|
|
990
|
if (rank != null) {
|
|
991
|
csvLine[table.getIndex(WordClassificationExportTable.RANK_SEQUENCE)] = String.valueOf(rank.getOrderIndex());
|
|
992
|
if (rank.isInfraGeneric()) {
|
|
993
|
try {
|
|
994
|
csvLine[table.getIndex(WordClassificationExportTable.INFRAGENERIC_RANK)] = name.getRank()
|
|
995
|
.getInfraGenericMarker();
|
|
996
|
} catch (UnknownCdmTypeException e) {
|
|
997
|
state.getResult().addError("Infrageneric marker expected but not available for rank "
|
|
998
|
+ name.getRank().getTitleCache());
|
|
999
|
}
|
|
1000
|
}
|
|
1001
|
if (rank.isInfraSpecific()) {
|
|
1002
|
csvLine[table.getIndex(WordClassificationExportTable.INFRASPECIFIC_RANK)] = name.getRank().getAbbreviation();
|
|
1003
|
}
|
|
1004
|
} else {
|
|
1005
|
csvLine[table.getIndex(WordClassificationExportTable.RANK_SEQUENCE)] = "";
|
|
1006
|
}
|
|
1007
|
if (name.isProtectedTitleCache()) {
|
|
1008
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_NAME_WITH_AUTHORS)] = name.getTitleCache();
|
|
1009
|
} else {
|
|
1010
|
// TODO: adapt the tropicos titlecache creation
|
|
1011
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_NAME_WITH_AUTHORS)] = name.getTitleCache();
|
|
1012
|
}
|
|
1013
|
|
|
1014
|
|
|
1015
|
if (!state.getConfig().isAddHTML()) {
|
|
1016
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_NAME_WITH_REF)] = name.getFullTitleCache();
|
|
1017
|
} else {
|
|
1018
|
List<TaggedText> taggedFullTitleCache = name.getTaggedFullTitle();
|
|
1019
|
List<TaggedText> taggedName = name.getTaggedName();
|
|
1020
|
|
|
1021
|
String fullTitleWithHtml = createNameWithItalics(taggedFullTitleCache);
|
|
1022
|
// TODO: adapt the tropicos titlecache creation
|
|
1023
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_NAME_WITH_REF)] = fullTitleWithHtml.trim();
|
|
1024
|
}
|
|
1025
|
|
|
1026
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_NAME_NO_AUTHORS)] = name.getNameCache();
|
|
1027
|
csvLine[table.getIndex(WordClassificationExportTable.GENUS_UNINOMIAL)] = name.getGenusOrUninomial();
|
|
1028
|
|
|
1029
|
csvLine[table.getIndex(WordClassificationExportTable.INFRAGENERIC_EPITHET)] = name.getInfraGenericEpithet();
|
|
1030
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIFIC_EPITHET)] = name.getSpecificEpithet();
|
|
1031
|
|
|
1032
|
csvLine[table.getIndex(WordClassificationExportTable.INFRASPECIFIC_EPITHET)] = name.getInfraSpecificEpithet();
|
|
1033
|
|
|
1034
|
csvLine[table.getIndex(WordClassificationExportTable.APPENDED_PHRASE)] = name.getAppendedPhrase();
|
|
1035
|
|
|
1036
|
csvLine[table.getIndex(WordClassificationExportTable.BAS_AUTHORTEAM_FK)] = getId(state, name.getBasionymAuthorship());
|
|
1037
|
if (name.getBasionymAuthorship() != null) {
|
|
1038
|
if (state.getAuthorFromStore(name.getBasionymAuthorship().getId()) == null) {
|
|
1039
|
handleAuthor(state, name.getBasionymAuthorship());
|
|
1040
|
}
|
|
1041
|
}
|
|
1042
|
csvLine[table.getIndex(WordClassificationExportTable.BAS_EX_AUTHORTEAM_FK)] = getId(state,
|
|
1043
|
name.getExBasionymAuthorship());
|
|
1044
|
if (name.getExBasionymAuthorship() != null) {
|
|
1045
|
if (state.getAuthorFromStore(name.getExBasionymAuthorship().getId()) == null) {
|
|
1046
|
handleAuthor(state, name.getExBasionymAuthorship());
|
|
1047
|
}
|
|
1048
|
|
|
1049
|
}
|
|
1050
|
csvLine[table.getIndex(WordClassificationExportTable.COMB_AUTHORTEAM_FK)] = getId(state,
|
|
1051
|
name.getCombinationAuthorship());
|
|
1052
|
if (name.getCombinationAuthorship() != null) {
|
|
1053
|
if (state.getAuthorFromStore(name.getCombinationAuthorship().getId()) == null) {
|
|
1054
|
handleAuthor(state, name.getCombinationAuthorship());
|
|
1055
|
}
|
|
1056
|
}
|
|
1057
|
csvLine[table.getIndex(WordClassificationExportTable.COMB_EX_AUTHORTEAM_FK)] = getId(state,
|
|
1058
|
name.getExCombinationAuthorship());
|
|
1059
|
if (name.getExCombinationAuthorship() != null) {
|
|
1060
|
if (state.getAuthorFromStore(name.getExCombinationAuthorship().getId()) == null) {
|
|
1061
|
handleAuthor(state, name.getExCombinationAuthorship());
|
|
1062
|
}
|
|
1063
|
|
|
1064
|
}
|
|
1065
|
|
|
1066
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_TEAM_STRING)] = name.getAuthorshipCache();
|
|
1067
|
|
|
1068
|
Reference nomRef = name.getNomenclaturalReference();
|
|
1069
|
|
|
1070
|
NomenclaturalSource nomenclaturalSource = name.getNomenclaturalSource();
|
|
1071
|
if (nomenclaturalSource != null &&nomenclaturalSource.getNameUsedInSource() != null){
|
|
1072
|
handleName(state, nomenclaturalSource.getNameUsedInSource(), null);
|
|
1073
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_USED_IN_SOURCE)] = getId(state, nomenclaturalSource.getNameUsedInSource());
|
|
1074
|
}
|
|
1075
|
|
|
1076
|
if (nomRef != null) {
|
|
1077
|
if (!state.getReferenceStore().contains(nomRef.getUuid())) {
|
|
1078
|
handleReference(state, nomRef);
|
|
1079
|
}
|
|
1080
|
csvLine[table.getIndex(WordClassificationExportTable.REFERENCE_FK)] = getId(state, nomRef);
|
|
1081
|
csvLine[table.getIndex(WordClassificationExportTable.PUBLICATION_TYPE)] = nomRef.getType().name();
|
|
1082
|
if (nomRef.getVolume() != null) {
|
|
1083
|
csvLine[table.getIndex(WordClassificationExportTable.VOLUME_ISSUE)] = nomRef.getVolume();
|
|
1084
|
csvLine[table.getIndex(WordClassificationExportTable.COLLATION)] = createCollatation(name);
|
|
1085
|
}
|
|
1086
|
if (nomRef.getDatePublished() != null) {
|
|
1087
|
csvLine[table.getIndex(WordClassificationExportTable.DATE_PUBLISHED)] = nomRef.getTimePeriodPublishedString();
|
|
1088
|
csvLine[table.getIndex(WordClassificationExportTable.YEAR_PUBLISHED)] = nomRef.getDatePublished().getYear();
|
|
1089
|
csvLine[table.getIndex(WordClassificationExportTable.VERBATIM_DATE)] = nomRef.getDatePublished()
|
|
1090
|
.getVerbatimDate();
|
|
1091
|
}
|
|
1092
|
if (name.getNomenclaturalMicroReference() != null) {
|
|
1093
|
csvLine[table.getIndex(WordClassificationExportTable.DETAIL)] = name.getNomenclaturalMicroReference();
|
|
1094
|
}
|
|
1095
|
nomRef = HibernateProxyHelper.deproxy(nomRef);
|
|
1096
|
if (nomRef.getInReference() != null) {
|
|
1097
|
Reference inReference = nomRef.getInReference();
|
|
1098
|
if (inReference.getDatePublished() != null && nomRef.getDatePublished() == null) {
|
|
1099
|
csvLine[table.getIndex(WordClassificationExportTable.DATE_PUBLISHED)] = inReference
|
|
1100
|
.getDatePublishedString();
|
|
1101
|
csvLine[table.getIndex(WordClassificationExportTable.YEAR_PUBLISHED)] = inReference.getDatePublished()
|
|
1102
|
.getYear();
|
|
1103
|
}
|
|
1104
|
if (nomRef.getVolume() == null && inReference.getVolume() != null) {
|
|
1105
|
csvLine[table.getIndex(WordClassificationExportTable.VOLUME_ISSUE)] = inReference.getVolume();
|
|
1106
|
csvLine[table.getIndex(WordClassificationExportTable.COLLATION)] = createCollatation(name);
|
|
1107
|
}
|
|
1108
|
if (inReference.getInReference() != null) {
|
|
1109
|
inReference = inReference.getInReference();
|
|
1110
|
}
|
|
1111
|
if (inReference.getAbbrevTitle() == null) {
|
|
1112
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_TITLE)] = CdmUtils
|
|
1113
|
.Nz(inReference.getTitle());
|
|
1114
|
} else {
|
|
1115
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_TITLE)] = CdmUtils
|
|
1116
|
.Nz(inReference.getAbbrevTitle());
|
|
1117
|
}
|
|
1118
|
if (inReference.getTitle() == null) {
|
|
1119
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_TITLE)] = CdmUtils
|
|
1120
|
.Nz(inReference.getAbbrevTitle()!= null? inReference.getAbbrevTitle(): inReference.getTitleCache());
|
|
1121
|
} else {
|
|
1122
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_TITLE)] = CdmUtils.Nz(inReference.getTitle());
|
|
1123
|
}
|
|
1124
|
|
|
1125
|
TeamOrPersonBase<?> author = inReference.getAuthorship();
|
|
1126
|
if (author != null
|
|
1127
|
&& (nomRef.isOfType(ReferenceType.BookSection) || nomRef.isOfType(ReferenceType.Section))) {
|
|
1128
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_REF_AUTHOR)] = author.isProtectedTitleCache()
|
|
1129
|
? author.getTitleCache() : CdmUtils.Nz(author.getNomenclaturalTitleCache());
|
|
1130
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_REF_AUTHOR)] = CdmUtils
|
|
1131
|
.Nz(author.getTitleCache());
|
|
1132
|
} else {
|
|
1133
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_REF_AUTHOR)] = "";
|
|
1134
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_REF_AUTHOR)] = "";
|
|
1135
|
}
|
|
1136
|
} else {
|
|
1137
|
if (nomRef.getAbbrevTitle() == null) {
|
|
1138
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_TITLE)] = CdmUtils
|
|
1139
|
.Nz(nomRef.getTitle()!= null? nomRef.getTitle():nomRef.getAbbrevTitleCache());
|
|
1140
|
} else {
|
|
1141
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_TITLE)] = CdmUtils
|
|
1142
|
.Nz(nomRef.getAbbrevTitle());
|
|
1143
|
}
|
|
1144
|
if (nomRef.getTitle() == null) {
|
|
1145
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_TITLE)] = CdmUtils
|
|
1146
|
.Nz(nomRef.getAbbrevTitle()!= null? nomRef.getAbbrevTitle(): nomRef.getTitleCache());
|
|
1147
|
} else {
|
|
1148
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_TITLE)] = CdmUtils.Nz(nomRef.getTitle());
|
|
1149
|
}
|
|
1150
|
TeamOrPersonBase<?> author = nomRef.getAuthorship();
|
|
1151
|
if (author != null) {
|
|
1152
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_REF_AUTHOR)] = author.isProtectedTitleCache()
|
|
1153
|
? author.getTitleCache() : CdmUtils.Nz(author.getNomenclaturalTitleCache());
|
|
1154
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_REF_AUTHOR)] = CdmUtils
|
|
1155
|
.Nz(author.getTitleCache());
|
|
1156
|
} else {
|
|
1157
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_REF_AUTHOR)] = "";
|
|
1158
|
csvLine[table.getIndex(WordClassificationExportTable.FULL_REF_AUTHOR)] = "";
|
|
1159
|
}
|
|
1160
|
|
|
1161
|
}
|
|
1162
|
} else {
|
|
1163
|
csvLine[table.getIndex(WordClassificationExportTable.PUBLICATION_TYPE)] = "";
|
|
1164
|
}
|
|
1165
|
|
|
1166
|
/*
|
|
1167
|
* Collation
|
|
1168
|
*
|
|
1169
|
* Detail
|
|
1170
|
*
|
|
1171
|
* TitlePageYear
|
|
1172
|
*/
|
|
1173
|
String protologueUriString = extractProtologueURIs(state, name);
|
|
1174
|
|
|
1175
|
csvLine[table.getIndex(WordClassificationExportTable.PROTOLOGUE_URI)] = protologueUriString;
|
|
1176
|
Collection<TypeDesignationBase> specimenTypeDesignations = new ArrayList<>();
|
|
1177
|
List<TextualTypeDesignation> textualTypeDesignations = new ArrayList<>();
|
|
1178
|
for (TypeDesignationBase<?> typeDesignation : name.getTypeDesignations()) {
|
|
1179
|
if (typeDesignation.isInstanceOf(TextualTypeDesignation.class)) {
|
|
1180
|
|
|
1181
|
if (((TextualTypeDesignation) typeDesignation).isVerbatim() ){
|
|
1182
|
Set<IdentifiableSource> sources = typeDesignation.getSources();
|
|
1183
|
boolean isProtologue = false;
|
|
1184
|
if (sources != null && !sources.isEmpty()){
|
|
1185
|
IdentifiableSource source = sources.iterator().next();
|
|
1186
|
if (name.getNomenclaturalReference() != null){
|
|
1187
|
isProtologue = source.getCitation() != null? source.getCitation().getUuid().equals(name.getNomenclaturalReference().getUuid()): false;
|
|
1188
|
}
|
|
1189
|
}
|
|
1190
|
if (isProtologue){
|
|
1191
|
csvLine[table.getIndex(WordClassificationExportTable.PROTOLOGUE_TYPE_STATEMENT)] = ((TextualTypeDesignation) typeDesignation)
|
|
1192
|
.getPreferredText(Language.DEFAULT());
|
|
1193
|
}else{
|
|
1194
|
textualTypeDesignations.add((TextualTypeDesignation) typeDesignation);
|
|
1195
|
}
|
|
1196
|
|
|
1197
|
} else {
|
|
1198
|
textualTypeDesignations.add((TextualTypeDesignation) typeDesignation);
|
|
1199
|
}
|
|
1200
|
} else if (typeDesignation.isInstanceOf(SpecimenTypeDesignation.class)) {
|
|
1201
|
SpecimenTypeDesignation specimenType = HibernateProxyHelper.deproxy(typeDesignation, SpecimenTypeDesignation.class);
|
|
1202
|
specimenTypeDesignations.add(specimenType);
|
|
1203
|
handleSpecimenType(state, specimenType);
|
|
1204
|
|
|
1205
|
|
|
1206
|
}else if (typeDesignation instanceof NameTypeDesignation){
|
|
1207
|
specimenTypeDesignations.add(HibernateProxyHelper.deproxy(typeDesignation, NameTypeDesignation.class));
|
|
1208
|
}
|
|
1209
|
}
|
|
1210
|
TypeDesignationSetContainer manager = new TypeDesignationSetContainer(specimenTypeDesignations, name, TypeDesignationSetComparator.ORDER_BY.TYPE_STATUS);
|
|
1211
|
HTMLTagRules rules = new HTMLTagRules();
|
|
1212
|
rules.addRule(TagEnum.name, "i");
|
|
1213
|
|
|
1214
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_SPECIMEN)] = manager.print(false, false, false, rules);
|
|
1215
|
|
|
1216
|
StringBuilder stringbuilder = new StringBuilder();
|
|
1217
|
int i = 1;
|
|
1218
|
for (TextualTypeDesignation typeDesignation : textualTypeDesignations) {
|
|
1219
|
stringbuilder.append(typeDesignation.getPreferredText(Language.DEFAULT()));
|
|
1220
|
if (typeDesignation.getSources() != null && !typeDesignation.getSources().isEmpty() ){
|
|
1221
|
stringbuilder.append( " [");
|
|
1222
|
int index = 1;
|
|
1223
|
for (IdentifiableSource source: typeDesignation.getSources()){
|
|
1224
|
if (source.getCitation() != null){
|
|
1225
|
stringbuilder.append(OriginalSourceFormatter.INSTANCE.format(source));
|
|
1226
|
}
|
|
1227
|
if (index < typeDesignation.getSources().size()) {
|
|
1228
|
stringbuilder.append( ", ");
|
|
1229
|
}
|
|
1230
|
index++;
|
|
1231
|
}
|
|
1232
|
stringbuilder.append( "]");
|
|
1233
|
}
|
|
1234
|
if (i < textualTypeDesignations.size()) {
|
|
1235
|
stringbuilder.append( "; ");
|
|
1236
|
} else {
|
|
1237
|
stringbuilder.append(".");
|
|
1238
|
}
|
|
1239
|
i++;
|
|
1240
|
}
|
|
1241
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_STATEMENT)] = stringbuilder.toString();
|
|
1242
|
|
|
1243
|
|
|
1244
|
if (name.getStatus() == null || name.getStatus().isEmpty()) {
|
|
1245
|
csvLine[table.getIndex(WordClassificationExportTable.NOM_STATUS)] = "";
|
|
1246
|
csvLine[table.getIndex(WordClassificationExportTable.NOM_STATUS_ABBREV)] = "";
|
|
1247
|
} else {
|
|
1248
|
|
|
1249
|
String statusStringAbbrev = extractStatusString(state, name, true);
|
|
1250
|
String statusString = extractStatusString(state, name, false);
|
|
1251
|
|
|
1252
|
csvLine[table.getIndex(WordClassificationExportTable.NOM_STATUS)] = statusString.trim();
|
|
1253
|
csvLine[table.getIndex(WordClassificationExportTable.NOM_STATUS_ABBREV)] = statusStringAbbrev.trim();
|
|
1254
|
}
|
|
1255
|
|
|
1256
|
HomotypicalGroup group = HibernateProxyHelper.deproxy(name.getHomotypicalGroup(), HomotypicalGroup.class);
|
|
1257
|
|
|
1258
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_FK)] = getId(state, group);
|
|
1259
|
List<TaxonName> typifiedNames = new ArrayList<>();
|
|
1260
|
if (acceptedTaxon != null){
|
|
1261
|
HomotypicGroupTaxonComparator comparator = new HomotypicGroupTaxonComparator(acceptedTaxon);
|
|
1262
|
List<Synonym> synonymsInGroup = null;
|
|
1263
|
if (group.equals(acceptedTaxon.getHomotypicGroup())){
|
|
1264
|
synonymsInGroup = acceptedTaxon.getHomotypicSynonymsByHomotypicGroup(comparator);
|
|
1265
|
typifiedNames.add(name);
|
|
1266
|
}else{
|
|
1267
|
synonymsInGroup = acceptedTaxon.getSynonymsInGroup(group, comparator);
|
|
1268
|
}
|
|
1269
|
|
|
1270
|
synonymsInGroup.stream().forEach(synonym -> typifiedNames.add(HibernateProxyHelper.deproxy(synonym.getName(), TaxonName.class)));
|
|
1271
|
|
|
1272
|
}else{
|
|
1273
|
typifiedNames.addAll(group.getTypifiedNames());
|
|
1274
|
}
|
|
1275
|
|
|
1276
|
|
|
1277
|
Integer seqNumber = typifiedNames.indexOf(name);
|
|
1278
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_SEQ)] = String.valueOf(seqNumber);
|
|
1279
|
state.getProcessor().put(table, name, csvLine);
|
|
1280
|
handleNameRelationships(state, name);
|
|
1281
|
|
|
1282
|
} catch (Exception e) {
|
|
1283
|
state.getResult().addException(e,
|
|
1284
|
"An unexpected error occurred when handling the name " + cdmBaseStr(name) + ": " + name.getTitleCache() + ": " + e.getMessage());
|
|
1285
|
|
|
1286
|
e.printStackTrace();
|
|
1287
|
}
|
|
1288
|
}
|
|
1289
|
|
|
1290
|
/**
|
|
1291
|
* @param specimenType
|
|
1292
|
*/
|
|
1293
|
private void handleSpecimenType_(WordClassificationExportState state, SpecimenTypeDesignation specimenType) {
|
|
1294
|
if (specimenType.getTypeSpecimen() != null){
|
|
1295
|
DerivedUnit specimen = specimenType.getTypeSpecimen();
|
|
1296
|
if(specimen != null && !state.getSpecimenStore().contains( specimen.getUuid())){
|
|
1297
|
handleSpecimen(state, specimen);
|
|
1298
|
}
|
|
1299
|
}
|
|
1300
|
WordClassificationExportTable table = WordClassificationExportTable.TYPE_DESIGNATION;
|
|
1301
|
String[] csvLine = new String[table.getSize()];
|
|
1302
|
//TYPE_ID, SPECIMEN_FK, TYPE_VERBATIM_CITATION, TYPE_STATUS, TYPE_DESIGNATED_BY_STRING, TYPE_DESIGNATED_BY_REF_FK};
|
|
1303
|
//Specimen_Fk und den Typusangaben (Art des Typus [holo, lecto, etc.], Quelle, Designation-Quelle, +
|
|
1304
|
Set<TaxonName> typifiedNames = specimenType.getTypifiedNames();
|
|
1305
|
for (TaxonName name: typifiedNames){
|
|
1306
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_STATUS)] = specimenType.getTypeStatus() != null? specimenType.getTypeStatus().getDescription(): "";
|
|
1307
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_ID)] = getId(state, specimenType);
|
|
1308
|
csvLine[table.getIndex(WordClassificationExportTable.TYPIFIED_NAME_FK)] = getId(state, name);
|
|
1309
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_FK)] = getId(state, specimenType.getTypeSpecimen());
|
|
1310
|
if (specimenType.getSources() != null && !specimenType.getSources().isEmpty()){
|
|
1311
|
String sourceString = "";
|
|
1312
|
int index = 0;
|
|
1313
|
for (IdentifiableSource source: specimenType.getSources()){
|
|
1314
|
if (source.getCitation()!= null){
|
|
1315
|
sourceString = sourceString.concat(source.getCitation().getCitation());
|
|
1316
|
}
|
|
1317
|
index++;
|
|
1318
|
if (index != specimenType.getSources().size()){
|
|
1319
|
sourceString.concat(", ");
|
|
1320
|
}
|
|
1321
|
}
|
|
1322
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_INFORMATION_REF_STRING)] = sourceString;
|
|
1323
|
}
|
|
1324
|
if (specimenType.getDesignationSource() != null && specimenType.getDesignationSource().getCitation() != null && !state.getReferenceStore().contains(specimenType.getDesignationSource().getCitation().getUuid())){
|
|
1325
|
handleReference(state, specimenType.getDesignationSource().getCitation());
|
|
1326
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_DESIGNATED_BY_REF_FK)] = specimenType.getDesignationSource() != null ? getId(state, specimenType.getDesignationSource().getCitation()): "";
|
|
1327
|
}
|
|
1328
|
|
|
1329
|
state.getProcessor().put(table, specimenType, csvLine);
|
|
1330
|
}
|
|
1331
|
}
|
|
1332
|
|
|
1333
|
|
|
1334
|
/**
|
|
1335
|
* @param specimenType
|
|
1336
|
*/
|
|
1337
|
private void handleSpecimenType(WordClassificationExportState state, SpecimenTypeDesignation specimenType) {
|
|
1338
|
if (specimenType.getTypeSpecimen() != null){
|
|
1339
|
DerivedUnit specimen = specimenType.getTypeSpecimen();
|
|
1340
|
if(specimen != null && !state.getSpecimenStore().contains( specimen.getUuid())){
|
|
1341
|
handleSpecimen(state, specimen);
|
|
1342
|
}
|
|
1343
|
}
|
|
1344
|
WordClassificationExportTable table = WordClassificationExportTable.TYPE_DESIGNATION;
|
|
1345
|
String[] csvLine = new String[table.getSize()];
|
|
1346
|
|
|
1347
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_STATUS)] = specimenType.getTypeStatus() != null? specimenType.getTypeStatus().getDescription(): "";
|
|
1348
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_ID)] = getId(state, specimenType);
|
|
1349
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_FK)] = getId(state, specimenType.getTypeSpecimen());
|
|
1350
|
if (specimenType.getSources() != null && !specimenType.getSources().isEmpty()){
|
|
1351
|
String sourceString = "";
|
|
1352
|
int index = 0;
|
|
1353
|
List<IdentifiableSource> sources = new ArrayList<>(specimenType.getSources());
|
|
1354
|
Comparator<IdentifiableSource> compareByYear = new Comparator<IdentifiableSource>() {
|
|
1355
|
@Override
|
|
1356
|
public int compare(IdentifiableSource o1, IdentifiableSource o2) {
|
|
1357
|
if (o1 == o2){
|
|
1358
|
return 0;
|
|
1359
|
}
|
|
1360
|
if (o1.getCitation() == null && o2.getCitation() != null){
|
|
1361
|
return -1;
|
|
1362
|
}
|
|
1363
|
if (o2.getCitation() == null && o1.getCitation() != null){
|
|
1364
|
return 1;
|
|
1365
|
}
|
|
1366
|
if (o1.getCitation().equals(o2.getCitation())){
|
|
1367
|
return 0;
|
|
1368
|
}
|
|
1369
|
if (o1.getCitation().getDatePublished() == null && o2.getCitation().getDatePublished() != null){
|
|
1370
|
return -1;
|
|
1371
|
}
|
|
1372
|
if (o1.getCitation().getDatePublished() != null && o2.getCitation().getDatePublished() == null){
|
|
1373
|
return 1;
|
|
1374
|
}
|
|
1375
|
if (o1.getCitation().getDatePublished().getYear() == null && o2.getCitation().getDatePublished().getYear() != null){
|
|
1376
|
return -1;
|
|
1377
|
}
|
|
1378
|
if (o1.getCitation().getDatePublished().getYear() != null && o2.getCitation().getDatePublished().getYear() == null){
|
|
1379
|
return 1;
|
|
1380
|
}
|
|
1381
|
return o1.getCitation().getDatePublished().getYear().compareTo(o2.getCitation().getDatePublished().getYear());
|
|
1382
|
}
|
|
1383
|
};
|
|
1384
|
Collections.sort(sources, compareByYear);
|
|
1385
|
for (IdentifiableSource source: sources){
|
|
1386
|
if (source.getCitation()!= null){
|
|
1387
|
sourceString = sourceString.concat(source.getCitation().getCitation());
|
|
1388
|
handleReference(state, source.getCitation());
|
|
1389
|
}
|
|
1390
|
index++;
|
|
1391
|
if (index <= specimenType.getSources().size()){
|
|
1392
|
sourceString = sourceString.concat("; ");
|
|
1393
|
}
|
|
1394
|
}
|
|
1395
|
|
|
1396
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_INFORMATION_REF_STRING)] = sourceString;
|
|
1397
|
if (sources.get(0).getCitation() != null ){
|
|
1398
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_INFORMATION_REF_FK)] = getId(state, sources.get(0).getCitation());
|
|
1399
|
}
|
|
1400
|
}
|
|
1401
|
if (specimenType.getDesignationSource() != null && specimenType.getDesignationSource().getCitation() != null && !state.getReferenceStore().contains(specimenType.getDesignationSource().getCitation().getUuid())){
|
|
1402
|
handleReference(state, specimenType.getDesignationSource().getCitation());
|
|
1403
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_DESIGNATED_BY_REF_FK)] = specimenType.getDesignationSource() != null ? getId(state, specimenType.getDesignationSource().getCitation()): "";
|
|
1404
|
}
|
|
1405
|
|
|
1406
|
|
|
1407
|
Set<TaxonName> typifiedNames = specimenType.getTypifiedNames();
|
|
1408
|
|
|
1409
|
if (typifiedNames.size() > 1){
|
|
1410
|
state.getResult().addWarning("Please check the specimen type "
|
|
1411
|
+ cdmBaseStr(specimenType) + " there are more then one typified name.");
|
|
1412
|
}
|
|
1413
|
if (typifiedNames.iterator().hasNext()){
|
|
1414
|
TaxonName name = typifiedNames.iterator().next();
|
|
1415
|
csvLine[table.getIndex(WordClassificationExportTable.TYPIFIED_NAME_FK)] = getId(state, name);
|
|
1416
|
}
|
|
1417
|
state.getProcessor().put(table, specimenType, csvLine);
|
|
1418
|
|
|
1419
|
|
|
1420
|
|
|
1421
|
|
|
1422
|
|
|
1423
|
}
|
|
1424
|
|
|
1425
|
|
|
1426
|
private String createNameWithItalics(List<TaggedText> taggedName) {
|
|
1427
|
|
|
1428
|
String fullTitleWithHtml = "";
|
|
1429
|
for (TaggedText taggedText: taggedName){
|
|
1430
|
if (taggedText.getType().equals(TagEnum.name)){
|
|
1431
|
fullTitleWithHtml += "<i>" + taggedText.getText() + "</i> ";
|
|
1432
|
}else if (taggedText.getType().equals(TagEnum.separator)){
|
|
1433
|
fullTitleWithHtml = fullTitleWithHtml.trim() + taggedText.getText() ;
|
|
1434
|
}else{
|
|
1435
|
fullTitleWithHtml += taggedText.getText() + " ";
|
|
1436
|
}
|
|
1437
|
}
|
|
1438
|
return fullTitleWithHtml;
|
|
1439
|
}
|
|
1440
|
|
|
1441
|
private void handleNameRelationships(WordClassificationExportState state, TaxonName name) {
|
|
1442
|
Set<NameRelationship> rels = name.getRelationsFromThisName();
|
|
1443
|
WordClassificationExportTable table = WordClassificationExportTable.NAME_RELATIONSHIP;
|
|
1444
|
String[] csvLine = new String[table.getSize()];
|
|
1445
|
|
|
1446
|
for (NameRelationship rel : rels) {
|
|
1447
|
NameRelationshipType type = rel.getType();
|
|
1448
|
TaxonName name2 = rel.getToName();
|
|
1449
|
name2 = HibernateProxyHelper.deproxy(name2, TaxonName.class);
|
|
1450
|
if (!state.getNameStore().containsKey(name2.getId())) {
|
|
1451
|
handleName(state, name2, null);
|
|
1452
|
}
|
|
1453
|
|
|
1454
|
csvLine[table.getIndex(WordClassificationExportTable.NAME_REL_TYPE)] = type.getLabel();
|
|
1455
|
csvLine[table.getIndex(WordClassificationExportTable.NAME1_FK)] = getId(state, name);
|
|
1456
|
csvLine[table.getIndex(WordClassificationExportTable.NAME2_FK)] = getId(state, name2);
|
|
1457
|
state.getProcessor().put(table, name, csvLine);
|
|
1458
|
}
|
|
1459
|
|
|
1460
|
rels = name.getRelationsToThisName();
|
|
1461
|
|
|
1462
|
csvLine = new String[table.getSize()];
|
|
1463
|
|
|
1464
|
for (NameRelationship rel : rels) {
|
|
1465
|
NameRelationshipType type = rel.getType();
|
|
1466
|
TaxonName name2 = rel.getFromName();
|
|
1467
|
name2 = HibernateProxyHelper.deproxy(name2, TaxonName.class);
|
|
1468
|
if (!state.getNameStore().containsKey(name2.getId())) {
|
|
1469
|
handleName(state, name2, null);
|
|
1470
|
}
|
|
1471
|
|
|
1472
|
|
|
1473
|
}
|
|
1474
|
}
|
|
1475
|
|
|
1476
|
private String createCollatation(TaxonName name) {
|
|
1477
|
String collation = "";
|
|
1478
|
if (name.getNomenclaturalReference() != null) {
|
|
1479
|
Reference ref = name.getNomenclaturalReference();
|
|
1480
|
collation = getVolume(ref);
|
|
1481
|
}
|
|
1482
|
if (name.getNomenclaturalMicroReference() != null) {
|
|
1483
|
if (!StringUtils.isBlank(collation)) {
|
|
1484
|
collation += ":";
|
|
1485
|
}
|
|
1486
|
collation += name.getNomenclaturalMicroReference();
|
|
1487
|
}
|
|
1488
|
|
|
1489
|
return collation;
|
|
1490
|
}
|
|
1491
|
|
|
1492
|
private String getVolume(Reference reference) {
|
|
1493
|
if (reference.getVolume() != null) {
|
|
1494
|
return reference.getVolume();
|
|
1495
|
} else if (reference.getInReference() != null) {
|
|
1496
|
if (reference.getInReference().getVolume() != null) {
|
|
1497
|
return reference.getInReference().getVolume();
|
|
1498
|
}
|
|
1499
|
}
|
|
1500
|
return null;
|
|
1501
|
}
|
|
1502
|
|
|
1503
|
private void handleIdentifier(WordClassificationExportState state, CdmBase cdmBase) {
|
|
1504
|
WordClassificationExportTable table = WordClassificationExportTable.IDENTIFIER;
|
|
1505
|
String[] csvLine;
|
|
1506
|
try {
|
|
1507
|
if (cdmBase instanceof TaxonName){
|
|
1508
|
TaxonName name = (TaxonName)cdmBase;
|
|
1509
|
|
|
1510
|
try{
|
|
1511
|
List<Identifier> identifiers = name.getIdentifiers();
|
|
1512
|
|
|
1513
|
//first check which kind of identifiers are available and then sort and create table entries
|
|
1514
|
Map<DefinedTerm, Set<Identifier>> identifierTypes = new HashMap<>();
|
|
1515
|
for (Identifier identifier: identifiers){
|
|
1516
|
DefinedTerm type = identifier.getType();
|
|
1517
|
if (identifierTypes.containsKey(type)){
|
|
1518
|
identifierTypes.get(type).add(identifier);
|
|
1519
|
}else{
|
|
1520
|
Set<Identifier> tempList = new HashSet<>();
|
|
1521
|
tempList.add(identifier);
|
|
1522
|
identifierTypes.put(type, tempList);
|
|
1523
|
}
|
|
1524
|
}
|
|
1525
|
|
|
1526
|
for (DefinedTerm type:identifierTypes.keySet()){
|
|
1527
|
Set<Identifier> identifiersByType = identifierTypes.get(type);
|
|
1528
|
csvLine = new String[table.getSize()];
|
|
1529
|
csvLine[table.getIndex(WordClassificationExportTable.FK)] = getId(state, name);
|
|
1530
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TABLE)] = "ScientificName";
|
|
1531
|
csvLine[table.getIndex(WordClassificationExportTable.IDENTIFIER_TYPE)] = type.getLabel();
|
|
1532
|
csvLine[table.getIndex(WordClassificationExportTable.EXTERNAL_NAME_IDENTIFIER)] = extractIdentifier(
|
|
1533
|
identifiersByType);
|
|
1534
|
state.getProcessor().put(table, name.getUuid() + ", " + type.getLabel(), csvLine);
|
|
1535
|
}
|
|
1536
|
|
|
1537
|
|
|
1538
|
// Set<String> IPNIidentifiers = name.getIdentifiers(DefinedTerm.IDENTIFIER_NAME_IPNI());
|
|
1539
|
// Set<String> tropicosIdentifiers = name.getIdentifiers(DefinedTerm.IDENTIFIER_NAME_TROPICOS());
|
|
1540
|
// Set<String> WFOIdentifiers = name.getIdentifiers(DefinedTerm.uuidWfoNameIdentifier);
|
|
1541
|
// if (!IPNIidentifiers.isEmpty()) {
|
|
1542
|
// csvLine = new String[table.getSize()];
|
|
1543
|
// csvLine[table.getIndex(CdmLightExportTable.FK)] = getId(state, name);
|
|
1544
|
// csvLine[table.getIndex(CdmLightExportTable.REF_TABLE)] = "ScientificName";
|
|
1545
|
// csvLine[table.getIndex(CdmLightExportTable.IDENTIFIER_TYPE)] = IPNI_NAME_IDENTIFIER;
|
|
1546
|
// csvLine[table.getIndex(CdmLightExportTable.EXTERNAL_NAME_IDENTIFIER)] = extractIdentifier(
|
|
1547
|
// IPNIidentifiers);
|
|
1548
|
// state.getProcessor().put(table, name.getUuid() + ", " + IPNI_NAME_IDENTIFIER, csvLine);
|
|
1549
|
// }
|
|
1550
|
// if (!tropicosIdentifiers.isEmpty()) {
|
|
1551
|
// csvLine = new String[table.getSize()];
|
|
1552
|
// csvLine[table.getIndex(CdmLightExportTable.FK)] = getId(state, name);
|
|
1553
|
// csvLine[table.getIndex(CdmLightExportTable.REF_TABLE)] = "ScientificName";
|
|
1554
|
// csvLine[table.getIndex(CdmLightExportTable.IDENTIFIER_TYPE)] = TROPICOS_NAME_IDENTIFIER;
|
|
1555
|
// csvLine[table.getIndex(CdmLightExportTable.EXTERNAL_NAME_IDENTIFIER)] = extractIdentifier(
|
|
1556
|
// tropicosIdentifiers);
|
|
1557
|
// state.getProcessor().put(table, name.getUuid() + ", " + IPNI_NAME_IDENTIFIER, csvLine);
|
|
1558
|
// }
|
|
1559
|
// if (!WFOIdentifiers.isEmpty()) {
|
|
1560
|
// csvLine = new String[table.getSize()];
|
|
1561
|
// csvLine[table.getIndex(CdmLightExportTable.FK)] = getId(state, name);
|
|
1562
|
// csvLine[table.getIndex(CdmLightExportTable.REF_TABLE)] = "ScientificName";
|
|
1563
|
// csvLine[table.getIndex(CdmLightExportTable.IDENTIFIER_TYPE)] = WFO_NAME_IDENTIFIER;
|
|
1564
|
// csvLine[table.getIndex(CdmLightExportTable.EXTERNAL_NAME_IDENTIFIER)] = extractIdentifier(
|
|
1565
|
// WFOIdentifiers);
|
|
1566
|
// state.getProcessor().put(table, name.getUuid() + ", " + WFO_NAME_IDENTIFIER, csvLine);
|
|
1567
|
// }
|
|
1568
|
}catch(Exception e){
|
|
1569
|
state.getResult().addWarning("Please check the identifiers for "
|
|
1570
|
+ cdmBaseStr(cdmBase) + " maybe there is an empty identifier");
|
|
1571
|
|
|
1572
|
|
|
1573
|
}
|
|
1574
|
}else{
|
|
1575
|
if (cdmBase instanceof IdentifiableEntity){
|
|
1576
|
IdentifiableEntity<?> identifiableEntity = (IdentifiableEntity<?>) cdmBase;
|
|
1577
|
List<Identifier> identifiers = identifiableEntity.getIdentifiers();
|
|
1578
|
String tableName = null;
|
|
1579
|
if (cdmBase instanceof Reference){
|
|
1580
|
tableName = "Reference";
|
|
1581
|
}else if (cdmBase instanceof SpecimenOrObservationBase){
|
|
1582
|
tableName = "Specimen";
|
|
1583
|
}else if (cdmBase instanceof Taxon){
|
|
1584
|
tableName = "Taxon";
|
|
1585
|
}else if (cdmBase instanceof Synonym){
|
|
1586
|
tableName = "Synonym";
|
|
1587
|
}else if (cdmBase instanceof TeamOrPersonBase){
|
|
1588
|
tableName = "PersonOrTeam";
|
|
1589
|
}
|
|
1590
|
|
|
1591
|
for (Identifier identifier: identifiers){
|
|
1592
|
if (identifier.getType() == null && identifier.getIdentifier() == null){
|
|
1593
|
state.getResult().addWarning("Please check the identifiers for "
|
|
1594
|
+ cdmBaseStr(cdmBase) + " there is an empty identifier");
|
|
1595
|
continue;
|
|
1596
|
}
|
|
1597
|
|
|
1598
|
csvLine = new String[table.getSize()];
|
|
1599
|
csvLine[table.getIndex(WordClassificationExportTable.FK)] = getId(state, cdmBase);
|
|
1600
|
|
|
1601
|
if (tableName != null){
|
|
1602
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TABLE)] = tableName;
|
|
1603
|
csvLine[table.getIndex(WordClassificationExportTable.IDENTIFIER_TYPE)] = identifier.getType() != null? identifier.getType().getLabel():null;
|
|
1604
|
csvLine[table.getIndex(WordClassificationExportTable.EXTERNAL_NAME_IDENTIFIER)] = identifier.getIdentifier();
|
|
1605
|
state.getProcessor().put(table, cdmBase.getUuid() + (identifier.getType() != null? identifier.getType().getLabel():null), csvLine);
|
|
1606
|
}
|
|
1607
|
}
|
|
1608
|
if (cdmBase instanceof Reference ){
|
|
1609
|
Reference ref = (Reference)cdmBase;
|
|
1610
|
if (ref.getDoi() != null){
|
|
1611
|
csvLine = new String[table.getSize()];
|
|
1612
|
csvLine[table.getIndex(WordClassificationExportTable.FK)] = getId(state, cdmBase);
|
|
1613
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TABLE)] = tableName;
|
|
1614
|
csvLine[table.getIndex(WordClassificationExportTable.IDENTIFIER_TYPE)] = "DOI";
|
|
1615
|
csvLine[table.getIndex(WordClassificationExportTable.EXTERNAL_NAME_IDENTIFIER)] = ref.getDoiString();
|
|
1616
|
state.getProcessor().put(table, cdmBase.getUuid() + "DOI", csvLine);
|
|
1617
|
}
|
|
1618
|
}
|
|
1619
|
|
|
1620
|
if (cdmBase instanceof TeamOrPersonBase){
|
|
1621
|
TeamOrPersonBase<?> person= HibernateProxyHelper.deproxy(cdmBase, TeamOrPersonBase.class);
|
|
1622
|
if (person instanceof Person && ((Person)person).getOrcid() != null){
|
|
1623
|
csvLine = new String[table.getSize()];
|
|
1624
|
csvLine[table.getIndex(WordClassificationExportTable.FK)] = getId(state, cdmBase);
|
|
1625
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TABLE)] = tableName;
|
|
1626
|
csvLine[table.getIndex(WordClassificationExportTable.IDENTIFIER_TYPE)] = "ORCID";
|
|
1627
|
csvLine[table.getIndex(WordClassificationExportTable.EXTERNAL_NAME_IDENTIFIER)]= ((Person)person).getOrcid().asURI();
|
|
1628
|
state.getProcessor().put(table, cdmBase.getUuid() + "ORCID", csvLine);
|
|
1629
|
}
|
|
1630
|
}
|
|
1631
|
}
|
|
1632
|
}
|
|
1633
|
} catch (Exception e) {
|
|
1634
|
state.getResult().addException(e, "An unexpected error occurred when handling identifiers for "
|
|
1635
|
+ cdmBaseStr(cdmBase) + ": " + e.getMessage());
|
|
1636
|
e.printStackTrace();
|
|
1637
|
}
|
|
1638
|
}
|
|
1639
|
|
|
1640
|
private String extractIdentifier(Set<Identifier> identifierSet) {
|
|
1641
|
|
|
1642
|
String identifierString = "";
|
|
1643
|
for (Identifier identifier : identifierSet) {
|
|
1644
|
if (!StringUtils.isBlank(identifierString)) {
|
|
1645
|
identifierString += ", ";
|
|
1646
|
}
|
|
1647
|
identifierString += identifier.getIdentifier();
|
|
1648
|
}
|
|
1649
|
return identifierString;
|
|
1650
|
}
|
|
1651
|
|
|
1652
|
private String extractProtologueURIs(WordClassificationExportState state, TaxonName name) {
|
|
1653
|
if (name.getNomenclaturalSource() != null){
|
|
1654
|
Set<ExternalLink> links = name.getNomenclaturalSource().getLinks();
|
|
1655
|
return extractLinkUris(links.iterator());
|
|
1656
|
}else{
|
|
1657
|
return null;
|
|
1658
|
}
|
|
1659
|
}
|
|
1660
|
|
|
1661
|
private String extractMediaURIs(WordClassificationExportState state, Set<? extends DescriptionBase<?>> descriptionsSet,
|
|
1662
|
Feature feature) {
|
|
1663
|
|
|
1664
|
String mediaUriString = "";
|
|
1665
|
Set<DescriptionElementBase> elements = new HashSet<>();
|
|
1666
|
for (DescriptionBase<?> description : descriptionsSet) {
|
|
1667
|
try {
|
|
1668
|
if (!description.getElements().isEmpty()) {
|
|
1669
|
elements = description.getElements();
|
|
1670
|
|
|
1671
|
for (DescriptionElementBase element : elements) {
|
|
1672
|
Feature entityFeature = HibernateProxyHelper.deproxy(element.getFeature());
|
|
1673
|
if (entityFeature.equals(feature)) {
|
|
1674
|
if (!element.getMedia().isEmpty()) {
|
|
1675
|
List<Media> media = element.getMedia();
|
|
1676
|
for (Media mediaElement : media) {
|
|
1677
|
Iterator<MediaRepresentation> it = mediaElement.getRepresentations().iterator();
|
|
1678
|
mediaUriString = extractMediaUris(it);
|
|
1679
|
}
|
|
1680
|
}
|
|
1681
|
}
|
|
1682
|
}
|
|
1683
|
}
|
|
1684
|
} catch (Exception e) {
|
|
1685
|
state.getResult().addException(e, "An unexpected error occurred when extracting media URIs for "
|
|
1686
|
+ cdmBaseStr(description) + ": " + e.getMessage());
|
|
1687
|
}
|
|
1688
|
}
|
|
1689
|
return mediaUriString;
|
|
1690
|
}
|
|
1691
|
|
|
1692
|
private void handleAuthor(WordClassificationExportState state, TeamOrPersonBase<?> author) {
|
|
1693
|
try {
|
|
1694
|
if (state.getAuthorFromStore(author.getId()) != null) {
|
|
1695
|
return;
|
|
1696
|
}
|
|
1697
|
state.addAuthorToStore(author);
|
|
1698
|
handleIdentifier(state, author);
|
|
1699
|
WordClassificationExportTable table = WordClassificationExportTable.NOMENCLATURAL_AUTHOR;
|
|
1700
|
String[] csvLine = new String[table.getSize()];
|
|
1701
|
WordClassificationExportTable tableAuthorRel = WordClassificationExportTable.NOMENCLATURAL_AUTHOR_TEAM_RELATION;
|
|
1702
|
String[] csvLineRel = new String[tableAuthorRel.getSize()];
|
|
1703
|
String[] csvLineMember = new String[table.getSize()];
|
|
1704
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_ID)] = getId(state, author);
|
|
1705
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_AUTHOR)] = author.isProtectedTitleCache()
|
|
1706
|
? author.getTitleCache() : author.getNomenclaturalTitleCache();
|
|
1707
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_TITLE)] = author.getTitleCache();
|
|
1708
|
author = HibernateProxyHelper.deproxy(author);
|
|
1709
|
if (author instanceof Person) {
|
|
1710
|
Person authorPerson = (Person) author;
|
|
1711
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_GIVEN_NAME)] = authorPerson.getGivenName();
|
|
1712
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_FAMILY_NAME)] = authorPerson.getFamilyName();
|
|
1713
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_PREFIX)] = authorPerson.getPrefix();
|
|
1714
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_SUFFIX)] = authorPerson.getSuffix();
|
|
1715
|
} else {
|
|
1716
|
// create an entry in rel table and all members in author table,
|
|
1717
|
// check whether the team members already in author table
|
|
1718
|
|
|
1719
|
Team authorTeam = (Team) author;
|
|
1720
|
int index = 0;
|
|
1721
|
for (Person member : authorTeam.getTeamMembers()) {
|
|
1722
|
csvLineRel = new String[tableAuthorRel.getSize()];
|
|
1723
|
csvLineRel[tableAuthorRel.getIndex(WordClassificationExportTable.AUTHOR_TEAM_FK)] = getId(state, authorTeam);
|
|
1724
|
csvLineRel[tableAuthorRel.getIndex(WordClassificationExportTable.AUTHOR_FK)] = getId(state, member);
|
|
1725
|
csvLineRel[tableAuthorRel.getIndex(WordClassificationExportTable.AUTHOR_TEAM_SEQ_NUMBER)] = String
|
|
1726
|
.valueOf(index);
|
|
1727
|
state.getProcessor().put(tableAuthorRel, authorTeam.getId() + ":" + member.getId(), csvLineRel);
|
|
1728
|
|
|
1729
|
if (state.getAuthorFromStore(member.getId()) == null) {
|
|
1730
|
state.addAuthorToStore(member);
|
|
1731
|
csvLineMember = new String[table.getSize()];
|
|
1732
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_ID)] = getId(state, member);
|
|
1733
|
csvLineMember[table.getIndex(WordClassificationExportTable.ABBREV_AUTHOR)] = member
|
|
1734
|
.isProtectedTitleCache() ? member.getTitleCache() : member.getNomenclaturalTitleCache();
|
|
1735
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_TITLE)] = member.getTitleCache();
|
|
1736
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_GIVEN_NAME)] = member.getGivenName();
|
|
1737
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_FAMILY_NAME)] = member.getFamilyName();
|
|
1738
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_PREFIX)] = member.getPrefix();
|
|
1739
|
csvLineMember[table.getIndex(WordClassificationExportTable.AUTHOR_SUFFIX)] = member.getSuffix();
|
|
1740
|
state.getProcessor().put(table, member, csvLineMember);
|
|
1741
|
}
|
|
1742
|
index++;
|
|
1743
|
}
|
|
1744
|
}
|
|
1745
|
state.getProcessor().put(table, author, csvLine);
|
|
1746
|
} catch (Exception e) {
|
|
1747
|
state.getResult().addException(e,
|
|
1748
|
"An unexpected error occurred when handling author " + cdmBaseStr(author) + ": " + e.getMessage());
|
|
1749
|
}
|
|
1750
|
}
|
|
1751
|
|
|
1752
|
private String extractStatusString(WordClassificationExportState state, TaxonName name, boolean abbrev) {
|
|
1753
|
try {
|
|
1754
|
Set<NomenclaturalStatus> status = name.getStatus();
|
|
1755
|
if (status.isEmpty()) {
|
|
1756
|
return "";
|
|
1757
|
}
|
|
1758
|
String statusString = "";
|
|
1759
|
for (NomenclaturalStatus nameStatus : status) {
|
|
1760
|
if (nameStatus != null) {
|
|
1761
|
if (abbrev) {
|
|
1762
|
if (nameStatus.getType() != null) {
|
|
1763
|
statusString += nameStatus.getType().getIdInVocabulary();
|
|
1764
|
}
|
|
1765
|
} else {
|
|
1766
|
if (nameStatus.getType() != null) {
|
|
1767
|
statusString += nameStatus.getType().getTitleCache();
|
|
1768
|
}
|
|
1769
|
}
|
|
1770
|
if (!abbrev) {
|
|
1771
|
|
|
1772
|
if (nameStatus.getRuleConsidered() != null
|
|
1773
|
&& !StringUtils.isBlank(nameStatus.getRuleConsidered())) {
|
|
1774
|
statusString += ": " + nameStatus.getRuleConsidered();
|
|
1775
|
}
|
|
1776
|
if (nameStatus.getCitation() != null) {
|
|
1777
|
String shortCitation = OriginalSourceFormatter.INSTANCE.format(nameStatus.getCitation(), null);
|
|
1778
|
statusString += " (" + shortCitation + ")";
|
|
1779
|
}
|
|
1780
|
// if (nameStatus.getCitationMicroReference() != null
|
|
1781
|
// && !StringUtils.isBlank(nameStatus.getCitationMicroReference())) {
|
|
1782
|
// statusString += " " + nameStatus.getCitationMicroReference();
|
|
1783
|
// }
|
|
1784
|
}
|
|
1785
|
statusString += " ";
|
|
1786
|
}
|
|
1787
|
}
|
|
1788
|
return statusString;
|
|
1789
|
} catch (Exception e) {
|
|
1790
|
state.getResult().addException(e, "An unexpected error occurred when extracting status string for "
|
|
1791
|
+ cdmBaseStr(name) + ": " + e.getMessage());
|
|
1792
|
return "";
|
|
1793
|
}
|
|
1794
|
}
|
|
1795
|
|
|
1796
|
private void handleHomotypicalGroup(WordClassificationExportState state, HomotypicalGroup group, Taxon acceptedTaxon, int sortIndex) {
|
|
1797
|
try {
|
|
1798
|
state.addHomotypicalGroupToStore(group);
|
|
1799
|
WordClassificationExportTable table = WordClassificationExportTable.HOMOTYPIC_GROUP;
|
|
1800
|
String[] csvLine = new String[table.getSize()];
|
|
1801
|
csvLine[table.getIndex(WordClassificationExportTable.SORT_INDEX)] = String.valueOf(sortIndex);
|
|
1802
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_ID)] = getId(state, group);
|
|
1803
|
|
|
1804
|
List<TaxonName> typifiedNames = new ArrayList<>();
|
|
1805
|
if (acceptedTaxon != null){
|
|
1806
|
List<Synonym> synonymsInGroup = acceptedTaxon.getSynonymsInGroup(group);
|
|
1807
|
if (group.equals(acceptedTaxon.getHomotypicGroup())){
|
|
1808
|
typifiedNames.add(acceptedTaxon.getName());
|
|
1809
|
}
|
|
1810
|
synonymsInGroup.stream().forEach(synonym -> typifiedNames.add(CdmBase.deproxy(synonym.getName())));
|
|
1811
|
}
|
|
1812
|
|
|
1813
|
|
|
1814
|
TaxonName firstname = null;
|
|
1815
|
for (TaxonName name: typifiedNames){
|
|
1816
|
Iterator<Taxon> taxa = name.getTaxa().iterator();
|
|
1817
|
while(taxa.hasNext()){
|
|
1818
|
Taxon taxon = taxa.next();
|
|
1819
|
if(!(taxon.isMisapplication() || taxon.isProparteSynonym())){
|
|
1820
|
firstname = name;
|
|
1821
|
break;
|
|
1822
|
}
|
|
1823
|
}
|
|
1824
|
}
|
|
1825
|
|
|
1826
|
// Collections.sort(typifiedNames, new HomotypicalGroupNameComparator(firstname, true));
|
|
1827
|
String typifiedNamesString = "";
|
|
1828
|
String typifiedNamesWithSecString = "";
|
|
1829
|
String typifiedNamesWithoutAccepted = "";
|
|
1830
|
String typifiedNamesWithoutAcceptedWithSec = "";
|
|
1831
|
int index = 0;
|
|
1832
|
for (TaxonName name : typifiedNames) {
|
|
1833
|
// Concatenated output string for homotypic group (names and
|
|
1834
|
// citations) + status + some name relations (e.g. “non”)
|
|
1835
|
// TODO: nameRelations, which and how to display
|
|
1836
|
Set<TaxonBase> taxonBases = name.getTaxonBases();
|
|
1837
|
TaxonBase<?> taxonBase;
|
|
1838
|
|
|
1839
|
String sec = "";
|
|
1840
|
String nameString = name.getFullTitleCache();
|
|
1841
|
String doubtful = "";
|
|
1842
|
|
|
1843
|
if (state.getConfig().isAddHTML()){
|
|
1844
|
nameString = createNameWithItalics(name.getTaggedFullTitle()) ;
|
|
1845
|
}
|
|
1846
|
|
|
1847
|
Set<NameRelationship> related = name.getNameRelations();
|
|
1848
|
List<NameRelationship> relatedList = new ArrayList<>(related);
|
|
1849
|
|
|
1850
|
Collections.sort(relatedList, new Comparator<NameRelationship>() {
|
|
1851
|
@Override
|
|
1852
|
public int compare(NameRelationship nr1, NameRelationship nr2) {
|
|
1853
|
return nr1.getType().compareTo(nr2.getType());
|
|
1854
|
}
|
|
1855
|
|
|
1856
|
});
|
|
1857
|
|
|
1858
|
List<NameRelationship> nonNames = new ArrayList<>();
|
|
1859
|
List<NameRelationship> otherRelationships = new ArrayList<>();
|
|
1860
|
|
|
1861
|
for (NameRelationship rel: relatedList){
|
|
1862
|
//no inverse relations
|
|
1863
|
if (rel.getFromName().equals(name)){
|
|
1864
|
// alle Homonyme und inverse blocking names
|
|
1865
|
if (rel.getType().equals(NameRelationshipType.LATER_HOMONYM())
|
|
1866
|
|| rel.getType().equals(NameRelationshipType.TREATED_AS_LATER_HOMONYM())
|
|
1867
|
|| (rel.getType().equals(NameRelationshipType.BLOCKING_NAME_FOR()))
|
|
1868
|
|| (rel.getType().equals(NameRelationshipType.UNSPECIFIC_NON()))){
|
|
1869
|
nonNames.add(rel);
|
|
1870
|
}else if (!rel.getType().isBasionymRelation()){
|
|
1871
|
otherRelationships.add(rel);
|
|
1872
|
}
|
|
1873
|
}
|
|
1874
|
}
|
|
1875
|
|
|
1876
|
String nonRelNames = "";
|
|
1877
|
String relNames = "";
|
|
1878
|
|
|
1879
|
if (nonNames.size() > 0){
|
|
1880
|
nonRelNames += " [";
|
|
1881
|
}
|
|
1882
|
for (NameRelationship relName: nonNames){
|
|
1883
|
String label = "non ";
|
|
1884
|
TaxonName relatedName = null;
|
|
1885
|
if (relName.getFromName().equals(name)){
|
|
1886
|
relatedName = relName.getToName();
|
|
1887
|
nonRelNames += label + relatedName.getTitleCache() + " ";
|
|
1888
|
}
|
|
1889
|
// else{
|
|
1890
|
// label = relName.getType().getInverseLabel() + " ";
|
|
1891
|
// relatedName = relName.getFromName();
|
|
1892
|
// nonRelNames += label + relatedName.getTitleCache() + " ";
|
|
1893
|
// }
|
|
1894
|
|
|
1895
|
|
|
1896
|
}
|
|
1897
|
relNames.trim();
|
|
1898
|
if (nonNames.size() > 0){
|
|
1899
|
nonRelNames = StringUtils.strip(nonRelNames, null);
|
|
1900
|
nonRelNames += "] ";
|
|
1901
|
}
|
|
1902
|
|
|
1903
|
if (otherRelationships.size() > 0){
|
|
1904
|
relNames += " [";
|
|
1905
|
}
|
|
1906
|
for (NameRelationship rel: otherRelationships){
|
|
1907
|
String label = "";
|
|
1908
|
TaxonName relatedName = null;
|
|
1909
|
if (rel.getFromName().equals(name)){
|
|
1910
|
label = rel.getType().getLabel() + " ";
|
|
1911
|
relatedName = rel.getToName();
|
|
1912
|
if (state.getConfig().isAddHTML()){
|
|
1913
|
relNames += label + createNameWithItalics(relatedName.getTaggedName())+ " ";
|
|
1914
|
}else{
|
|
1915
|
relNames += label + relatedName.getTitleCache();
|
|
1916
|
}
|
|
1917
|
}
|
|
1918
|
// else {
|
|
1919
|
// label = rel.getType().getInverseLabel() + " ";
|
|
1920
|
// relatedName = rel.getFromName();
|
|
1921
|
// }
|
|
1922
|
|
|
1923
|
}
|
|
1924
|
relNames.trim();
|
|
1925
|
if (otherRelationships.size() > 0){
|
|
1926
|
relNames = StringUtils.stripEnd(relNames, null);
|
|
1927
|
relNames += "] ";
|
|
1928
|
}
|
|
1929
|
|
|
1930
|
String synonymSign = "";
|
|
1931
|
if (index > 0){
|
|
1932
|
if (name.isInvalid()){
|
|
1933
|
synonymSign = "\u2212 ";
|
|
1934
|
}else{
|
|
1935
|
synonymSign = "\u2261 ";
|
|
1936
|
}
|
|
1937
|
}else{
|
|
1938
|
if (name.isInvalid() ){
|
|
1939
|
synonymSign = "\u2212 ";
|
|
1940
|
}else{
|
|
1941
|
synonymSign = "\u003D ";
|
|
1942
|
}
|
|
1943
|
}
|
|
1944
|
boolean isAccepted = false;
|
|
1945
|
|
|
1946
|
if (taxonBases.size() == 1){
|
|
1947
|
taxonBase = HibernateProxyHelper.deproxy(taxonBases.iterator().next());
|
|
1948
|
|
|
1949
|
if (taxonBase.getSec() != null){
|
|
1950
|
sec = OriginalSourceFormatter.INSTANCE_WITH_YEAR_BRACKETS.format(taxonBase.getSecSource());
|
|
1951
|
}
|
|
1952
|
if (taxonBase.isDoubtful()){
|
|
1953
|
doubtful = "?";
|
|
1954
|
}else{
|
|
1955
|
doubtful = "";
|
|
1956
|
}
|
|
1957
|
if (taxonBase instanceof Synonym){
|
|
1958
|
if (isNotBlank(sec)){
|
|
1959
|
sec = " syn. sec. " + sec + " ";
|
|
1960
|
}else {
|
|
1961
|
sec = "";
|
|
1962
|
}
|
|
1963
|
|
|
1964
|
typifiedNamesWithoutAccepted += synonymSign + doubtful + nameString + nonRelNames + relNames;
|
|
1965
|
typifiedNamesWithoutAcceptedWithSec += synonymSign + doubtful + nameString + sec + nonRelNames + relNames;
|
|
1966
|
}else{
|
|
1967
|
// sec = "";
|
|
1968
|
if (!(((Taxon)taxonBase).isProparteSynonym() || ((Taxon)taxonBase).isMisapplication())){
|
|
1969
|
isAccepted = true;
|
|
1970
|
}else {
|
|
1971
|
synonymSign = "\u003D ";
|
|
1972
|
}
|
|
1973
|
|
|
1974
|
}
|
|
1975
|
if (taxonBase.getAppendedPhrase() != null){
|
|
1976
|
if (state.getConfig().isAddHTML()){
|
|
1977
|
String taxonString = createNameWithItalics(taxonBase.getTaggedTitle()) ;
|
|
1978
|
taxonString = taxonString.replace("sec "+sec, "");
|
|
1979
|
String nameCacheWithItalics = createNameWithItalics(name.getTaggedName());
|
|
1980
|
nameString = nameString.replace(nameCacheWithItalics, taxonString);
|
|
1981
|
}
|
|
1982
|
}
|
|
1983
|
}else{
|
|
1984
|
//there are names used more than once?
|
|
1985
|
for (TaxonBase<?> tb: taxonBases){
|
|
1986
|
if (tb.getSec() != null){
|
|
1987
|
sec = OriginalSourceFormatter.INSTANCE_WITH_YEAR_BRACKETS.format(tb.getSecSource());
|
|
1988
|
}
|
|
1989
|
if (tb.isDoubtful()){
|
|
1990
|
doubtful = "?";
|
|
1991
|
}else{
|
|
1992
|
doubtful = "";
|
|
1993
|
}
|
|
1994
|
if (tb instanceof Synonym){
|
|
1995
|
if (StringUtils.isNotBlank(sec)){
|
|
1996
|
sec = " syn. sec. " + sec + " ";
|
|
1997
|
}else {
|
|
1998
|
sec = "";
|
|
1999
|
}
|
|
2000
|
|
|
2001
|
break;
|
|
2002
|
}else{
|
|
2003
|
sec = "";
|
|
2004
|
if (!(((Taxon)tb).isProparteSynonym() || ((Taxon)tb).isMisapplication())){
|
|
2005
|
isAccepted = true;
|
|
2006
|
break;
|
|
2007
|
}else {
|
|
2008
|
synonymSign = "\u003D ";
|
|
2009
|
}
|
|
2010
|
|
|
2011
|
}
|
|
2012
|
}
|
|
2013
|
if (!isAccepted){
|
|
2014
|
typifiedNamesWithoutAccepted += synonymSign + doubtful + nameString + "; ";
|
|
2015
|
typifiedNamesWithoutAcceptedWithSec += synonymSign + doubtful + nameString + sec;
|
|
2016
|
typifiedNamesWithoutAcceptedWithSec = typifiedNamesWithoutAcceptedWithSec.trim() + "; ";
|
|
2017
|
}
|
|
2018
|
}
|
|
2019
|
typifiedNamesString += synonymSign + doubtful + nameString + nonRelNames + relNames;
|
|
2020
|
typifiedNamesWithSecString += synonymSign + doubtful + nameString + sec + nonRelNames + relNames;
|
|
2021
|
|
|
2022
|
|
|
2023
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_STRING)] = typifiedNamesString.trim();
|
|
2024
|
|
|
2025
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_WITH_SEC_STRING)] = typifiedNamesWithSecString.trim();
|
|
2026
|
|
|
2027
|
if (typifiedNamesWithoutAccepted != null && firstname != null) {
|
|
2028
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_WITHOUT_ACCEPTED)] = typifiedNamesWithoutAccepted.trim();
|
|
2029
|
} else {
|
|
2030
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_WITHOUT_ACCEPTED)] = "";
|
|
2031
|
}
|
|
2032
|
|
|
2033
|
if (typifiedNamesWithoutAcceptedWithSec != null && firstname != null) {
|
|
2034
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_WITHOUT_ACCEPTEDWITHSEC)] = typifiedNamesWithoutAcceptedWithSec.trim();
|
|
2035
|
} else {
|
|
2036
|
csvLine[table.getIndex(WordClassificationExportTable.HOMOTYPIC_GROUP_WITHOUT_ACCEPTEDWITHSEC)] = "";
|
|
2037
|
}
|
|
2038
|
index++;
|
|
2039
|
}
|
|
2040
|
|
|
2041
|
Set<TypeDesignationBase<?>> typeDesigantionSet = group.getTypeDesignations();
|
|
2042
|
List<TypeDesignationBase<?>> designationList = new ArrayList<>();
|
|
2043
|
designationList.addAll(typeDesigantionSet);
|
|
2044
|
Collections.sort(designationList, new TypeComparator());
|
|
2045
|
|
|
2046
|
List<TaggedText> list = new ArrayList<>();
|
|
2047
|
if (!designationList.isEmpty()) {
|
|
2048
|
TypeDesignationSetContainer manager = new TypeDesignationSetContainer(group);
|
|
2049
|
list.addAll(new TypeDesignationSetFormatter(true, false, false).toTaggedText(manager));
|
|
2050
|
}
|
|
2051
|
String typeTextDesignations = "";
|
|
2052
|
//The typeDesignationManager does not handle the textual typeDesignations
|
|
2053
|
for (TypeDesignationBase<?> typeDes: designationList) {
|
|
2054
|
if (typeDes instanceof TextualTypeDesignation) {
|
|
2055
|
typeTextDesignations = typeTextDesignations + ((TextualTypeDesignation)typeDes).getText(Language.getDefaultLanguage());
|
|
2056
|
String typeDesStateRefs = "";
|
|
2057
|
if (typeDes.getDesignationSource() != null ){
|
|
2058
|
typeDesStateRefs = "[";
|
|
2059
|
NamedSource source = typeDes.getDesignationSource();
|
|
2060
|
if (source.getCitation() != null){
|
|
2061
|
typeDesStateRefs += "fide " + OriginalSourceFormatter.INSTANCE.format(source.getCitation(), null);
|
|
2062
|
}
|
|
2063
|
typeDesStateRefs += "]";
|
|
2064
|
}else if (typeDes.getSources() != null && !typeDes.getSources().isEmpty()){
|
|
2065
|
typeDesStateRefs = "[";
|
|
2066
|
for (IdentifiableSource source: typeDes.getSources()) {
|
|
2067
|
if (source.getCitation() != null){
|
|
2068
|
typeDesStateRefs += "fide " +OriginalSourceFormatter.INSTANCE.format(source.getCitation(), null);
|
|
2069
|
}
|
|
2070
|
}
|
|
2071
|
|
|
2072
|
typeDesStateRefs += "]";
|
|
2073
|
}
|
|
2074
|
|
|
2075
|
typeTextDesignations = typeTextDesignations + typeDesStateRefs +"; ";
|
|
2076
|
|
|
2077
|
}else if (typeDes instanceof SpecimenTypeDesignation){
|
|
2078
|
DerivedUnit specimen = ((SpecimenTypeDesignation)typeDes).getTypeSpecimen();
|
|
2079
|
if(specimen != null && !state.getSpecimenStore().contains( specimen.getUuid())){
|
|
2080
|
handleSpecimen(state, specimen);
|
|
2081
|
}
|
|
2082
|
}
|
|
2083
|
}
|
|
2084
|
if (typeTextDesignations.equals("; ")) {
|
|
2085
|
typeTextDesignations = "";
|
|
2086
|
}
|
|
2087
|
if (StringUtils.isNotBlank(typeTextDesignations)) {
|
|
2088
|
typeTextDesignations = typeTextDesignations.substring(0, typeTextDesignations.length()-2);
|
|
2089
|
}
|
|
2090
|
String specimenTypeString = !list.isEmpty()? createTypeDesignationString(list, true, typifiedNames.get(0).isSpecies() || typifiedNames.get(0).isInfraSpecific()):"";
|
|
2091
|
|
|
2092
|
if (StringUtils.isNotBlank(specimenTypeString)) {
|
|
2093
|
if (!specimenTypeString.endsWith(".")) {
|
|
2094
|
specimenTypeString = specimenTypeString + ".";
|
|
2095
|
}
|
|
2096
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_STRING)] = specimenTypeString;
|
|
2097
|
|
|
2098
|
} else {
|
|
2099
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_STRING)] = "";
|
|
2100
|
}
|
|
2101
|
if (StringUtils.isNotBlank(typeTextDesignations)) {
|
|
2102
|
if (!typeTextDesignations.endsWith(".")) {
|
|
2103
|
typeTextDesignations = typeTextDesignations + ".";
|
|
2104
|
}
|
|
2105
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_CACHE)] = typeTextDesignations;
|
|
2106
|
|
|
2107
|
} else {
|
|
2108
|
csvLine[table.getIndex(WordClassificationExportTable.TYPE_CACHE)] = "";
|
|
2109
|
}
|
|
2110
|
state.getProcessor().put(table, String.valueOf(group.getId()), csvLine);
|
|
2111
|
} catch (Exception e) {
|
|
2112
|
state.getResult().addException(e, "An unexpected error occurred when handling homotypic group "
|
|
2113
|
+ cdmBaseStr(group) + ": " + e.getMessage());
|
|
2114
|
}
|
|
2115
|
}
|
|
2116
|
|
|
2117
|
private String createTypeDesignationString(List<TaggedText> list, boolean isHomotypicGroup, boolean isSpecimenTypeDesignation) {
|
|
2118
|
StringBuffer homotypicalGroupTypeDesignationString = new StringBuffer();
|
|
2119
|
|
|
2120
|
for (TaggedText text : list) {
|
|
2121
|
if (text == null || text.getText() == null){
|
|
2122
|
continue; //just in case
|
|
2123
|
}
|
|
2124
|
if ((text.getText().equalsIgnoreCase("Type:") //should not happen anymore
|
|
2125
|
|| text.getText().equalsIgnoreCase("Nametype:") //should not happen anymore
|
|
2126
|
|| (text.getType().equals(TagEnum.name) && !isHomotypicGroup))) {
|
|
2127
|
// do nothing
|
|
2128
|
}else if (text.getType().equals(TagEnum.reference)) {
|
|
2129
|
homotypicalGroupTypeDesignationString.append(text.getText());
|
|
2130
|
}else if (text.getType().equals(TagEnum.name)){
|
|
2131
|
if (!isSpecimenTypeDesignation){
|
|
2132
|
homotypicalGroupTypeDesignationString
|
|
2133
|
.append("<i>"+text.getText()+"</i> ");
|
|
2134
|
}
|
|
2135
|
}else if (text.getType().equals(TagEnum.typeDesignation) ) {
|
|
2136
|
if(isSpecimenTypeDesignation){
|
|
2137
|
homotypicalGroupTypeDesignationString
|
|
2138
|
.append(text.getText().replace(").", "").replace("(", "").replace(")", ""));
|
|
2139
|
}else{
|
|
2140
|
homotypicalGroupTypeDesignationString
|
|
2141
|
.append(text.getText());
|
|
2142
|
}
|
|
2143
|
|
|
2144
|
} else {
|
|
2145
|
homotypicalGroupTypeDesignationString.append(text.getText());
|
|
2146
|
}
|
|
2147
|
}
|
|
2148
|
|
|
2149
|
String typeDesignations = homotypicalGroupTypeDesignationString.toString();
|
|
2150
|
typeDesignations = typeDesignations.trim();
|
|
2151
|
|
|
2152
|
if (typeDesignations.endsWith(";")){
|
|
2153
|
typeDesignations = typeDesignations.substring(0, typeDesignations.length()-1);
|
|
2154
|
}
|
|
2155
|
typeDesignations += ".";
|
|
2156
|
typeDesignations = typeDesignations.replace("..", ".");
|
|
2157
|
typeDesignations = typeDesignations.replace(". .", ".");
|
|
2158
|
typeDesignations = typeDesignations.replace("; \u2261", " \u2261 ");
|
|
2159
|
|
|
2160
|
if (typeDesignations.trim().equals(".")) {
|
|
2161
|
typeDesignations = null;
|
|
2162
|
}
|
|
2163
|
|
|
2164
|
return typeDesignations;
|
|
2165
|
}
|
|
2166
|
|
|
2167
|
private String getTropicosTitleCache(WordClassificationExportState state, TaxonName name) {
|
|
2168
|
try {
|
|
2169
|
String basionymStart = "(";
|
|
2170
|
String basionymEnd = ") ";
|
|
2171
|
String exAuthorSeperator = " ex ";
|
|
2172
|
TeamOrPersonBase<?> combinationAuthor = name.getCombinationAuthorship();
|
|
2173
|
TeamOrPersonBase<?> exCombinationAuthor = name.getExCombinationAuthorship();
|
|
2174
|
TeamOrPersonBase<?> basionymAuthor = name.getBasionymAuthorship();
|
|
2175
|
TeamOrPersonBase<?> exBasionymAuthor = name.getExBasionymAuthorship();
|
|
2176
|
|
|
2177
|
String combinationAuthorString = "";
|
|
2178
|
if (combinationAuthor != null) {
|
|
2179
|
combinationAuthor = HibernateProxyHelper.deproxy(combinationAuthor);
|
|
2180
|
if (combinationAuthor instanceof Team) {
|
|
2181
|
combinationAuthorString = createTropicosTeamTitle(combinationAuthor);
|
|
2182
|
} else {
|
|
2183
|
Person person = HibernateProxyHelper.deproxy(combinationAuthor, Person.class);
|
|
2184
|
combinationAuthorString = createTropicosAuthorString(person);
|
|
2185
|
}
|
|
2186
|
}
|
|
2187
|
String exCombinationAuthorString = "";
|
|
2188
|
if (exCombinationAuthor != null) {
|
|
2189
|
exCombinationAuthor = HibernateProxyHelper.deproxy(exCombinationAuthor);
|
|
2190
|
if (exCombinationAuthor instanceof Team) {
|
|
2191
|
exCombinationAuthorString = createTropicosTeamTitle(exCombinationAuthor);
|
|
2192
|
} else {
|
|
2193
|
Person person = HibernateProxyHelper.deproxy(exCombinationAuthor, Person.class);
|
|
2194
|
exCombinationAuthorString = createTropicosAuthorString(person);
|
|
2195
|
}
|
|
2196
|
}
|
|
2197
|
|
|
2198
|
String basionymAuthorString = "";
|
|
2199
|
if (basionymAuthor != null) {
|
|
2200
|
basionymAuthor = HibernateProxyHelper.deproxy(basionymAuthor);
|
|
2201
|
if (basionymAuthor instanceof Team) {
|
|
2202
|
basionymAuthorString = createTropicosTeamTitle(basionymAuthor);
|
|
2203
|
} else {
|
|
2204
|
Person person = HibernateProxyHelper.deproxy(basionymAuthor, Person.class);
|
|
2205
|
basionymAuthorString = createTropicosAuthorString(person);
|
|
2206
|
}
|
|
2207
|
}
|
|
2208
|
|
|
2209
|
String exBasionymAuthorString = "";
|
|
2210
|
|
|
2211
|
if (exBasionymAuthor != null) {
|
|
2212
|
exBasionymAuthor = HibernateProxyHelper.deproxy(exBasionymAuthor);
|
|
2213
|
if (exBasionymAuthor instanceof Team) {
|
|
2214
|
exBasionymAuthorString = createTropicosTeamTitle(exBasionymAuthor);
|
|
2215
|
|
|
2216
|
} else {
|
|
2217
|
Person person = HibernateProxyHelper.deproxy(exBasionymAuthor, Person.class);
|
|
2218
|
exBasionymAuthorString = createTropicosAuthorString(person);
|
|
2219
|
}
|
|
2220
|
}
|
|
2221
|
String completeAuthorString = name.getNameCache() + " ";
|
|
2222
|
|
|
2223
|
completeAuthorString += (!CdmUtils.isBlank(exBasionymAuthorString)
|
|
2224
|
|| !CdmUtils.isBlank(basionymAuthorString)) ? basionymStart : "";
|
|
2225
|
completeAuthorString += (!CdmUtils.isBlank(exBasionymAuthorString))
|
|
2226
|
? (CdmUtils.Nz(exBasionymAuthorString) + exAuthorSeperator) : "";
|
|
2227
|
completeAuthorString += (!CdmUtils.isBlank(basionymAuthorString)) ? CdmUtils.Nz(basionymAuthorString) : "";
|
|
2228
|
completeAuthorString += (!CdmUtils.isBlank(exBasionymAuthorString)
|
|
2229
|
|| !CdmUtils.isBlank(basionymAuthorString)) ? basionymEnd : "";
|
|
2230
|
completeAuthorString += (!CdmUtils.isBlank(exCombinationAuthorString))
|
|
2231
|
? (CdmUtils.Nz(exCombinationAuthorString) + exAuthorSeperator) : "";
|
|
2232
|
completeAuthorString += (!CdmUtils.isBlank(combinationAuthorString)) ? CdmUtils.Nz(combinationAuthorString)
|
|
2233
|
: "";
|
|
2234
|
|
|
2235
|
return completeAuthorString;
|
|
2236
|
} catch (Exception e) {
|
|
2237
|
state.getResult().addException(e, "An unexpected error occurred when handling tropicos title cache for "
|
|
2238
|
+ cdmBaseStr(name) + ": " + e.getMessage());
|
|
2239
|
return null;
|
|
2240
|
}
|
|
2241
|
}
|
|
2242
|
|
|
2243
|
private String createTropicosTeamTitle(TeamOrPersonBase<?> combinationAuthor) {
|
|
2244
|
String combinationAuthorString;
|
|
2245
|
Team team = HibernateProxyHelper.deproxy(combinationAuthor, Team.class);
|
|
2246
|
Team tempTeam = Team.NewInstance();
|
|
2247
|
for (Person teamMember : team.getTeamMembers()) {
|
|
2248
|
combinationAuthorString = createTropicosAuthorString(teamMember);
|
|
2249
|
Person tempPerson = Person.NewTitledInstance(combinationAuthorString);
|
|
2250
|
tempTeam.addTeamMember(tempPerson);
|
|
2251
|
}
|
|
2252
|
combinationAuthorString = tempTeam.generateTitle();
|
|
2253
|
return combinationAuthorString;
|
|
2254
|
}
|
|
2255
|
|
|
2256
|
private String createTropicosAuthorString(Person teamMember) {
|
|
2257
|
String nomAuthorString = "";
|
|
2258
|
String[] splittedAuthorString = null;
|
|
2259
|
if (teamMember == null) {
|
|
2260
|
return nomAuthorString;
|
|
2261
|
}
|
|
2262
|
|
|
2263
|
if (teamMember.getGivenName() != null) {
|
|
2264
|
String givenNameString = teamMember.getGivenName().replaceAll("\\.", "\\. ");
|
|
2265
|
splittedAuthorString = givenNameString.split("\\s");
|
|
2266
|
for (String split : splittedAuthorString) {
|
|
2267
|
if (!StringUtils.isBlank(split)) {
|
|
2268
|
nomAuthorString += split.substring(0, 1);
|
|
2269
|
nomAuthorString += ".";
|
|
2270
|
}
|
|
2271
|
}
|
|
2272
|
}
|
|
2273
|
if (teamMember.getFamilyName() != null) {
|
|
2274
|
String familyNameString = teamMember.getFamilyName().replaceAll("\\.", "\\. ");
|
|
2275
|
splittedAuthorString = familyNameString.split("\\s");
|
|
2276
|
for (String split : splittedAuthorString) {
|
|
2277
|
nomAuthorString += " " + split;
|
|
2278
|
}
|
|
2279
|
}
|
|
2280
|
if (isBlank(nomAuthorString.trim())) {
|
|
2281
|
if (teamMember.getTitleCache() != null) {
|
|
2282
|
String titleCacheString = teamMember.getTitleCache().replaceAll("\\.", "\\. ");
|
|
2283
|
splittedAuthorString = titleCacheString.split("\\s");
|
|
2284
|
} else {
|
|
2285
|
splittedAuthorString = new String[0];
|
|
2286
|
}
|
|
2287
|
|
|
2288
|
int index = 0;
|
|
2289
|
for (String split : splittedAuthorString) {
|
|
2290
|
if (index < splittedAuthorString.length - 1 && (split.length() == 1 || split.endsWith("."))) {
|
|
2291
|
nomAuthorString += split;
|
|
2292
|
} else {
|
|
2293
|
nomAuthorString = nomAuthorString + " " + split;
|
|
2294
|
}
|
|
2295
|
index++;
|
|
2296
|
}
|
|
2297
|
}
|
|
2298
|
return nomAuthorString.trim();
|
|
2299
|
}
|
|
2300
|
|
|
2301
|
private void handleReference(WordClassificationExportState state, Reference reference) {
|
|
2302
|
try {
|
|
2303
|
state.addReferenceToStore(reference);
|
|
2304
|
WordClassificationExportTable table = WordClassificationExportTable.REFERENCE;
|
|
2305
|
reference = HibernateProxyHelper.deproxy(reference);
|
|
2306
|
|
|
2307
|
handleIdentifier(state, reference);
|
|
2308
|
String[] csvLine = new String[table.getSize()];
|
|
2309
|
csvLine[table.getIndex(WordClassificationExportTable.REFERENCE_ID)] = getId(state, reference);
|
|
2310
|
// TODO short citations correctly
|
|
2311
|
String shortCitation = OriginalSourceFormatter.INSTANCE_WITH_YEAR_BRACKETS.format(reference, null); // Should be Author(year) like in Taxon.sec
|
|
2312
|
csvLine[table.getIndex(WordClassificationExportTable.BIBLIO_SHORT_CITATION)] = shortCitation;
|
|
2313
|
// TODO get preferred title
|
|
2314
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TITLE)] = reference.isProtectedTitleCache()
|
|
2315
|
? reference.getTitleCache() : reference.getTitle();
|
|
2316
|
csvLine[table.getIndex(WordClassificationExportTable.ABBREV_REF_TITLE)] = reference.isProtectedAbbrevTitleCache()
|
|
2317
|
? reference.getAbbrevTitleCache() : reference.getAbbrevTitle();
|
|
2318
|
csvLine[table.getIndex(WordClassificationExportTable.DATE_PUBLISHED)] = reference.getDatePublishedString();
|
|
2319
|
// TBC
|
|
2320
|
csvLine[table.getIndex(WordClassificationExportTable.EDITION)] = reference.getEdition();
|
|
2321
|
csvLine[table.getIndex(WordClassificationExportTable.EDITOR)] = reference.getEditor();
|
|
2322
|
csvLine[table.getIndex(WordClassificationExportTable.ISBN)] = reference.getIsbn();
|
|
2323
|
csvLine[table.getIndex(WordClassificationExportTable.ISSN)] = reference.getIssn();
|
|
2324
|
csvLine[table.getIndex(WordClassificationExportTable.ORGANISATION)] = reference.getOrganization();
|
|
2325
|
csvLine[table.getIndex(WordClassificationExportTable.PAGES)] = reference.getPages();
|
|
2326
|
csvLine[table.getIndex(WordClassificationExportTable.PLACE_PUBLISHED)] = reference.getPlacePublished();
|
|
2327
|
csvLine[table.getIndex(WordClassificationExportTable.PUBLISHER)] = reference.getPublisher();
|
|
2328
|
csvLine[table.getIndex(WordClassificationExportTable.REF_ABSTRACT)] = reference.getReferenceAbstract();
|
|
2329
|
csvLine[table.getIndex(WordClassificationExportTable.SERIES_PART)] = reference.getSeriesPart();
|
|
2330
|
csvLine[table.getIndex(WordClassificationExportTable.VOLUME)] = reference.getVolume();
|
|
2331
|
csvLine[table.getIndex(WordClassificationExportTable.YEAR)] = reference.getYear();
|
|
2332
|
|
|
2333
|
if (reference.getAuthorship() != null) {
|
|
2334
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHORSHIP_TITLE)] = createFullAuthorship(reference);
|
|
2335
|
csvLine[table.getIndex(WordClassificationExportTable.AUTHOR_FK)] = getId(state, reference.getAuthorship());
|
|
2336
|
}
|
|
2337
|
|
|
2338
|
csvLine[table.getIndex(WordClassificationExportTable.IN_REFERENCE)] = getId(state, reference.getInReference());
|
|
2339
|
if (reference.getInReference() != null
|
|
2340
|
&& !state.getReferenceStore().contains(reference.getInReference().getUuid())) {
|
|
2341
|
handleReference(state, reference.getInReference());
|
|
2342
|
}
|
|
2343
|
if (reference.getInstitution() != null) {
|
|
2344
|
csvLine[table.getIndex(WordClassificationExportTable.INSTITUTION)] = reference.getInstitution().getTitleCache();
|
|
2345
|
}
|
|
2346
|
if (reference.getLsid() != null) {
|
|
2347
|
csvLine[table.getIndex(WordClassificationExportTable.LSID)] = reference.getLsid().getLsid();
|
|
2348
|
}
|
|
2349
|
if (reference.getSchool() != null) {
|
|
2350
|
csvLine[table.getIndex(WordClassificationExportTable.SCHOOL)] = reference.getSchool().getTitleCache();
|
|
2351
|
}
|
|
2352
|
if (reference.getUri() != null) {
|
|
2353
|
csvLine[table.getIndex(WordClassificationExportTable.URI)] = reference.getUri().toString();
|
|
2354
|
}
|
|
2355
|
csvLine[table.getIndex(WordClassificationExportTable.REF_TYPE)] = reference.getType().getKey();
|
|
2356
|
|
|
2357
|
state.getProcessor().put(table, reference, csvLine);
|
|
2358
|
} catch (Exception e) {
|
|
2359
|
state.getResult().addException(e, "An unexpected error occurred when handling reference "
|
|
2360
|
+ cdmBaseStr(reference) + ": " + e.getMessage());
|
|
2361
|
}
|
|
2362
|
}
|
|
2363
|
|
|
2364
|
private String createFullAuthorship(Reference reference) {
|
|
2365
|
TeamOrPersonBase<?> authorship = reference.getAuthorship();
|
|
2366
|
String fullAuthorship = "";
|
|
2367
|
if (authorship == null) {
|
|
2368
|
return null;
|
|
2369
|
}
|
|
2370
|
authorship = HibernateProxyHelper.deproxy(authorship);
|
|
2371
|
if (authorship instanceof Person) {
|
|
2372
|
fullAuthorship = ((Person) authorship).getTitleCache();
|
|
2373
|
|
|
2374
|
} else if (authorship instanceof Team) {
|
|
2375
|
|
|
2376
|
Team authorTeam = (Team)authorship;
|
|
2377
|
fullAuthorship = authorTeam.cacheStrategy().getTitleCache(authorTeam);
|
|
2378
|
}
|
|
2379
|
return fullAuthorship;
|
|
2380
|
}
|
|
2381
|
|
|
2382
|
private void handleSpecimen(WordClassificationExportState state, SpecimenOrObservationBase<?> specimen) {
|
|
2383
|
try {
|
|
2384
|
state.addSpecimenToStore(specimen);
|
|
2385
|
WordClassificationExportTable table = WordClassificationExportTable.SPECIMEN;
|
|
2386
|
String specimenId = getId(state, specimen);
|
|
2387
|
String[] csvLine = new String[table.getSize()];
|
|
2388
|
|
|
2389
|
/*
|
|
2390
|
* SpecimenCitation = “El Salvador, Municipio La Libertad, San
|
|
2391
|
* Diego, El Amatal, 14.4.1993, González 159” [Auch ohne Punkt] ->
|
|
2392
|
* FieldUnit TitleCache HerbariumAbbrev = “B” [wie gehabt]
|
|
2393
|
* HerbariumCode
|
|
2394
|
*
|
|
2395
|
*/
|
|
2396
|
|
|
2397
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_ID)] = specimenId;
|
|
2398
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_CITATION)] = specimen.getTitleCache();
|
|
2399
|
Collection<FieldUnit> fieldUnits = this.getOccurrenceService().findFieldUnits(specimen.getUuid(), null);
|
|
2400
|
if (fieldUnits.size() == 1) {
|
|
2401
|
Iterator<FieldUnit> iterator = fieldUnits.iterator();
|
|
2402
|
if (iterator.hasNext()){
|
|
2403
|
FieldUnit fieldUnit = iterator.next();
|
|
2404
|
csvLine[table.getIndex(WordClassificationExportTable.FIELDUNIT_CITATION)] = fieldUnit.getTitleCache();
|
|
2405
|
}
|
|
2406
|
}
|
|
2407
|
if (specimen.isInstanceOf(DerivedUnit.class)){
|
|
2408
|
DerivedUnit derivedUnit = (DerivedUnit) specimen;
|
|
2409
|
if (!StringUtils.isBlank(derivedUnit.getBarcode())){
|
|
2410
|
csvLine[table.getIndex(WordClassificationExportTable.BARCODE)] = derivedUnit.getBarcode();
|
|
2411
|
}
|
|
2412
|
if (!StringUtils.isBlank(derivedUnit.getAccessionNumber())){
|
|
2413
|
csvLine[table.getIndex(WordClassificationExportTable.ACCESSION_NUMBER)] = derivedUnit.getAccessionNumber();
|
|
2414
|
}
|
|
2415
|
if (!StringUtils.isBlank(derivedUnit.getCatalogNumber())){
|
|
2416
|
csvLine[table.getIndex(WordClassificationExportTable.CATALOGUE_NUMBER)] = derivedUnit.getCatalogNumber();
|
|
2417
|
}
|
|
2418
|
}
|
|
2419
|
|
|
2420
|
csvLine[table.getIndex(WordClassificationExportTable.PREFERREDSTABLE_ID)] = specimen.getPreferredStableUri() != null? specimen.getPreferredStableUri().toString(): null;
|
|
2421
|
csvLine[table.getIndex(WordClassificationExportTable.SPECIMEN_IMAGE_URIS)] = extractMediaURIs(state,
|
|
2422
|
specimen.getDescriptions(), Feature.IMAGE());
|
|
2423
|
if (specimen instanceof DerivedUnit) {
|
|
2424
|
DerivedUnit derivedUnit = HibernateProxyHelper.deproxy(specimen, DerivedUnit.class);
|
|
2425
|
if (derivedUnit.getCollection() != null) {
|
|
2426
|
csvLine[table.getIndex(WordClassificationExportTable.HERBARIUM_ABBREV)] = derivedUnit.getCollection()
|
|
2427
|
.getCode();
|
|
2428
|
}
|
|
2429
|
|
|
2430
|
if (specimen instanceof MediaSpecimen) {
|
|
2431
|
MediaSpecimen mediaSpecimen = (MediaSpecimen) specimen;
|
|
2432
|
Iterator<MediaRepresentation> it = mediaSpecimen.getMediaSpecimen().getRepresentations().iterator();
|
|
2433
|
String mediaUris = extractMediaUris(it);
|
|
2434
|
csvLine[table.getIndex(WordClassificationExportTable.MEDIA_SPECIMEN_URL)] = mediaUris;
|
|
2435
|
|
|
2436
|
}
|
|
2437
|
|
|
2438
|
if (derivedUnit.getDerivedFrom() != null) {
|
|
2439
|
for (SpecimenOrObservationBase<?> original : derivedUnit.getDerivedFrom().getOriginals()) {
|
|
2440
|
// TODO: What to do if there are more then one
|
|
2441
|
// FieldUnit??
|
|
2442
|
if (original instanceof FieldUnit) {
|
|
2443
|
FieldUnit fieldUnit = (FieldUnit) original;
|
|
2444
|
csvLine[table.getIndex(WordClassificationExportTable.COLLECTOR_NUMBER)] = fieldUnit.getFieldNumber();
|
|
2445
|
|
|
2446
|
GatheringEvent gathering = fieldUnit.getGatheringEvent();
|
|
2447
|
if (gathering != null) {
|
|
2448
|
if (gathering.getLocality() != null) {
|
|
2449
|
csvLine[table.getIndex(WordClassificationExportTable.LOCALITY)] = gathering.getLocality()
|
|
2450
|
.getText();
|
|
2451
|
}
|
|
2452
|
if (gathering.getCountry() != null) {
|
|
2453
|
csvLine[table.getIndex(WordClassificationExportTable.COUNTRY)] = gathering.getCountry()
|
|
2454
|
.getLabel();
|
|
2455
|
}
|
|
2456
|
csvLine[table.getIndex(WordClassificationExportTable.COLLECTOR_STRING)] = createCollectorString(
|
|
2457
|
state, gathering, fieldUnit);
|
|
2458
|
|
|
2459
|
if (gathering.getGatheringDate() != null) {
|
|
2460
|
csvLine[table.getIndex(WordClassificationExportTable.COLLECTION_DATE)] = gathering
|
|
2461
|
.getGatheringDate().toString();
|
|
2462
|
}
|
|
2463
|
if (!gathering.getCollectingAreas().isEmpty()) {
|
|
2464
|
int index = 0;
|
|
2465
|
csvLine[table.getIndex(WordClassificationExportTable.FURTHER_AREAS)] = "0";
|
|
2466
|
for (NamedArea area : gathering.getCollectingAreas()) {
|
|
2467
|
if (index == 0) {
|
|
2468
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_CATEGORY1)] = area.getLevel() != null?area
|
|
2469
|
.getLevel().getLabel():"";
|
|
2470
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_NAME1)] = area.getLabel();
|
|
2471
|
}
|
|
2472
|
if (index == 1) {
|
|
2473
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_CATEGORY2)] = area.getLevel() != null?area
|
|
2474
|
.getLevel().getLabel():"";
|
|
2475
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_NAME2)] = area.getLabel();
|
|
2476
|
}
|
|
2477
|
if (index == 2) {
|
|
2478
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_CATEGORY3)] = area.getLevel() != null?area
|
|
2479
|
.getLevel().getLabel():"";
|
|
2480
|
csvLine[table.getIndex(WordClassificationExportTable.AREA_NAME3)] = area.getLabel();
|
|
2481
|
}
|
|
2482
|
if (index == 3) {
|
|
2483
|
csvLine[table.getIndex(WordClassificationExportTable.FURTHER_AREAS)] = "1";
|
|
2484
|
break;
|
|
2485
|
}
|
|
2486
|
index++;
|
|
2487
|
}
|
|
2488
|
}
|
|
2489
|
}
|
|
2490
|
}
|
|
2491
|
}
|
|
2492
|
} else {
|
|
2493
|
state.getResult().addWarning("The specimen with uuid " + specimen.getUuid()
|
|
2494
|
+ " is not an DerivedUnit.");
|
|
2495
|
}
|
|
2496
|
}
|
|
2497
|
|
|
2498
|
state.getProcessor().put(table, specimen, csvLine);
|
|
2499
|
} catch (Exception e) {
|
|
2500
|
state.getResult().addException(e, "An unexpected error occurred when handling specimen "
|
|
2501
|
+ cdmBaseStr(specimen) + ": " + e.getMessage());
|
|
2502
|
}
|
|
2503
|
}
|
|
2504
|
|
|
2505
|
private String extractMediaUris(Iterator<MediaRepresentation> it) {
|
|
2506
|
|
|
2507
|
String mediaUriString = "";
|
|
2508
|
boolean first = true;
|
|
2509
|
while (it.hasNext()) {
|
|
2510
|
MediaRepresentation rep = it.next();
|
|
2511
|
List<MediaRepresentationPart> parts = rep.getParts();
|
|
2512
|
for (MediaRepresentationPart part : parts) {
|
|
2513
|
if (first) {
|
|
2514
|
if (part.getUri() != null) {
|
|
2515
|
mediaUriString += part.getUri().toString();
|
|
2516
|
first = false;
|
|
2517
|
}
|
|
2518
|
} else {
|
|
2519
|
if (part.getUri() != null) {
|
|
2520
|
mediaUriString += ", " + part.getUri().toString();
|
|
2521
|
}
|
|
2522
|
}
|
|
2523
|
}
|
|
2524
|
}
|
|
2525
|
|
|
2526
|
return mediaUriString;
|
|
2527
|
}
|
|
2528
|
|
|
2529
|
private String extractLinkUris(Iterator<ExternalLink> it) {
|
|
2530
|
|
|
2531
|
String linkUriString = "";
|
|
2532
|
boolean first = true;
|
|
2533
|
while (it.hasNext()) {
|
|
2534
|
ExternalLink link = it.next();
|
|
2535
|
if (first) {
|
|
2536
|
if (link.getUri() != null) {
|
|
2537
|
linkUriString += link.getUri().toString();
|
|
2538
|
first = false;
|
|
2539
|
}
|
|
2540
|
} else {
|
|
2541
|
if (link.getUri() != null) {
|
|
2542
|
linkUriString += ", " + link.getUri().toString();
|
|
2543
|
}
|
|
2544
|
}
|
|
2545
|
}
|
|
2546
|
return linkUriString;
|
|
2547
|
}
|
|
2548
|
|
|
2549
|
private String createCollectorString(WordClassificationExportState state, GatheringEvent gathering, FieldUnit fieldUnit) {
|
|
2550
|
try {
|
|
2551
|
String collectorString = "";
|
|
2552
|
AgentBase<?> collectorA = CdmBase.deproxy(gathering.getCollector());
|
|
2553
|
if (gathering.getCollector() != null) {
|
|
2554
|
if (collectorA instanceof TeamOrPersonBase && state.getConfig().isHighLightPrimaryCollector()) {
|
|
2555
|
|
|
2556
|
Person primaryCollector = fieldUnit.getPrimaryCollector();
|
|
2557
|
if (collectorA instanceof Team) {
|
|
2558
|
Team collectorTeam = (Team) collectorA;
|
|
2559
|
boolean isFirst = true;
|
|
2560
|
for (Person member : collectorTeam.getTeamMembers()) {
|
|
2561
|
if (!isFirst) {
|
|
2562
|
collectorString += "; ";
|
|
2563
|
}
|
|
2564
|
if (member.equals(primaryCollector)) {
|
|
2565
|
// highlight
|
|
2566
|
collectorString += "<b>" + member.getTitleCache() + "</b>";
|
|
2567
|
} else {
|
|
2568
|
collectorString += member.getTitleCache();
|
|
2569
|
}
|
|
2570
|
}
|
|
2571
|
}
|
|
2572
|
} else {
|
|
2573
|
collectorString = collectorA.getTitleCache();
|
|
2574
|
}
|
|
2575
|
}
|
|
2576
|
return collectorString;
|
|
2577
|
} catch (Exception e) {
|
|
2578
|
state.getResult().addException(e, "An unexpected error occurred when creating collector string for "
|
|
2579
|
+ cdmBaseStr(fieldUnit) + ": " + e.getMessage());
|
|
2580
|
return "";
|
|
2581
|
}
|
|
2582
|
}
|
|
2583
|
|
|
2584
|
/**
|
|
2585
|
* Returns a string representation of the {@link CdmBase cdmBase} object for
|
|
2586
|
* result messages.
|
|
2587
|
*/
|
|
2588
|
private String cdmBaseStr(CdmBase cdmBase) {
|
|
2589
|
if (cdmBase == null) {
|
|
2590
|
return "-no object available-";
|
|
2591
|
} else {
|
|
2592
|
return cdmBase.getClass().getSimpleName() + ": " + cdmBase.getUuid();
|
|
2593
|
}
|
|
2594
|
}
|
|
2595
|
|
|
2596
|
@Override
|
|
2597
|
protected boolean doCheck(WordClassificationExportState state) {
|
|
2598
|
return false;
|
|
2599
|
}
|
|
2600
|
|
|
2601
|
@Override
|
|
2602
|
protected boolean isIgnore(WordClassificationExportState state) {
|
|
2603
|
return false;
|
|
2604
|
}
|
|
2605
|
|
|
2606
|
}
|