1
|
/**
|
2
|
* Copyright (C) 2009 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.dwca.in;
|
10
|
|
11
|
import java.net.URI;
|
12
|
import java.util.ArrayList;
|
13
|
import java.util.HashSet;
|
14
|
import java.util.List;
|
15
|
import java.util.Map;
|
16
|
import java.util.Set;
|
17
|
import java.util.UUID;
|
18
|
|
19
|
import org.apache.commons.lang.StringUtils;
|
20
|
import org.apache.log4j.Logger;
|
21
|
|
22
|
import com.ibm.lsid.MalformedLSIDException;
|
23
|
|
24
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
25
|
import eu.etaxonomy.cdm.io.common.mapping.UndefinedTransformerMethodException;
|
26
|
import eu.etaxonomy.cdm.io.stream.IPartitionableConverter;
|
27
|
import eu.etaxonomy.cdm.io.stream.IReader;
|
28
|
import eu.etaxonomy.cdm.io.stream.ItemFilter;
|
29
|
import eu.etaxonomy.cdm.io.stream.ListReader;
|
30
|
import eu.etaxonomy.cdm.io.stream.MappedCdmBase;
|
31
|
import eu.etaxonomy.cdm.io.stream.PartitionableConverterBase;
|
32
|
import eu.etaxonomy.cdm.io.stream.StreamImportBase;
|
33
|
import eu.etaxonomy.cdm.io.stream.StreamImportStateBase;
|
34
|
import eu.etaxonomy.cdm.io.stream.StreamItem;
|
35
|
import eu.etaxonomy.cdm.io.stream.terms.TermUri;
|
36
|
import eu.etaxonomy.cdm.model.common.Annotation;
|
37
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
38
|
import eu.etaxonomy.cdm.model.common.Extension;
|
39
|
import eu.etaxonomy.cdm.model.common.ExtensionType;
|
40
|
import eu.etaxonomy.cdm.model.common.IdentifiableSource;
|
41
|
import eu.etaxonomy.cdm.model.common.Identifier;
|
42
|
import eu.etaxonomy.cdm.model.common.LSID;
|
43
|
import eu.etaxonomy.cdm.model.common.Language;
|
44
|
import eu.etaxonomy.cdm.model.common.Marker;
|
45
|
import eu.etaxonomy.cdm.model.common.MarkerType;
|
46
|
import eu.etaxonomy.cdm.model.description.CommonTaxonName;
|
47
|
import eu.etaxonomy.cdm.model.description.Distribution;
|
48
|
import eu.etaxonomy.cdm.model.description.PresenceAbsenceTerm;
|
49
|
import eu.etaxonomy.cdm.model.description.TaxonDescription;
|
50
|
import eu.etaxonomy.cdm.model.location.NamedArea;
|
51
|
import eu.etaxonomy.cdm.model.name.NomenclaturalCode;
|
52
|
import eu.etaxonomy.cdm.model.name.Rank;
|
53
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
54
|
import eu.etaxonomy.cdm.model.reference.OriginalSourceType;
|
55
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
56
|
import eu.etaxonomy.cdm.model.reference.ReferenceFactory;
|
57
|
import eu.etaxonomy.cdm.model.taxon.Classification;
|
58
|
import eu.etaxonomy.cdm.model.taxon.Synonym;
|
59
|
import eu.etaxonomy.cdm.model.taxon.Taxon;
|
60
|
import eu.etaxonomy.cdm.model.taxon.TaxonBase;
|
61
|
import eu.etaxonomy.cdm.model.term.DefinedTerm;
|
62
|
import eu.etaxonomy.cdm.model.term.DefinedTermBase;
|
63
|
import eu.etaxonomy.cdm.strategy.exceptions.StringNotParsableException;
|
64
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
65
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
66
|
|
67
|
/**
|
68
|
* @author a.mueller
|
69
|
* @since 22.11.2011
|
70
|
*
|
71
|
*/
|
72
|
public class DwcTaxonStreamItem2CdmTaxonConverter<CONFIG extends DwcaDataImportConfiguratorBase, STATE extends StreamImportStateBase<CONFIG, StreamImportBase>>
|
73
|
extends PartitionableConverterBase<CONFIG, STATE>
|
74
|
implements IPartitionableConverter<StreamItem, IReader<CdmBase>, String>, ItemFilter<StreamItem> {
|
75
|
|
76
|
private static final Logger logger = Logger.getLogger(DwcTaxonStreamItem2CdmTaxonConverter.class);
|
77
|
|
78
|
//if this converter is used as filter we may not want to delete item parts during evaluation
|
79
|
boolean isFilterOnly = false;
|
80
|
|
81
|
private static final String ID = "id";
|
82
|
// temporary key for the case that no dataset information is supplied, TODO use something better
|
83
|
public static final String NO_DATASET = "no_dataset_jli773oebhjklw";
|
84
|
|
85
|
private final NonViralNameParserImpl parser = NonViralNameParserImpl.NewInstance();
|
86
|
|
87
|
/**
|
88
|
* @param state
|
89
|
*/
|
90
|
public DwcTaxonStreamItem2CdmTaxonConverter(STATE state) {
|
91
|
super(state);
|
92
|
}
|
93
|
|
94
|
public DwcTaxonStreamItem2CdmTaxonConverter(STATE state, boolean isFilter) {
|
95
|
super(state);
|
96
|
this.isFilterOnly = isFilter;
|
97
|
}
|
98
|
|
99
|
@Override
|
100
|
public boolean toBeRemovedFromStream(StreamItem item) {
|
101
|
if (!config.isDoSplitRelationshipImport()){
|
102
|
return false;
|
103
|
}else{
|
104
|
if (isSynonym(item)){
|
105
|
return ! this.config.isDoSynonymRelationships();
|
106
|
}else{
|
107
|
NomenclaturalCode nomCode = getNomCode(item);
|
108
|
Rank rank = getRank(item, nomCode);
|
109
|
boolean isHigherRank = rank == null || rank.isHigher(Rank.SPECIES());
|
110
|
if (isHigherRank){
|
111
|
return ! config.isDoHigherRankRelationships();
|
112
|
}else{
|
113
|
return ! config.isDoLowerRankRelationships();
|
114
|
}
|
115
|
}
|
116
|
}
|
117
|
}
|
118
|
|
119
|
private boolean isSynonym(StreamItem item) {
|
120
|
TaxonBase<?> taxonBase = getTaxonBase(item);
|
121
|
return taxonBase instanceof Synonym;
|
122
|
}
|
123
|
|
124
|
@Override
|
125
|
public IReader<MappedCdmBase<? extends CdmBase>> map(StreamItem csvTaxonRecord){
|
126
|
List<MappedCdmBase<? extends CdmBase>> resultList = new ArrayList<>();
|
127
|
|
128
|
//TODO what if not transactional?
|
129
|
Reference sourceReference = state.getTransactionalSourceReference();
|
130
|
String sourceReferenceDetail = null;
|
131
|
|
132
|
//taxon
|
133
|
TaxonBase<?> taxonBase = getTaxonBase(csvTaxonRecord);
|
134
|
MappedCdmBase<TaxonBase<?>> mcb = new MappedCdmBase<>(csvTaxonRecord.term, csvTaxonRecord.get(ID), taxonBase);
|
135
|
resultList.add(mcb);
|
136
|
|
137
|
//original source
|
138
|
String id = csvTaxonRecord.get(ID);
|
139
|
IdentifiableSource source = taxonBase.addSource(OriginalSourceType.Import, id, "Taxon", sourceReference, sourceReferenceDetail);
|
140
|
MappedCdmBase<IdentifiableSource> mappedSource = new MappedCdmBase<>(csvTaxonRecord.get(ID), source);
|
141
|
resultList.add(mappedSource);
|
142
|
csvTaxonRecord.remove(ID);
|
143
|
|
144
|
//rank
|
145
|
NomenclaturalCode nomCode = getNomCode(csvTaxonRecord);
|
146
|
Rank rank = getRank(csvTaxonRecord, nomCode);
|
147
|
|
148
|
//name && name published in
|
149
|
TaxonName name = getScientificName(csvTaxonRecord, nomCode, rank, resultList, sourceReference);
|
150
|
taxonBase.setName(name);
|
151
|
|
152
|
//nameAccordingTo
|
153
|
MappedCdmBase<Reference> sec = getNameAccordingTo(csvTaxonRecord, resultList);
|
154
|
|
155
|
if (sec == null && state.getConfig().isUseSourceReferenceAsSec()){
|
156
|
sec = new MappedCdmBase<>(state.getTransactionalSourceReference());
|
157
|
}
|
158
|
if (sec != null){
|
159
|
taxonBase.setSec(sec.getCdmBase());
|
160
|
}
|
161
|
|
162
|
//classification
|
163
|
handleDataset(csvTaxonRecord, taxonBase, resultList, sourceReference, sourceReferenceDetail);
|
164
|
|
165
|
//NON core
|
166
|
//term="http://purl.org/dc/terms/identifier"
|
167
|
//currently only LSIDs or generic
|
168
|
handleIdentifier(csvTaxonRecord, taxonBase);
|
169
|
|
170
|
//TaxonRemarks
|
171
|
handleTaxonRemarks(csvTaxonRecord, taxonBase);
|
172
|
|
173
|
//TDWG_1
|
174
|
handleTdwgArea(csvTaxonRecord, taxonBase);
|
175
|
|
176
|
//VernecularName
|
177
|
handleCommonNames(csvTaxonRecord, taxonBase);
|
178
|
|
179
|
//External Sources, ID's and References
|
180
|
handleIdentifiableObjects(csvTaxonRecord, taxonBase);
|
181
|
|
182
|
|
183
|
// <!-- Top level group; listed as kingdom but may be interpreted as domain or superkingdom
|
184
|
// The following eight groups are recognized: Animalia, Archaea, Bacteria, Chromista,
|
185
|
// Fungi, Plantae, Protozoa, Viruses -->
|
186
|
// <field index='10' term='http://rs.tdwg.org/dwc/terms/kingdom'/>
|
187
|
|
188
|
// <!-- Phylum in which the taxon has been classified -->
|
189
|
// <field index='11' term='http://rs.tdwg.org/dwc/terms/phylum'/>
|
190
|
|
191
|
// <!-- Class in which the taxon has been classified -->
|
192
|
// <field index='12' term='http://rs.tdwg.org/dwc/terms/class'/>
|
193
|
|
194
|
// <!-- Order in which the taxon has been classified -->
|
195
|
// <field index='13' term='http://rs.tdwg.org/dwc/terms/order'/>
|
196
|
|
197
|
// <!-- Family in which the taxon has been classified -->
|
198
|
// <field index='14' term='http://rs.tdwg.org/dwc/terms/family'/>
|
199
|
|
200
|
// <!-- Genus in which the taxon has been classified -->
|
201
|
// <field index='15' term='http://rs.tdwg.org/dwc/terms/genus'/>
|
202
|
|
203
|
// <!-- Subgenus in which the taxon has been classified -->
|
204
|
// <field index='16' term='http://rs.tdwg.org/dwc/terms/subgenus'/>
|
205
|
// <!-- Specific epithet; for hybrids, the multiplication symbol is included in the epithet -->
|
206
|
|
207
|
// <field index='17' term='http://rs.tdwg.org/dwc/terms/specificEpithet'/>
|
208
|
// <!-- Infraspecific epithet -->
|
209
|
|
210
|
// <field index='18' term='http://rs.tdwg.org/dwc/terms/infraspecificEpithet'/>
|
211
|
// <!-- Authorship -->
|
212
|
|
213
|
// <field index='19' term='http://rs.tdwg.org/dwc/terms/scientificNameAuthorship'/>
|
214
|
// ==> see scientific name
|
215
|
//
|
216
|
// <!-- Acceptance status published in -->
|
217
|
// <field index='20' term='http://purl.org/dc/terms/source'/>
|
218
|
// <!-- Reference in which the scientific name was first published -->
|
219
|
// <field index='21' term='http://rs.tdwg.org/dwc/terms/namePublishedIn'/>
|
220
|
// <!-- Taxon scrutinized by -->
|
221
|
// <field index='22' term='http://rs.tdwg.org/dwc/terms/nameAccordingTo'/>
|
222
|
// <!-- Scrutiny date -->
|
223
|
// <field index='23' term='http://purl.org/dc/terms/modified'/>
|
224
|
// <!-- Additional data for the taxon -->
|
225
|
// <field index='24' term='http://purl.org/dc/terms/description'/>
|
226
|
// </core>
|
227
|
|
228
|
handleModified(csvTaxonRecord, taxonBase);
|
229
|
|
230
|
handleIsExtinct(csvTaxonRecord, taxonBase);
|
231
|
|
232
|
|
233
|
|
234
|
return new ListReader<>(resultList);
|
235
|
}
|
236
|
|
237
|
|
238
|
|
239
|
/**
|
240
|
* @param csvTaxonRecord
|
241
|
* @param taxonBase
|
242
|
*/
|
243
|
private void handleIsExtinct(StreamItem item, TaxonBase<?> taxonBase) {
|
244
|
String isExtinctStr = item.get(TermUri.GBIF_IS_EXTINCT);
|
245
|
if (isBlank(isExtinctStr)){
|
246
|
return;
|
247
|
}
|
248
|
Boolean isExtinct = getBoolean(isExtinctStr, item);
|
249
|
if (isExtinct != null){
|
250
|
try {
|
251
|
UUID isExtinctUuid = state.getTransformer().getMarkerTypeUuid("isExtinct");
|
252
|
MarkerType markerType = state.getCurrentIO().getMarkerType(state, isExtinctUuid, "extinct", "extinct", "extinct");
|
253
|
Marker.NewInstance(taxonBase, isExtinct, markerType);
|
254
|
|
255
|
} catch (UndefinedTransformerMethodException e) {
|
256
|
String message = "GetMarkerType not available for import. This should not happen. Please conntact developer";
|
257
|
fireWarningEvent(message, item.getLocation(), 8);
|
258
|
}
|
259
|
}
|
260
|
|
261
|
}
|
262
|
|
263
|
/**
|
264
|
* @param item
|
265
|
* @param isExtinctStr
|
266
|
* @return
|
267
|
*/
|
268
|
private Boolean getBoolean(String booleanStr, StreamItem item) {
|
269
|
try {
|
270
|
return Boolean.valueOf(booleanStr);
|
271
|
} catch (Exception e) {
|
272
|
String message = "Boolean value could not be parsed";
|
273
|
fireWarningEvent(message, item, 4);
|
274
|
return null;
|
275
|
}
|
276
|
}
|
277
|
|
278
|
|
279
|
|
280
|
/**
|
281
|
* @param csvTaxonRecord
|
282
|
* @param taxonBase
|
283
|
*/
|
284
|
private void handleModified(StreamItem item, TaxonBase<?> taxonBase) {
|
285
|
String modifiedStr = item.get(TermUri.DC_MODIFIED);
|
286
|
if (isBlank(modifiedStr)){
|
287
|
return;
|
288
|
}
|
289
|
|
290
|
try {
|
291
|
UUID modifiedUuid = state.getTransformer().getExtensionTypeUuid("modified");
|
292
|
ExtensionType extensionType = state.getCurrentIO().getExtensionType(state, modifiedUuid, "modified", "modified", "modified");
|
293
|
Extension.NewInstance(taxonBase, modifiedStr, extensionType);
|
294
|
|
295
|
} catch (UndefinedTransformerMethodException e) {
|
296
|
String message = "GetMarkerType not available for import. This should not happen. Please conntact developer";
|
297
|
fireWarningEvent(message, item.getLocation(), 8);
|
298
|
}
|
299
|
|
300
|
|
301
|
}
|
302
|
|
303
|
/**
|
304
|
* @param item
|
305
|
* @param taxonBase
|
306
|
*/
|
307
|
private void handleIdentifiableObjects(StreamItem item,TaxonBase<?> taxonBase) {
|
308
|
|
309
|
String references = item.get(TermUri.DC_REFERENCES);
|
310
|
|
311
|
if (references == null || references == "") {
|
312
|
references = item.get(TermUri.DWC_NAME_PUBLISHED_IN_ID);//lorna temporary until Scratchpads move the reference to the correct place.
|
313
|
}
|
314
|
|
315
|
if (StringUtils.isNotBlank(references)){
|
316
|
URI uri = makeUriIfIs(references);
|
317
|
if (uri != null){
|
318
|
Extension.NewInstance(taxonBase, references, ExtensionType.URL());
|
319
|
}else{
|
320
|
String message = "Non-URI Dublin Core References not yet handled for taxa. References is: %s";
|
321
|
fireWarningEvent(String.format(message, references), item, 6);
|
322
|
}
|
323
|
}
|
324
|
|
325
|
|
326
|
//TODO: Finish properly
|
327
|
String id = item.get(TermUri.CDM_SOURCE_IDINSOURCE);
|
328
|
String idNamespace = item.get(TermUri.CDM_SOURCE_IDNAMESPACE);
|
329
|
String reference = item.get(TermUri.CDM_SOURCE_REFERENCE);
|
330
|
if(StringUtils.isNotBlank(id) && StringUtils.isNotBlank(idNamespace) && StringUtils.isNotBlank(reference)){
|
331
|
Reference ref = ReferenceFactory.newGeneric();
|
332
|
ref.setTitle(reference);
|
333
|
Taxon taxon = (Taxon) taxonBase;
|
334
|
taxon.addSource(OriginalSourceType.Import, id, idNamespace, ref, null);
|
335
|
}
|
336
|
|
337
|
}
|
338
|
|
339
|
|
340
|
/**
|
341
|
* If str is an uri it returns is as an {@link URI}. If not it returns <code>null</code>.
|
342
|
* @param str
|
343
|
* @return the URI.
|
344
|
*/
|
345
|
private URI makeUriIfIs(String str) {
|
346
|
if (! str.startsWith("http:")){
|
347
|
return null;
|
348
|
}else{
|
349
|
try {
|
350
|
URI uri = URI.create(str);
|
351
|
return uri;
|
352
|
} catch (Exception e) {
|
353
|
return null;
|
354
|
}
|
355
|
}
|
356
|
|
357
|
}
|
358
|
|
359
|
|
360
|
/**
|
361
|
* @param item
|
362
|
* @param taxonBase
|
363
|
*/
|
364
|
private void handleCommonNames(StreamItem item,TaxonBase<?> taxonBase) {
|
365
|
//TODO: handle comma separated values
|
366
|
String commonName = item.get(TermUri.DWC_VERNACULAR_NAME);
|
367
|
if (StringUtils.isNotBlank(commonName)){
|
368
|
|
369
|
Language language = getLanguage(item);
|
370
|
CommonTaxonName commonTaxonName = CommonTaxonName.NewInstance(commonName, language);
|
371
|
if(taxonBase instanceof Taxon){
|
372
|
Taxon taxon = (Taxon) taxonBase;
|
373
|
TaxonDescription taxonDescription = getTaxonDescription(taxon, false);
|
374
|
taxonDescription.addElement(commonTaxonName);
|
375
|
logger.info("Common name " + commonName + " added to " + taxon.getTitleCache());
|
376
|
}
|
377
|
}
|
378
|
}
|
379
|
|
380
|
|
381
|
|
382
|
/**
|
383
|
* @param csvTaxonRecord
|
384
|
* @param taxonBase
|
385
|
*/
|
386
|
private void handleTdwgArea(StreamItem item, TaxonBase<?> taxonBase) {
|
387
|
String tdwg_area = item.get(TermUri.DWC_COUNTRY_CODE);
|
388
|
if (tdwg_area != null){
|
389
|
if(taxonBase instanceof Synonym){
|
390
|
Synonym synonym = CdmBase.deproxy(taxonBase, Synonym.class);
|
391
|
Taxon acceptedTaxon = synonym.getAcceptedTaxon();
|
392
|
if (acceptedTaxon != null){
|
393
|
TaxonDescription td = getTaxonDescription(acceptedTaxon, false);
|
394
|
NamedArea area = NamedArea.getAreaByTdwgAbbreviation(tdwg_area);
|
395
|
|
396
|
if (area == null){
|
397
|
area = NamedArea.getAreaByTdwgLabel(tdwg_area);
|
398
|
}
|
399
|
if (area != null){
|
400
|
Distribution distribution = Distribution.NewInstance(area, PresenceAbsenceTerm.PRESENT());
|
401
|
td.addElement(distribution);
|
402
|
}
|
403
|
}
|
404
|
}
|
405
|
if(!(taxonBase instanceof Synonym)){
|
406
|
Taxon taxon = CdmBase.deproxy(taxonBase, Taxon.class);
|
407
|
TaxonDescription td = getTaxonDescription(taxon, false);
|
408
|
NamedArea area = NamedArea.getAreaByTdwgAbbreviation(tdwg_area);
|
409
|
|
410
|
if (area == null){
|
411
|
area = NamedArea.getAreaByTdwgLabel(tdwg_area);
|
412
|
}
|
413
|
if (area != null){
|
414
|
Distribution distribution = Distribution.NewInstance(area, PresenceAbsenceTerm.PRESENT());
|
415
|
td.addElement(distribution);
|
416
|
}
|
417
|
}
|
418
|
}
|
419
|
}
|
420
|
|
421
|
|
422
|
/**
|
423
|
* @param item
|
424
|
* @param taxonBase
|
425
|
*/
|
426
|
private void handleTaxonRemarks(StreamItem item,TaxonBase<?> taxonBase) {
|
427
|
String comment = item.get(TermUri.DWC_TAXON_REMARKS);
|
428
|
Language language = getLanguage(item);
|
429
|
if(StringUtils.isNotBlank(comment)){
|
430
|
Annotation annotation = Annotation.NewInstance(comment, language);
|
431
|
taxonBase.addAnnotation(annotation);
|
432
|
}else{
|
433
|
// String message = "Comment is empty or some error appeared while saving: %s";
|
434
|
//// message = String.format(message);
|
435
|
// fireWarningEvent(message, item, 1);
|
436
|
}
|
437
|
}
|
438
|
|
439
|
|
440
|
//TODO handle non LSIDs
|
441
|
//TODO handle LSIDs for names
|
442
|
private void handleIdentifier(StreamItem csvTaxonRecord, TaxonBase<?> taxonBase) {
|
443
|
String identifier = csvTaxonRecord.get(TermUri.DC_IDENTIFIER);
|
444
|
if (StringUtils.isNotBlank(identifier)){
|
445
|
if (identifier.trim().startsWith("urn:lsid")){
|
446
|
try {
|
447
|
LSID lsid = new LSID(identifier);
|
448
|
taxonBase.setLsid(lsid);
|
449
|
} catch (MalformedLSIDException e) {
|
450
|
String message = "LSID is malformed and can't be handled as LSID: %s";
|
451
|
message = String.format(message, identifier);
|
452
|
fireWarningEvent(message, csvTaxonRecord, 4);
|
453
|
Identifier.NewInstance(taxonBase, identifier, DefinedTermBase.getTermByClassAndUUID(DefinedTerm.class, DefinedTerm.uuidLsid));
|
454
|
}
|
455
|
}else{
|
456
|
Identifier.NewInstance(taxonBase, identifier, null);
|
457
|
String message = "Identifier type not recognized. Create generic identifier: %s";
|
458
|
message = String.format(message, identifier);
|
459
|
fireWarningEvent(message, csvTaxonRecord, 1);
|
460
|
}
|
461
|
}
|
462
|
|
463
|
}
|
464
|
|
465
|
|
466
|
private void handleDataset(StreamItem item, TaxonBase<?> taxonBase,
|
467
|
List<MappedCdmBase<? extends CdmBase>> resultList,
|
468
|
Reference sourceReference,
|
469
|
String sourceReferecenDetail) {
|
470
|
|
471
|
TermUri idTerm = TermUri.DWC_DATASET_ID;
|
472
|
TermUri strTerm = TermUri.DWC_DATASET_NAME;
|
473
|
|
474
|
if (config.isDatasetsAsClassifications()){
|
475
|
String datasetId = CdmUtils.Nz(item.get(idTerm)).trim();
|
476
|
String datasetName = CdmUtils.Nz(item.get(strTerm)).trim();
|
477
|
if (CdmUtils.areBlank(datasetId, datasetName) ){
|
478
|
datasetId = NO_DATASET;
|
479
|
}
|
480
|
|
481
|
//check id
|
482
|
boolean classificationExists = state.exists(idTerm.toString() , datasetId, Classification.class);
|
483
|
|
484
|
//check name
|
485
|
if (!classificationExists){
|
486
|
classificationExists = state.exists(strTerm.toString() , datasetName, Classification.class);
|
487
|
}
|
488
|
|
489
|
//if not exists, create new
|
490
|
if (! classificationExists){
|
491
|
String classificationName = StringUtils.isBlank(datasetName)? datasetId : datasetName;
|
492
|
if (classificationName.equals(NO_DATASET)){
|
493
|
classificationName = config.getClassificationName();
|
494
|
//classificationName = "Classification (no name)"; //TODO define by config or zipfile or metadata
|
495
|
}
|
496
|
|
497
|
String classificationId = StringUtils.isBlank(datasetId)? datasetName : datasetId;
|
498
|
Classification classification = Classification.NewInstance(classificationName);
|
499
|
//source
|
500
|
IdentifiableSource source = classification.addSource(OriginalSourceType.Import, classificationId, "Dataset", sourceReference, sourceReferecenDetail);
|
501
|
//add to result
|
502
|
resultList.add(new MappedCdmBase<>(idTerm, datasetId, classification));
|
503
|
resultList.add(new MappedCdmBase<>(strTerm, datasetName, classification));
|
504
|
resultList.add(new MappedCdmBase<>(source));
|
505
|
//TODO this is not so nice but currently necessary as classifications are requested in the same partition
|
506
|
state.putMapping(idTerm.toString(), classificationId, classification);
|
507
|
state.putMapping(strTerm.toString(), classificationName, classification);
|
508
|
}
|
509
|
}else if (config.isDatasetsAsSecundumReference() || config.isDatasetsAsOriginalSource()){
|
510
|
MappedCdmBase<Reference> mappedCitation = getReference(item, resultList, idTerm, strTerm, true);
|
511
|
if (mappedCitation != null){
|
512
|
Reference ref = mappedCitation.getCdmBase();
|
513
|
if (config.isDatasetsAsSecundumReference()){
|
514
|
//dataset as secundum reference
|
515
|
taxonBase.setSec(ref);
|
516
|
}else{
|
517
|
//dataset as original source
|
518
|
taxonBase.addSource(OriginalSourceType.Import, null, null, ref, null);
|
519
|
}
|
520
|
}
|
521
|
}else{
|
522
|
String message = "DatasetUse type not yet implemented. Can't import dataset information.";
|
523
|
fireWarningEvent(message, item, 4);
|
524
|
}
|
525
|
|
526
|
//remove to later check if all attributes were used
|
527
|
removeItemInfo(item, idTerm);
|
528
|
removeItemInfo(item, strTerm);
|
529
|
}
|
530
|
|
531
|
|
532
|
@Override
|
533
|
public String getSourceId(StreamItem item) {
|
534
|
String id = item.get(ID);
|
535
|
return id;
|
536
|
}
|
537
|
|
538
|
private MappedCdmBase<Reference> getNameAccordingTo(StreamItem item, List<MappedCdmBase<? extends CdmBase>> resultList) {
|
539
|
if (config.isDatasetsAsSecundumReference()){
|
540
|
//TODO store nameAccordingTo info some where else or let the user define where to store it.
|
541
|
return null;
|
542
|
}else{
|
543
|
TermUri idTerm = TermUri.DWC_NAME_ACCORDING_TO_ID;
|
544
|
TermUri strTerm = TermUri.DWC_NAME_ACCORDING_TO;
|
545
|
MappedCdmBase<Reference> secRef = getReference(item, resultList, idTerm, strTerm, false);
|
546
|
return secRef;
|
547
|
}
|
548
|
}
|
549
|
|
550
|
private NomenclaturalCode getNomCode(StreamItem item) {
|
551
|
String strNomCode = getValue(item, TermUri.DWC_NOMENCLATURAL_CODE);
|
552
|
NomenclaturalCode nomCode = null;
|
553
|
// by Nomcenclatural Code
|
554
|
if (strNomCode != null){
|
555
|
nomCode = NomenclaturalCode.fromString(strNomCode);
|
556
|
if (nomCode == null){
|
557
|
String message = "NomCode '%s' not recognized";
|
558
|
message = String.format(message, strNomCode);
|
559
|
fireWarningEvent(message, item, 4);
|
560
|
}else{
|
561
|
return nomCode;
|
562
|
}
|
563
|
}
|
564
|
// by Kingdom
|
565
|
String strKingdom = getValue(item, TermUri.DWC_KINGDOM);
|
566
|
if (strKingdom != null){
|
567
|
if (strKingdom.equalsIgnoreCase("Plantae")){
|
568
|
nomCode = NomenclaturalCode.ICNAFP;
|
569
|
}else if (strKingdom.equalsIgnoreCase("Fungi")){
|
570
|
nomCode = NomenclaturalCode.ICNAFP;
|
571
|
}else if (strKingdom.equalsIgnoreCase("Animalia")){
|
572
|
nomCode = NomenclaturalCode.ICZN;
|
573
|
}else if (strKingdom.equalsIgnoreCase("Protozoa")){
|
574
|
nomCode = NomenclaturalCode.ICZN;
|
575
|
}
|
576
|
}
|
577
|
|
578
|
//TODO further kingdoms
|
579
|
if (nomCode == null){
|
580
|
//TODO warning
|
581
|
if (config.getNomenclaturalCode() != null){
|
582
|
nomCode = config.getNomenclaturalCode();
|
583
|
}
|
584
|
}
|
585
|
return nomCode;
|
586
|
}
|
587
|
|
588
|
|
589
|
private TaxonName getScientificName(StreamItem item, NomenclaturalCode nomCode, Rank rank, List<MappedCdmBase<? extends CdmBase>> resultList, Reference sourceReference) {
|
590
|
TaxonName name = null;
|
591
|
String strScientificName = getValue(item, TermUri.DWC_SCIENTIFIC_NAME);
|
592
|
//Name
|
593
|
if (strScientificName != null){
|
594
|
name = (TaxonName)parser.parseFullName(strScientificName, nomCode, rank);
|
595
|
if ( rank != null && name != null && name.getRank() != null && ! rank.equals(name.getRank())){
|
596
|
if (config.isValidateRankConsistency()){
|
597
|
String message = "Parsed rank %s (%s) differs from rank %s given by fields 'taxonRank' or 'verbatimTaxonRank'";
|
598
|
message = String.format(message, name.getRank().getTitleCache(), strScientificName, rank.getTitleCache());
|
599
|
fireWarningEvent(message, item, 4);
|
600
|
}
|
601
|
}
|
602
|
checkAuthorship(name, item);
|
603
|
resultList.add(new MappedCdmBase(TermUri.DWC_SCIENTIFIC_NAME, strScientificName, name));
|
604
|
}
|
605
|
//By ID
|
606
|
String strScientificNameId = getValue(item, TermUri.DWC_SCIENTIFIC_NAME_ID);
|
607
|
if (strScientificNameId != null){
|
608
|
if (config.isScientificNameIdAsOriginalSourceId()){
|
609
|
if (name != null){
|
610
|
IdentifiableSource source = IdentifiableSource.NewInstance(OriginalSourceType.Import, strScientificNameId, TermUri.DWC_SCIENTIFIC_NAME_ID.toString(), sourceReference, null);
|
611
|
name.addSource(source);
|
612
|
}
|
613
|
}else{
|
614
|
String message = "ScientificNameId not yet implemented: '%s'";
|
615
|
message = String.format(message, strScientificNameId);
|
616
|
fireWarningEvent(message, item, 4);
|
617
|
}
|
618
|
}
|
619
|
|
620
|
//namePublishedIn
|
621
|
TermUri idTerm = TermUri.DWC_NAME_PUBLISHED_IN_ID;
|
622
|
TermUri strTerm = TermUri.DWC_NAME_PUBLISHED_IN;
|
623
|
MappedCdmBase<Reference> nomRef = getReference(item, resultList, idTerm, strTerm, false);
|
624
|
|
625
|
if (name != null){
|
626
|
if (nomRef != null){
|
627
|
name.setNomenclaturalReference(nomRef.getCdmBase()); //check if name already has a nomRef, shouldn't be the case usually
|
628
|
}
|
629
|
}else{
|
630
|
if (nomRef != null){
|
631
|
String message = "NamePublishedIn information available but no name exists";
|
632
|
fireWarningEvent(message, item, 4);
|
633
|
}
|
634
|
}
|
635
|
return name;
|
636
|
}
|
637
|
|
638
|
|
639
|
/**
|
640
|
* General method to handle references used for multiple attributes.
|
641
|
* @param item
|
642
|
* @param resultList
|
643
|
* @param idTerm
|
644
|
* @param strTerm
|
645
|
* @param idIsInternal
|
646
|
* @return
|
647
|
*/
|
648
|
private MappedCdmBase<Reference> getReference(StreamItem item,
|
649
|
List<MappedCdmBase<? extends CdmBase>> resultList, TermUri idTerm,
|
650
|
TermUri strTerm, boolean idIsInternal) {
|
651
|
Reference newRef = null;
|
652
|
Reference sourceCitation = null;
|
653
|
|
654
|
MappedCdmBase<Reference> result = null;
|
655
|
if (exists(idTerm, item) || exists(strTerm, item)){
|
656
|
String refId = CdmUtils.Nz(item.get(idTerm)).trim();
|
657
|
String refStr = CdmUtils.Nz(item.get(strTerm)).trim();
|
658
|
if (StringUtils.isNotBlank(refId)){
|
659
|
List<Reference> references = state.get(idTerm.toString(), refId, Reference.class);
|
660
|
if (references.size() == 0){
|
661
|
if (! idIsInternal){
|
662
|
//references should already exist in store if not linking to external links like URLs
|
663
|
String message = "External namePublishedInIDs are not yet supported";
|
664
|
fireWarningEvent(message, item, 4);//set to DEBUG
|
665
|
}else{
|
666
|
newRef = ReferenceFactory.newGeneric(); //TODO handle other types if possible
|
667
|
newRef.addSource(OriginalSourceType.Import, refId, idTerm.toString(), sourceCitation, null);
|
668
|
MappedCdmBase<Reference> idResult = new MappedCdmBase<>(idTerm, refId, newRef);
|
669
|
resultList.add(idResult);
|
670
|
}
|
671
|
}else{
|
672
|
//TODO handle list.size > 1 , do we need a list here ?
|
673
|
result = new MappedCdmBase<Reference>(idTerm, refId , references.get(0));
|
674
|
}
|
675
|
}
|
676
|
if (result == null){
|
677
|
List<Reference> nomRefs = state.get(strTerm.toString(), refStr, Reference.class);
|
678
|
if (nomRefs.size() > 0){
|
679
|
//TODO handle list.size > 1 , do we need a list here ?
|
680
|
result = new MappedCdmBase<>(strTerm, refStr , nomRefs.get(0));
|
681
|
}else{
|
682
|
// new Reference
|
683
|
if (newRef == null){
|
684
|
newRef = ReferenceFactory.newGeneric(); //TODO handle other types if possible
|
685
|
}
|
686
|
newRef.setTitleCache(refStr, true);
|
687
|
//TODO distinguish available year, authorship, etc. if
|
688
|
result = new MappedCdmBase<>(strTerm, refStr, newRef);
|
689
|
resultList.add(result);
|
690
|
}
|
691
|
}
|
692
|
}
|
693
|
return result;
|
694
|
}
|
695
|
|
696
|
|
697
|
//TODO we may configure in configuration that scientific name never includes Authorship
|
698
|
private void checkAuthorship(TaxonName nameBase, StreamItem item) {
|
699
|
if (nameBase.isViral()){
|
700
|
return;
|
701
|
}
|
702
|
String strAuthors = getValue(item, TermUri.DWC_SCIENTIFIC_NAME_AUTHORS);
|
703
|
|
704
|
if (! nameBase.isProtectedTitleCache()){
|
705
|
if (isBlank(nameBase.getAuthorshipCache())){
|
706
|
if (nameBase.isBotanical() || nameBase.isZoological()){
|
707
|
//TODO can't we also parse NonViralNames correctly ?
|
708
|
try {
|
709
|
parser.parseAuthors(nameBase, strAuthors);
|
710
|
} catch (StringNotParsableException e) {
|
711
|
nameBase.setAuthorshipCache(strAuthors);
|
712
|
}
|
713
|
}else{
|
714
|
nameBase.setAuthorshipCache(strAuthors);
|
715
|
}
|
716
|
//TODO throw warning (scientific name should always include authorship) by DwC definition
|
717
|
}
|
718
|
}
|
719
|
|
720
|
}
|
721
|
|
722
|
|
723
|
private Rank getRank(StreamItem csvTaxonRecord, NomenclaturalCode nomCode) {
|
724
|
boolean USE_UNKNOWN = true;
|
725
|
Rank rank = null;
|
726
|
String strRank = getValue(csvTaxonRecord,TermUri.DWC_TAXON_RANK);
|
727
|
String strVerbatimRank = getValue(csvTaxonRecord,TermUri.DWC_VERBATIM_TAXON_RANK);
|
728
|
if (strRank != null){
|
729
|
try {
|
730
|
rank = Rank.getRankByEnglishName(strRank, nomCode, USE_UNKNOWN);
|
731
|
if (rank.equals(Rank.UNKNOWN_RANK())){
|
732
|
rank = Rank.getRankByNameOrIdInVoc(strRank, USE_UNKNOWN);
|
733
|
if (rank.equals(Rank.UNKNOWN_RANK())){
|
734
|
String message = "Rank can not be defined for '%s'";
|
735
|
message = String.format(message, strRank);
|
736
|
fireWarningEvent(message, csvTaxonRecord, 4);
|
737
|
}
|
738
|
}
|
739
|
} catch (UnknownCdmTypeException e) {
|
740
|
//should not happen as USE_UNKNOWN is used
|
741
|
rank = Rank.UNKNOWN_RANK();
|
742
|
}
|
743
|
}
|
744
|
if ( (rank == null || rank.equals(Rank.UNKNOWN_RANK())) && strVerbatimRank != null){
|
745
|
try {
|
746
|
rank = Rank.getRankByNameOrIdInVoc(strVerbatimRank, USE_UNKNOWN);
|
747
|
if (rank.equals(Rank.UNKNOWN_RANK())){
|
748
|
String message = "Rank can not be defined for '%s'";
|
749
|
message = String.format(message, strVerbatimRank);
|
750
|
fireWarningEvent(message, csvTaxonRecord, 4);
|
751
|
}
|
752
|
} catch (UnknownCdmTypeException e) {
|
753
|
//should not happen as USE_UNKNOWN is used
|
754
|
rank = Rank.UNKNOWN_RANK();
|
755
|
}
|
756
|
}
|
757
|
return rank;
|
758
|
}
|
759
|
|
760
|
|
761
|
/**
|
762
|
* Creates an empty taxon object with a given status.
|
763
|
* <i>Empty</i> taxon means, without a defined name or sec.
|
764
|
* @param item
|
765
|
* @return
|
766
|
*/
|
767
|
private TaxonBase<?> getTaxonBase(StreamItem item) {
|
768
|
TaxonName name = null;
|
769
|
Reference sec = null;
|
770
|
TaxonBase<?> result;
|
771
|
String taxStatus = item.get(TermUri.DWC_TAXONOMIC_STATUS);
|
772
|
String status = "";
|
773
|
|
774
|
if (taxStatus != null){
|
775
|
if (taxStatus.matches("accepted.*|valid")){
|
776
|
status += "A";
|
777
|
} else if (taxStatus.matches(".*synonym|invalid|not accepted")){ //not accepted comes from scratchpads
|
778
|
status += "S";
|
779
|
} else if (taxStatus.matches("misapplied.*")){
|
780
|
status += "M";
|
781
|
} else{
|
782
|
status += "?";
|
783
|
}
|
784
|
removeItemInfo(item, TermUri.DWC_TAXONOMIC_STATUS);
|
785
|
}
|
786
|
if (! CdmUtils.isBlank(item.get(TermUri.DWC_ACCEPTED_NAME_USAGE_ID))){
|
787
|
// acceptedNameUsageId = id
|
788
|
if (getSourceId(item).equals(item.get(TermUri.DWC_ACCEPTED_NAME_USAGE_ID))){
|
789
|
status += "A";
|
790
|
}else{
|
791
|
status += "S";
|
792
|
}
|
793
|
}
|
794
|
if (status.contains("A") || status.contains("M")){
|
795
|
result = Taxon.NewInstance(name, sec);
|
796
|
if (status.contains("S") && ! status.contains("M") ){
|
797
|
String message = "Ambigous taxon status (%s)";
|
798
|
message = String.format(message, status);
|
799
|
fireWarningEvent(message, item, 6);
|
800
|
}
|
801
|
} else if (status.contains("S")){
|
802
|
result = Synonym.NewInstance(name, sec);
|
803
|
} else{
|
804
|
result = Taxon.NewUnknownStatusInstance(name, sec);
|
805
|
}
|
806
|
|
807
|
return result;
|
808
|
|
809
|
}
|
810
|
|
811
|
|
812
|
|
813
|
/**
|
814
|
* @param item
|
815
|
* @return
|
816
|
*/
|
817
|
private Language getLanguage(StreamItem item) {
|
818
|
String langItem = item.get(TermUri.DC_LANGUAGE);
|
819
|
Language language = null;
|
820
|
|
821
|
if(StringUtils.equalsIgnoreCase(langItem, "de")){
|
822
|
language = Language.GERMAN();
|
823
|
}else if(StringUtils.equalsIgnoreCase(langItem, "en")){
|
824
|
language = Language.ENGLISH();
|
825
|
}else{
|
826
|
language = Language.DEFAULT();
|
827
|
}
|
828
|
return language;
|
829
|
}
|
830
|
|
831
|
// ********************** PARTITIONABLE ****************************************/
|
832
|
|
833
|
|
834
|
@Override
|
835
|
protected void makeForeignKeysForItem(StreamItem item, Map<String, Set<String>> fkMap) {
|
836
|
String value;
|
837
|
String key;
|
838
|
|
839
|
//namePublishedIn
|
840
|
if ( hasValue(value = item.get(key = TermUri.DWC_NAME_PUBLISHED_IN_ID.toString()))){
|
841
|
Set<String> keySet = getKeySet(key, fkMap);
|
842
|
keySet.add(value);
|
843
|
}
|
844
|
if (config.isDeduplicateNamePublishedIn()){
|
845
|
if ( hasValue(value = item.get(key = TermUri.DWC_NAME_PUBLISHED_IN.toString()))){
|
846
|
Set<String> keySet = getKeySet(key, fkMap);
|
847
|
keySet.add(value);
|
848
|
}
|
849
|
}
|
850
|
|
851
|
//nameAccordingTo
|
852
|
if (! config.isDatasetsAsSecundumReference()){
|
853
|
if ( hasValue(value = item.get(key = TermUri.DWC_NAME_ACCORDING_TO_ID.toString()))){
|
854
|
Set<String> keySet = getKeySet(key, fkMap);
|
855
|
keySet.add(value);
|
856
|
}
|
857
|
if ( hasValue(value = item.get(key = TermUri.DWC_NAME_ACCORDING_TO.toString()))){
|
858
|
Set<String> keySet = getKeySet(key, fkMap);
|
859
|
keySet.add(value);
|
860
|
}
|
861
|
}
|
862
|
|
863
|
//dataset
|
864
|
if ( hasValue(value = item.get(key = TermUri.DWC_DATASET_ID.toString()))){
|
865
|
Set<String> keySet = getKeySet(key, fkMap);
|
866
|
keySet.add(value);
|
867
|
}
|
868
|
if ( hasValue(value = item.get(key = TermUri.DWC_DATASET_NAME.toString()))){
|
869
|
Set<String> keySet = getKeySet(key, fkMap);
|
870
|
keySet.add(value);
|
871
|
}
|
872
|
|
873
|
}
|
874
|
|
875
|
|
876
|
@Override
|
877
|
public Set<String> requiredSourceNamespaces() {
|
878
|
Set<String> result = new HashSet<>();
|
879
|
result.add(TermUri.DWC_NAME_PUBLISHED_IN_ID.toString());
|
880
|
result.add(TermUri.DWC_NAME_PUBLISHED_IN.toString());
|
881
|
if (!config.isDatasetsAsSecundumReference()){
|
882
|
result.add(TermUri.DWC_NAME_ACCORDING_TO_ID.toString());
|
883
|
result.add(TermUri.DWC_NAME_ACCORDING_TO.toString());
|
884
|
}
|
885
|
result.add(TermUri.DWC_DATASET_ID.toString());
|
886
|
result.add(TermUri.DWC_DATASET_NAME.toString());
|
887
|
return result;
|
888
|
}
|
889
|
|
890
|
|
891
|
/**
|
892
|
* @param item
|
893
|
* @param dwcTaxonomicStatus
|
894
|
*/
|
895
|
private void removeItemInfo(StreamItem item, TermUri dwcTaxonomicStatus) {
|
896
|
if (!isFilterOnly){
|
897
|
item.remove(dwcTaxonomicStatus);
|
898
|
}
|
899
|
}
|
900
|
|
901
|
|
902
|
//** ***************************** TO STRING *********************************************/
|
903
|
|
904
|
@Override
|
905
|
public String toString(){
|
906
|
return this.getClass().getName();
|
907
|
}
|
908
|
}
|