|
1
|
/**
|
|
2
|
* Copyright (C) 2007 EDIT
|
|
3
|
* European Distributed Institute of Taxonomy
|
|
4
|
* http://www.e-taxonomy.eu
|
|
5
|
*
|
|
6
|
* The contents of this file are subject to the Mozilla Public License Version 1.1
|
|
7
|
* See LICENSE.TXT at the top of this package for the full license terms.
|
|
8
|
*/
|
|
9
|
|
|
10
|
package eu.etaxonomy.cdm.io.redlist.bfnXml.in;
|
|
11
|
|
|
12
|
import java.util.ArrayList;
|
|
13
|
import java.util.Collection;
|
|
14
|
import java.util.LinkedHashMap;
|
|
15
|
import java.util.List;
|
|
16
|
import java.util.Map;
|
|
17
|
import java.util.UUID;
|
|
18
|
|
|
19
|
import org.apache.commons.lang.StringUtils;
|
|
20
|
import org.apache.log4j.Logger;
|
|
21
|
import org.jdom.Element;
|
|
22
|
import org.jdom.Namespace;
|
|
23
|
import org.springframework.stereotype.Component;
|
|
24
|
import org.springframework.transaction.TransactionStatus;
|
|
25
|
|
|
26
|
import eu.etaxonomy.cdm.api.service.IClassificationService;
|
|
27
|
import eu.etaxonomy.cdm.api.service.ITaxonService;
|
|
28
|
import eu.etaxonomy.cdm.common.ResultWrapper;
|
|
29
|
import eu.etaxonomy.cdm.common.XmlHelp;
|
|
30
|
import eu.etaxonomy.cdm.io.redlist.bfnXml.BfnXmlConstants;
|
|
31
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
|
32
|
import eu.etaxonomy.cdm.model.common.ExtensionType;
|
|
33
|
import eu.etaxonomy.cdm.model.common.Language;
|
|
34
|
import eu.etaxonomy.cdm.model.description.CategoricalData;
|
|
35
|
import eu.etaxonomy.cdm.model.description.CommonTaxonName;
|
|
36
|
import eu.etaxonomy.cdm.model.description.DescriptionElementBase;
|
|
37
|
import eu.etaxonomy.cdm.model.description.Distribution;
|
|
38
|
import eu.etaxonomy.cdm.model.description.Feature;
|
|
39
|
import eu.etaxonomy.cdm.model.description.PresenceAbsenceTerm;
|
|
40
|
import eu.etaxonomy.cdm.model.description.State;
|
|
41
|
import eu.etaxonomy.cdm.model.description.TaxonDescription;
|
|
42
|
import eu.etaxonomy.cdm.model.description.TextData;
|
|
43
|
import eu.etaxonomy.cdm.model.location.NamedArea;
|
|
44
|
import eu.etaxonomy.cdm.model.name.NomenclaturalCode;
|
|
45
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
|
|
46
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatusType;
|
|
47
|
import eu.etaxonomy.cdm.model.name.Rank;
|
|
48
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
|
49
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
|
50
|
import eu.etaxonomy.cdm.model.taxon.Classification;
|
|
51
|
import eu.etaxonomy.cdm.model.taxon.Synonym;
|
|
52
|
import eu.etaxonomy.cdm.model.taxon.SynonymType;
|
|
53
|
import eu.etaxonomy.cdm.model.taxon.Taxon;
|
|
54
|
import eu.etaxonomy.cdm.model.taxon.TaxonBase;
|
|
55
|
import eu.etaxonomy.cdm.model.taxon.TaxonRelationship;
|
|
56
|
import eu.etaxonomy.cdm.model.taxon.TaxonRelationshipType;
|
|
57
|
import eu.etaxonomy.cdm.model.term.DefinedTermBase;
|
|
58
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
|
59
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
|
60
|
import eu.etaxonomy.cdm.strategy.parser.ParserProblem;
|
|
61
|
/**
|
|
62
|
*
|
|
63
|
* @author a.oppermann
|
|
64
|
* @since 04.07.2013
|
|
65
|
*
|
|
66
|
*/
|
|
67
|
//@Component("bfnXmlTaxonNameIO")
|
|
68
|
@Component
|
|
69
|
public class BfnXmlImportTaxonName extends BfnXmlImportBase {
|
|
70
|
|
|
71
|
private static final long serialVersionUID = -6684136204048549833L;
|
|
72
|
|
|
73
|
private static final Logger logger = Logger.getLogger(BfnXmlImportTaxonName.class);
|
|
74
|
|
|
75
|
private static NomenclaturalCode nomenclaturalCode = null;
|
|
76
|
private static int parsingProblemCounter = 0;
|
|
77
|
private Map<Integer, Taxon> firstList;
|
|
78
|
private Map<Integer, Taxon> secondList;
|
|
79
|
|
|
80
|
// private ImportDeduplicationHelper<BfnXmlImportState> deduplicationHelper = (ImportDeduplicationHelper<BfnXmlImportState>)ImportDeduplicationHelper.NewInstance(this);
|
|
81
|
|
|
82
|
public BfnXmlImportTaxonName(){
|
|
83
|
super();
|
|
84
|
}
|
|
85
|
|
|
86
|
|
|
87
|
@Override
|
|
88
|
@SuppressWarnings({"rawtypes" })
|
|
89
|
public void doInvoke(BfnXmlImportState state){
|
|
90
|
|
|
91
|
TransactionStatus tx = startTransaction();
|
|
92
|
|
|
93
|
ITaxonService taxonService = getTaxonService();
|
|
94
|
BfnXmlImportConfigurator config = state.getConfig();
|
|
95
|
nomenclaturalCode = config.getNomenclaturalCode();
|
|
96
|
Element elDataSet = getDataSetElement(config);
|
|
97
|
//TODO set Namespace
|
|
98
|
Namespace bfnNamespace = config.getBfnXmlNamespace();
|
|
99
|
|
|
100
|
List<?> contentXML = elDataSet.getContent();
|
|
101
|
Element currentElement = null;
|
|
102
|
state.setFillSecondList(false);
|
|
103
|
for(Object object:contentXML){
|
|
104
|
|
|
105
|
if(object instanceof Element){
|
|
106
|
currentElement = (Element)object;
|
|
107
|
//import taxon lists
|
|
108
|
if(currentElement.getName().equalsIgnoreCase(BfnXmlConstants.EL_ROTELISTEDATEN)){
|
|
109
|
|
|
110
|
Map<UUID, TaxonBase> savedTaxonMap = extractTaxonNames(state, taxonService, config, currentElement, bfnNamespace);
|
|
111
|
createOrUpdateClassification(state, taxonService, savedTaxonMap, currentElement);
|
|
112
|
state.setFillSecondList(true);
|
|
113
|
|
|
114
|
}//import concept relations of taxon lists
|
|
115
|
if(config.isHasSecondList()){
|
|
116
|
if(currentElement.getName().equalsIgnoreCase(BfnXmlConstants.EL_KONZEPTBEZIEHUNGEN)){
|
|
117
|
extractTaxonConceptRelationShips(bfnNamespace,currentElement);
|
|
118
|
}
|
|
119
|
}
|
|
120
|
}
|
|
121
|
}
|
|
122
|
commitTransaction(tx);
|
|
123
|
return;
|
|
124
|
}
|
|
125
|
|
|
126
|
/**
|
|
127
|
* This method will parse the XML concept relationships and tries to map them into cdm relationship types.
|
|
128
|
*
|
|
129
|
* @param bfnNamespace
|
|
130
|
* @param currentElement
|
|
131
|
*/
|
|
132
|
private void extractTaxonConceptRelationShips(Namespace bfnNamespace, Element currentElement) {
|
|
133
|
String childName;
|
|
134
|
String bfnElementName = BfnXmlConstants.EL_KONZEPTBEZIEHUNG;
|
|
135
|
ResultWrapper<Boolean> success = ResultWrapper.NewInstance(true);
|
|
136
|
@SuppressWarnings("unchecked")
|
|
137
|
List<Element> elConceptList = currentElement.getChildren(bfnElementName, bfnNamespace);
|
|
138
|
List<TaxonBase> updatedTaxonList = new ArrayList<>();
|
|
139
|
for(Element element:elConceptList){
|
|
140
|
|
|
141
|
childName = "TAXONYM1";
|
|
142
|
Element elTaxon1 = XmlHelp.getSingleChildElement(success, element, childName, bfnNamespace, false);
|
|
143
|
String taxNr1 = elTaxon1.getAttributeValue(BfnXmlConstants.ATT_TAXNR);
|
|
144
|
int int1 = Integer.parseInt(taxNr1);
|
|
145
|
Taxon taxon1 = firstList.get(int1);
|
|
146
|
TaxonBase<?> taxonBase1 = getTaxonService().load(taxon1.getUuid());
|
|
147
|
taxon1 = (Taxon)taxonBase1;
|
|
148
|
|
|
149
|
childName = "TAXONYM2";
|
|
150
|
Element elTaxon2 = XmlHelp.getSingleChildElement(success, element, childName, bfnNamespace, false);
|
|
151
|
String taxNr2 = elTaxon2.getAttributeValue(BfnXmlConstants.ATT_TAXNR);
|
|
152
|
int int2 = Integer.parseInt(taxNr2);
|
|
153
|
Taxon taxon2 = secondList.get(int2);
|
|
154
|
TaxonBase<?> taxonBase2 = getTaxonService().load(taxon2.getUuid());
|
|
155
|
taxon2 = (Taxon) taxonBase2;
|
|
156
|
|
|
157
|
childName = "STATUS";
|
|
158
|
Element elConceptStatus = XmlHelp.getSingleChildElement(success, element, childName, bfnNamespace, false);
|
|
159
|
String conceptStatusValue = elConceptStatus.getValue();
|
|
160
|
conceptStatusValue = conceptStatusValue.replaceAll("\u00A0", "").trim();
|
|
161
|
TaxonRelationshipType taxonRelationType = null;
|
|
162
|
/**
|
|
163
|
* This if case only exists because it was decided not to have a included_in relationship type.
|
|
164
|
*/
|
|
165
|
if(conceptStatusValue.equalsIgnoreCase("<")){
|
|
166
|
taxon2.addTaxonRelation(taxon1, TaxonRelationshipType.INCLUDES(), null, null);
|
|
167
|
}else{
|
|
168
|
taxonRelationType = BfnXmlTransformer.getTaxonRelationForConceptCode(conceptStatusValue);
|
|
169
|
taxon1.addTaxonRelation(taxon2, taxonRelationType , null, null);
|
|
170
|
}
|
|
171
|
if(taxonRelationType != null && taxonRelationType.equals(TaxonRelationshipType.ALL_RELATIONSHIPS())){
|
|
172
|
List<TaxonRelationship> relationsFromThisTaxon = (List<TaxonRelationship>) taxon1.getRelationsFromThisTaxon();
|
|
173
|
TaxonRelationship taxonRelationship = relationsFromThisTaxon.get(0);
|
|
174
|
taxonRelationship.setDoubtful(true);
|
|
175
|
}
|
|
176
|
updatedTaxonList.add(taxon2);
|
|
177
|
updatedTaxonList.add(taxon1);
|
|
178
|
}
|
|
179
|
getTaxonService().saveOrUpdate(updatedTaxonList);
|
|
180
|
logger.info("taxon relationships imported...");
|
|
181
|
}
|
|
182
|
|
|
183
|
/**
|
|
184
|
* This method stores the current imported maps in global variables to make
|
|
185
|
* them later available for matching the taxon relationships between these
|
|
186
|
* imported lists.
|
|
187
|
*
|
|
188
|
* @param state
|
|
189
|
* @param taxonMap
|
|
190
|
*/
|
|
191
|
private void prepareListforConceptImport(BfnXmlImportState state,Map<Integer, Taxon> taxonMap) {
|
|
192
|
if(state.isFillSecondList()){
|
|
193
|
secondList = taxonMap;
|
|
194
|
}else{
|
|
195
|
firstList = taxonMap;
|
|
196
|
}
|
|
197
|
}
|
|
198
|
|
|
199
|
/**
|
|
200
|
*
|
|
201
|
* @param state
|
|
202
|
* @param taxonService
|
|
203
|
* @param config
|
|
204
|
* @param elDataSet
|
|
205
|
* @param bfnNamespace
|
|
206
|
* @return
|
|
207
|
*/
|
|
208
|
private Map<UUID, TaxonBase> extractTaxonNames(BfnXmlImportState state,
|
|
209
|
ITaxonService taxonService, BfnXmlImportConfigurator config,
|
|
210
|
Element elDataSet, Namespace bfnNamespace) {
|
|
211
|
|
|
212
|
logger.info("start make TaxonNames...");
|
|
213
|
Map<Integer, Taxon> taxonMap = new LinkedHashMap<>();
|
|
214
|
ResultWrapper<Boolean> success = ResultWrapper.NewInstance(true);
|
|
215
|
String childName;
|
|
216
|
boolean obligatory;
|
|
217
|
|
|
218
|
childName = BfnXmlConstants.EL_TAXONYME;
|
|
219
|
obligatory = false;
|
|
220
|
Element elTaxonNames = XmlHelp.getSingleChildElement(success, elDataSet, childName, bfnNamespace, obligatory);
|
|
221
|
|
|
222
|
String bfnElementName = BfnXmlConstants.EL_TAXONYM;
|
|
223
|
@SuppressWarnings("unchecked")
|
|
224
|
List<Element> elTaxonList = elTaxonNames.getChildren(bfnElementName, bfnNamespace);
|
|
225
|
|
|
226
|
//for each taxonName
|
|
227
|
for (Element elTaxon : elTaxonList){
|
|
228
|
//create Taxon
|
|
229
|
String taxonId = elTaxon.getAttributeValue(BfnXmlConstants.ATT_TAXNR);
|
|
230
|
String reihenfolge = elTaxon.getAttributeValue(BfnXmlConstants.ATT_REIHENFOLGE);
|
|
231
|
childName = BfnXmlConstants.EL_WISSNAME;
|
|
232
|
Element elWissName = XmlHelp.getSingleChildElement(success, elTaxon, childName, bfnNamespace, obligatory);
|
|
233
|
String childElementName = BfnXmlConstants.EL_NANTEIL;
|
|
234
|
Taxon taxon = createOrUpdateTaxon(success, taxonId, reihenfolge, config, bfnNamespace, elWissName, childElementName, state);
|
|
235
|
|
|
236
|
//for each synonym
|
|
237
|
childName = "SYNONYME";
|
|
238
|
Element elSynonyms = XmlHelp.getSingleChildElement(success, elTaxon, childName, bfnNamespace, obligatory);
|
|
239
|
if(elSynonyms != null){
|
|
240
|
childElementName = "SYNONYM";
|
|
241
|
createOrUpdateSynonym(taxon, success, obligatory, bfnNamespace, childElementName,elSynonyms, taxonId, state);
|
|
242
|
}
|
|
243
|
|
|
244
|
//for vernacular name
|
|
245
|
childName = BfnXmlConstants.EL_DEUTSCHENAMEN;
|
|
246
|
Element elVernacularName = XmlHelp.getSingleChildElement(success, elTaxon, childName, bfnNamespace, obligatory);
|
|
247
|
if(elVernacularName != null){
|
|
248
|
childElementName = BfnXmlConstants.EL_DNAME;
|
|
249
|
createOrUpdateVernacularName(taxon, bfnNamespace, childElementName, elVernacularName, state);
|
|
250
|
}
|
|
251
|
|
|
252
|
//for each information concerning the taxon element
|
|
253
|
//TODO Information block
|
|
254
|
if(config.isDoInformationImport()){
|
|
255
|
childName = BfnXmlConstants.EL_INFORMATIONEN;
|
|
256
|
Element elInformations = XmlHelp.getSingleChildElement(success, elTaxon, childName, bfnNamespace, obligatory);
|
|
257
|
if(elInformations != null){
|
|
258
|
createOrUpdateInformation(taxon, bfnNamespace, elInformations, state);
|
|
259
|
}
|
|
260
|
}
|
|
261
|
taxonMap.put(Integer.parseInt(taxonId), taxon);
|
|
262
|
}
|
|
263
|
|
|
264
|
//Quick'n'dirty to set concept relationships between two imported list
|
|
265
|
prepareListforConceptImport(state, taxonMap);
|
|
266
|
|
|
267
|
Map<UUID, TaxonBase> savedTaxonMap = taxonService.saveOrUpdate((Collection)taxonMap.values());
|
|
268
|
|
|
269
|
logger.info("end makeTaxonNames ...");
|
|
270
|
if (!success.getValue()){
|
|
271
|
state.setUnsuccessfull();
|
|
272
|
}
|
|
273
|
return savedTaxonMap;
|
|
274
|
}
|
|
275
|
|
|
276
|
|
|
277
|
|
|
278
|
|
|
279
|
/**
|
|
280
|
* This will put the prior imported list into a classification
|
|
281
|
*
|
|
282
|
* @param state
|
|
283
|
* @param taxonService
|
|
284
|
* @param state
|
|
285
|
* @param savedTaxonMap
|
|
286
|
* @param currentElement
|
|
287
|
* @param state
|
|
288
|
* @return
|
|
289
|
*/
|
|
290
|
@SuppressWarnings("rawtypes")
|
|
291
|
private boolean createOrUpdateClassification(BfnXmlImportState state, ITaxonService taxonService, Map<UUID, TaxonBase> savedTaxonMap, Element currentElement) {
|
|
292
|
boolean isNewClassification = true;
|
|
293
|
String name = state.getFirstClassificationName() + " " + currentElement.getAttributeValue("inhalt");
|
|
294
|
Classification classification = Classification.NewInstance(name, state.getCurrentSecRef());
|
|
295
|
String microRef = null; //state.getCurrentSecRef() == null ? null : state.getCurrentSecRef().getTitleCache();
|
|
296
|
classification.addImportSource(null, null, state.getCompleteSourceRef(), microRef);
|
|
297
|
|
|
298
|
for(TaxonBase tb:savedTaxonMap.values()){
|
|
299
|
if(tb instanceof Taxon){
|
|
300
|
TaxonBase tbase = CdmBase.deproxy(tb, TaxonBase.class);
|
|
301
|
Taxon taxon = (Taxon)tbase;
|
|
302
|
taxon = CdmBase.deproxy(taxon, Taxon.class);
|
|
303
|
classification.addChildTaxon(taxon, null, null);
|
|
304
|
}
|
|
305
|
}
|
|
306
|
IClassificationService classificationService = getClassificationService();
|
|
307
|
classificationService.saveOrUpdate(classification);
|
|
308
|
return isNewClassification;
|
|
309
|
}
|
|
310
|
|
|
311
|
|
|
312
|
/**
|
|
313
|
* Matches the XML attributes against CDM entities.<BR>
|
|
314
|
* Imports Scientific Name, Rank, etc. and creates a taxon.<br>
|
|
315
|
* <b>Existing taxon names won't be matched yet</b>
|
|
316
|
*
|
|
317
|
* @param success
|
|
318
|
* @param taxonId
|
|
319
|
* @param reihenfolge
|
|
320
|
* @param config
|
|
321
|
* @param bfnNamespace
|
|
322
|
* @param elTaxonName
|
|
323
|
* @param childElementName
|
|
324
|
* @param state
|
|
325
|
* @return
|
|
326
|
*/
|
|
327
|
|
|
328
|
@SuppressWarnings({ "unchecked" })
|
|
329
|
private Taxon createOrUpdateTaxon(
|
|
330
|
ResultWrapper<Boolean> success, String taxonId,
|
|
331
|
String reihenfolge, BfnXmlImportConfigurator config, Namespace bfnNamespace,
|
|
332
|
Element elTaxonName, String childElementName, BfnXmlImportState state) {
|
|
333
|
|
|
334
|
List<Element> elWissNameList = elTaxonName.getChildren(childElementName, bfnNamespace);
|
|
335
|
Rank rank = null;
|
|
336
|
String strAuthor = null;
|
|
337
|
String strSupplement = null;
|
|
338
|
Taxon taxon = null;
|
|
339
|
String uniqueID = null;
|
|
340
|
String uriNameSpace = null;
|
|
341
|
// Long uniqueID = null;
|
|
342
|
for(Element elWissName:elWissNameList){
|
|
343
|
|
|
344
|
if(elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("Eindeutiger Code")){
|
|
345
|
uriNameSpace = elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH);
|
|
346
|
String textNormalize = elWissName.getTextNormalize();
|
|
347
|
if(StringUtils.isBlank(textNormalize)){
|
|
348
|
uniqueID = "";
|
|
349
|
}else{
|
|
350
|
uniqueID = textNormalize;
|
|
351
|
}
|
|
352
|
}
|
|
353
|
if(elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("Autoren")){
|
|
354
|
strAuthor = elWissName.getTextNormalize();
|
|
355
|
}
|
|
356
|
if(elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("Rang")){
|
|
357
|
String strRank = elWissName.getTextNormalize();
|
|
358
|
rank = makeRank(strRank);
|
|
359
|
}
|
|
360
|
if(elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("Zusätze")){
|
|
361
|
strSupplement = elWissName.getTextNormalize();
|
|
362
|
}
|
|
363
|
if(elWissName.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("wissName")){
|
|
364
|
try{
|
|
365
|
TaxonName name = parseNonviralNames(rank,strAuthor,strSupplement,elWissName);
|
|
366
|
if(name.isProtectedTitleCache() == true){
|
|
367
|
logger.warn("Taxon " + name.getTitleCache());
|
|
368
|
}
|
|
369
|
|
|
370
|
//TODO extract to method?
|
|
371
|
if(strSupplement != null){
|
|
372
|
name.setAppendedPhrase(strSupplement);
|
|
373
|
}
|
|
374
|
if(strSupplement != null && strSupplement.equalsIgnoreCase("nom. illeg.")){
|
|
375
|
name.addStatus(NomenclaturalStatus.NewInstance(NomenclaturalStatusType.ILLEGITIMATE()));
|
|
376
|
}
|
|
377
|
|
|
378
|
//no deduplication wanted by BfN
|
|
379
|
// deduplicationHelper.replaceAuthorNamesAndNomRef(state, name);
|
|
380
|
|
|
381
|
Reference secRef = state.isFillSecondList() ?
|
|
382
|
state.getSecondListSecRef():
|
|
383
|
state.getFirstListSecRef();
|
|
384
|
state.setCurrentSecundumRef(secRef);
|
|
385
|
taxon = Taxon.NewInstance(name, state.getCurrentSecRef());
|
|
386
|
//set create and set path of nameSpace
|
|
387
|
|
|
388
|
String namespace = getNamespace(uriNameSpace, elWissName);
|
|
389
|
taxon.addImportSource(uniqueID, namespace, state.getCompleteSourceRef(), null);
|
|
390
|
name.addImportSource(uniqueID, namespace, state.getCompleteSourceRef(), null);
|
|
391
|
|
|
392
|
taxon.addIdentifier(taxonId, getIdentiferType(state, BfnXmlTransformer.UUID_TAX_NR_IDENTIFIER_TYPE, "taxNr", "TaxNr attribute of Bfn Xml file", "taxNr", null));
|
|
393
|
taxon.addExtension(reihenfolge, ExtensionType.ORDER());
|
|
394
|
taxon.addIdentifier(reihenfolge, getIdentiferType(state, BfnXmlTransformer.UUID_REIHENFOLGE_IDENTIFIER_TYPE, "reihenfolge", "reihenfolge attribute of Bfn Xml file", "reihenfolge", null));
|
|
395
|
} catch (UnknownCdmTypeException e) {
|
|
396
|
success.setValue(false);
|
|
397
|
}
|
|
398
|
}
|
|
399
|
}
|
|
400
|
return taxon;
|
|
401
|
}
|
|
402
|
|
|
403
|
|
|
404
|
/**
|
|
405
|
* @param uriNameSpace
|
|
406
|
* @param elWissName
|
|
407
|
* @return
|
|
408
|
*/
|
|
409
|
protected String getNamespace(String uriNameSpace, Element elWissName) {
|
|
410
|
Element parentElement = elWissName.getParentElement();
|
|
411
|
Element grandParentElement = parentElement.getParentElement();
|
|
412
|
String namespace = grandParentElement.getName() + ":" + parentElement.getName() + ":"+elWissName.getName() + ":" + uriNameSpace;
|
|
413
|
return namespace;
|
|
414
|
}
|
|
415
|
|
|
416
|
/**
|
|
417
|
* Matches the XML attributes against CDM entities.<BR>
|
|
418
|
* Imports Scientific Name, Rank etc. and create a synonym.<br>
|
|
419
|
* <b>Existing synonym names won't be matched yet</b>
|
|
420
|
*
|
|
421
|
* @param taxon
|
|
422
|
* @param success
|
|
423
|
* @param obligatory
|
|
424
|
* @param bfnNamespace
|
|
425
|
* @param childElementName
|
|
426
|
* @param elSynonyms
|
|
427
|
* @param taxonId
|
|
428
|
* @param config
|
|
429
|
* @param state
|
|
430
|
*/
|
|
431
|
@SuppressWarnings({ "unchecked" })
|
|
432
|
private void createOrUpdateSynonym(Taxon taxon, ResultWrapper<Boolean> success, boolean obligatory, Namespace bfnNamespace,
|
|
433
|
String childElementName, Element elSynonyms, String taxonId, BfnXmlImportState state) {
|
|
434
|
|
|
435
|
String childName;
|
|
436
|
List<Element> elSynonymList = elSynonyms.getChildren(childElementName, bfnNamespace);
|
|
437
|
|
|
438
|
for(Element elSyn:elSynonymList){
|
|
439
|
Rank rank = null;
|
|
440
|
String strAuthor = null;
|
|
441
|
String strSupplement = null;
|
|
442
|
childName = BfnXmlConstants.EL_WISSNAME;
|
|
443
|
Element elSynScientificName = XmlHelp.getSingleChildElement(success, elSyn, childName, bfnNamespace, obligatory);
|
|
444
|
|
|
445
|
childElementName = BfnXmlConstants.EL_NANTEIL;
|
|
446
|
List<Element> elSynDetails = elSynScientificName.getChildren(childElementName, bfnNamespace);
|
|
447
|
|
|
448
|
for(Element elSynDetail:elSynDetails){
|
|
449
|
if(elSynDetail.getAttributeValue(BfnXmlConstants.ATT_BEREICH).equalsIgnoreCase("Rang")){
|
|
450
|
String strRank = elSynDetail.getTextNormalize();
|
|
451
|
rank = makeRank(strRank);
|
|
452
|
}
|
|
453
|
if(elSynDetail.getAttributeValue(BfnXmlConstants.ATT_BEREICH).equalsIgnoreCase("Autoren")){
|
|
454
|
strAuthor = elSynDetail.getTextNormalize();
|
|
455
|
}
|
|
456
|
if(elSynDetail.getAttributeValue(BfnXmlConstants.ATT_BEREICH, bfnNamespace).equalsIgnoreCase("Zusätze")){
|
|
457
|
strSupplement = elSynDetail.getTextNormalize();
|
|
458
|
}
|
|
459
|
if(elSynDetail.getAttributeValue(BfnXmlConstants.ATT_BEREICH).equalsIgnoreCase("wissName")){
|
|
460
|
try{
|
|
461
|
TaxonName name = parseNonviralNames(rank,strAuthor,strSupplement,elSynDetail);
|
|
462
|
//BfN does not want any deduplication, to be on the save side that no
|
|
463
|
// deduplicationHelper.replaceAuthorNamesAndNomRef(state, name);
|
|
464
|
|
|
465
|
//TODO find best matching Taxa
|
|
466
|
Synonym synonym = Synonym.NewInstance(name, state.getCurrentSecRef());
|
|
467
|
taxon.addSynonym(synonym, SynonymType.SYNONYM_OF());
|
|
468
|
|
|
469
|
} catch (UnknownCdmTypeException e) {
|
|
470
|
logger.warn("Name with id " + taxonId + " has unknown nomenclatural code.");
|
|
471
|
success.setValue(false);
|
|
472
|
}
|
|
473
|
|
|
474
|
}
|
|
475
|
|
|
476
|
}
|
|
477
|
}
|
|
478
|
}
|
|
479
|
|
|
480
|
|
|
481
|
/**
|
|
482
|
*
|
|
483
|
* @param taxon
|
|
484
|
* @param bfnNamespace
|
|
485
|
* @param childElementName
|
|
486
|
* @param elVernacularName
|
|
487
|
* @param state
|
|
488
|
*/
|
|
489
|
private void createOrUpdateVernacularName(Taxon taxon,
|
|
490
|
Namespace bfnNamespace, String childElementName,
|
|
491
|
Element elVernacularName, BfnXmlImportState state) {
|
|
492
|
|
|
493
|
@SuppressWarnings("unchecked")
|
|
494
|
List<Element> elVernacularNameList = elVernacularName.getChildren(childElementName, bfnNamespace);
|
|
495
|
|
|
496
|
TaxonDescription taxonDescription = getTaxonDescription(taxon, false, true);
|
|
497
|
|
|
498
|
for(Element elVernacular : elVernacularNameList){
|
|
499
|
Element child = elVernacular.getChild("TRIVIALNAME");
|
|
500
|
if(child != null){
|
|
501
|
makeCommonName(taxonDescription, child, state);
|
|
502
|
}
|
|
503
|
}
|
|
504
|
|
|
505
|
}
|
|
506
|
|
|
507
|
/**
|
|
508
|
*
|
|
509
|
* @param taxon
|
|
510
|
* @param bfnNamespace
|
|
511
|
* @param childElementName
|
|
512
|
* @param elInformations
|
|
513
|
* @param state
|
|
514
|
* @throws UnknownCdmTypeException
|
|
515
|
*/
|
|
516
|
|
|
517
|
@SuppressWarnings("unchecked")
|
|
518
|
private void createOrUpdateInformation(Taxon taxon,
|
|
519
|
Namespace bfnNamespace,
|
|
520
|
Element elInformations,
|
|
521
|
BfnXmlImportState state){
|
|
522
|
|
|
523
|
String childElementName = BfnXmlConstants.EL_BEZUGSRAUM;
|
|
524
|
|
|
525
|
List<Element> elInformationList = elInformations.getChildren(childElementName, bfnNamespace);
|
|
526
|
|
|
527
|
for(Element elInfo:elInformationList){
|
|
528
|
//check if geographical scope is Bund and import only these information for now
|
|
529
|
//TODO create several taxon descriptions for different geographical scope
|
|
530
|
if(elInfo.getName().equalsIgnoreCase(BfnXmlConstants.EL_BEZUGSRAUM) && elInfo.getAttributeValue("name").equalsIgnoreCase("Bund")){
|
|
531
|
childElementName = BfnXmlConstants.EL_IWERT;
|
|
532
|
TaxonDescription taxonDescription = getTaxonDescription(taxon, false, true);
|
|
533
|
try {
|
|
534
|
UUID germanStateUUID = BfnXmlTransformer.getAreaUUID("Deutschland");
|
|
535
|
NamedArea area = (NamedArea)getTermService().load(germanStateUUID);
|
|
536
|
//FIXME GEOSCOPE_ID CANNOT BE NULL Exception
|
|
537
|
if (area != null){
|
|
538
|
taxonDescription.addGeoScope(area);
|
|
539
|
}else{
|
|
540
|
logger.warn("Did not find area 'Deutschland'");
|
|
541
|
}
|
|
542
|
} catch (UnknownCdmTypeException e) {
|
|
543
|
// TODO Auto-generated catch block
|
|
544
|
e.printStackTrace();
|
|
545
|
}
|
|
546
|
List<Element> elInfoDetailList = elInfo.getChildren(childElementName, bfnNamespace);
|
|
547
|
|
|
548
|
for(Element elInfoDetail : elInfoDetailList){
|
|
549
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_RL_KAT)){
|
|
550
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
551
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
552
|
}
|
|
553
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_KAT)){
|
|
554
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
555
|
}
|
|
556
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_AKTUELLE_BESTANDSSTITUATION)){
|
|
557
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
558
|
}
|
|
559
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_LANGFRISTIGER_BESTANDSTREND)){
|
|
560
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
561
|
}
|
|
562
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_KURZFRISTIGER_BESTANDSTREND)){
|
|
563
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
564
|
}
|
|
565
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_RISIKOFAKTOREN)){
|
|
566
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
567
|
}
|
|
568
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_VERANTWORTLICHKEIT)){
|
|
569
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
570
|
}
|
|
571
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_ALTE_RL_KAT)){
|
|
572
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
573
|
}
|
|
574
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_NEOBIOTA)){
|
|
575
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
576
|
}
|
|
577
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_EINDEUTIGER_CODE)){
|
|
578
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
579
|
}
|
|
580
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.FEAT_KOMMENTAR_TAXONOMIE)){
|
|
581
|
makeFeatures(taxonDescription, elInfoDetail, state, true);
|
|
582
|
}
|
|
583
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.FEAT_KOMMENTAR_GEFAEHRDUNG)){
|
|
584
|
makeFeatures(taxonDescription, elInfoDetail, state, true);
|
|
585
|
}
|
|
586
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.VOC_SONDERFAELLE)){
|
|
587
|
makeFeatures(taxonDescription, elInfoDetail, state, false);
|
|
588
|
}
|
|
589
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.FEAT_LETZTER_NACHWEIS)){
|
|
590
|
makeFeatures(taxonDescription, elInfoDetail, state, true);
|
|
591
|
}
|
|
592
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase(BfnXmlConstants.FEAT_WEITERE_KOMMENTARE)){
|
|
593
|
makeFeatures(taxonDescription, elInfoDetail, state, true);
|
|
594
|
}
|
|
595
|
//create german federal states distribution status
|
|
596
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("BW")){
|
|
597
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
598
|
}
|
|
599
|
//create german federal states distribution status
|
|
600
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("BY")){
|
|
601
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
602
|
}
|
|
603
|
//create german federal states distribution status
|
|
604
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("BE")){
|
|
605
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
606
|
}
|
|
607
|
//create german federal states distribution status
|
|
608
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("BB")){
|
|
609
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
610
|
}
|
|
611
|
//create german federal states distribution status
|
|
612
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("HB")){
|
|
613
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
614
|
}
|
|
615
|
//create german federal states distribution status
|
|
616
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("HH")){
|
|
617
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
618
|
}
|
|
619
|
//create german federal states distribution status
|
|
620
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("HE")){
|
|
621
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
622
|
}
|
|
623
|
//create german federal states distribution status
|
|
624
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("MV")){
|
|
625
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
626
|
}
|
|
627
|
//create german federal states distribution status
|
|
628
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("NI")){
|
|
629
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
630
|
}
|
|
631
|
//create german federal states distribution status
|
|
632
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("NW")){
|
|
633
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
634
|
}
|
|
635
|
//create german federal states distribution status
|
|
636
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("RP")){
|
|
637
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
638
|
}
|
|
639
|
//create german federal states distribution status
|
|
640
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("SL")){
|
|
641
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
642
|
}
|
|
643
|
//create german federal states distribution status
|
|
644
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("SN")){
|
|
645
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
646
|
}
|
|
647
|
//create german federal states distribution status
|
|
648
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("ST")){
|
|
649
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
650
|
}
|
|
651
|
//create german federal states distribution status
|
|
652
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("SH")){
|
|
653
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
654
|
}
|
|
655
|
//create german federal states distribution status
|
|
656
|
if(elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME).equalsIgnoreCase("TH")){
|
|
657
|
createDistributionStatus(elInfoDetail, state, taxonDescription);
|
|
658
|
}
|
|
659
|
}
|
|
660
|
}
|
|
661
|
}
|
|
662
|
}
|
|
663
|
|
|
664
|
|
|
665
|
private void makeCommonName(TaxonDescription taxonDescription,
|
|
666
|
Element child, BfnXmlImportState state) {
|
|
667
|
String commonNameValue = child.getValue();
|
|
668
|
NamedArea area = getTermService().getAreaByTdwgAbbreviation("GER");
|
|
669
|
CommonTaxonName commonName = CommonTaxonName.NewInstance(commonNameValue, Language.GERMAN(), area);
|
|
670
|
taxonDescription.addElement(commonName);
|
|
671
|
}
|
|
672
|
|
|
673
|
|
|
674
|
/**
|
|
675
|
*
|
|
676
|
* @param taxonDescription
|
|
677
|
* @param elInfoDetail
|
|
678
|
* @param state
|
|
679
|
* @param isTextData
|
|
680
|
*/
|
|
681
|
private void makeFeatures(
|
|
682
|
TaxonDescription taxonDescription,
|
|
683
|
Element elInfoDetail,
|
|
684
|
BfnXmlImportState state,
|
|
685
|
boolean isTextData) {
|
|
686
|
|
|
687
|
String transformedRlKatValue = null;
|
|
688
|
UUID featureUUID = null;
|
|
689
|
UUID stateTermUUID = null;
|
|
690
|
String strRlKatValue = elInfoDetail.getChild(BfnXmlConstants.EL_WERT).getValue();
|
|
691
|
String strRlKat = elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME);
|
|
692
|
boolean randomStateUUID = false;
|
|
693
|
try {
|
|
694
|
featureUUID = BfnXmlTransformer.getRedlistFeatureUUID(strRlKat);
|
|
695
|
transformedRlKatValue = BfnXmlTransformer.redListString2RedListCode(strRlKatValue);
|
|
696
|
} catch (UnknownCdmTypeException e) {
|
|
697
|
transformedRlKatValue = strRlKatValue;
|
|
698
|
}
|
|
699
|
if (featureUUID == null){
|
|
700
|
logger.warn("featureUUID is null for " + strRlKat);
|
|
701
|
}
|
|
702
|
State rlState = null;
|
|
703
|
//if is text data a state is not needed
|
|
704
|
if(!isTextData){
|
|
705
|
try {
|
|
706
|
stateTermUUID = BfnXmlTransformer.getRedlistStateTermUUID(transformedRlKatValue, strRlKat);
|
|
707
|
} catch (UnknownCdmTypeException e) {
|
|
708
|
stateTermUUID = UUID.randomUUID();
|
|
709
|
randomStateUUID = true;
|
|
710
|
}
|
|
711
|
if(randomStateUUID || stateTermUUID == BfnXmlTransformer.stateTermEmpty){
|
|
712
|
if(stateTermUUID == BfnXmlTransformer.stateTermEmpty) {
|
|
713
|
transformedRlKatValue = "keine Angabe";
|
|
714
|
}
|
|
715
|
rlState = getStateTerm(state, stateTermUUID, transformedRlKatValue, transformedRlKatValue, transformedRlKatValue, null);
|
|
716
|
}else{
|
|
717
|
rlState = getStateTerm(state, stateTermUUID);
|
|
718
|
}
|
|
719
|
}
|
|
720
|
|
|
721
|
if (featureUUID != null){
|
|
722
|
Feature redListFeature = getFeature(state, featureUUID);
|
|
723
|
if(isTextData){
|
|
724
|
TextData textData = TextData.NewInstance(redListFeature);
|
|
725
|
textData.putText(Language.GERMAN(), strRlKatValue);
|
|
726
|
DescriptionElementBase descriptionElement = textData;
|
|
727
|
taxonDescription.addElement(descriptionElement);
|
|
728
|
}else{
|
|
729
|
CategoricalData catData = CategoricalData.NewInstance(rlState, redListFeature);
|
|
730
|
DescriptionElementBase descriptionElement = catData;
|
|
731
|
taxonDescription.addElement(descriptionElement);
|
|
732
|
}
|
|
733
|
}else{
|
|
734
|
logger.warn("Not descriptive data imported");
|
|
735
|
}
|
|
736
|
}
|
|
737
|
|
|
738
|
/**
|
|
739
|
* Returns the rank represented by the rank element.<br>
|
|
740
|
* Returns <code>null</code> if the element is null.<br>
|
|
741
|
* Returns <code>null</code> if the code and the text are both either empty or do not exists.<br>
|
|
742
|
* Returns the rank represented by the code attribute, if the code attribute is not empty and could be resolved.<br>
|
|
743
|
* If the code could not be resolved it returns the rank represented most likely by the elements text.<br>
|
|
744
|
* Returns UNKNOWN_RANK if code attribute and element text could not be resolved.
|
|
745
|
* @param strRank bfn rank element
|
|
746
|
* @return
|
|
747
|
*/
|
|
748
|
protected static Rank makeRank(String strRank){
|
|
749
|
Rank result;
|
|
750
|
if (StringUtils.isBlank(strRank)){
|
|
751
|
return null;
|
|
752
|
}
|
|
753
|
Rank codeRank = BfnXmlTransformer.getRankForRankCode(strRank);
|
|
754
|
if(codeRank==null){
|
|
755
|
codeRank = Rank.UNKNOWN_RANK();
|
|
756
|
}
|
|
757
|
//codeRank exists
|
|
758
|
if ( (codeRank != null) && !codeRank.equals(Rank.UNKNOWN_RANK())){
|
|
759
|
result = codeRank;
|
|
760
|
}
|
|
761
|
//codeRank does not exist
|
|
762
|
else{
|
|
763
|
result = codeRank;
|
|
764
|
logger.warn("string rank ('"+strRank+"') used, because code rank does not exist or was not recognized: " + codeRank.getTitleCache()+" "+strRank);
|
|
765
|
}
|
|
766
|
return result;
|
|
767
|
}
|
|
768
|
|
|
769
|
/**
|
|
770
|
* @param rank
|
|
771
|
* @param strAuthor
|
|
772
|
* @param strSupplement
|
|
773
|
* @param elWissName
|
|
774
|
* @return
|
|
775
|
* @throws UnknownCdmTypeException
|
|
776
|
*/
|
|
777
|
private TaxonName parseNonviralNames(Rank rank, String strAuthor, String strSupplement, Element elWissName)
|
|
778
|
throws UnknownCdmTypeException {
|
|
779
|
TaxonName taxonNameBase = null;
|
|
780
|
|
|
781
|
String strScientificName = elWissName.getTextNormalize();
|
|
782
|
strScientificName = normalizeScientificName(strScientificName, strSupplement);
|
|
783
|
NonViralNameParserImpl parser = NonViralNameParserImpl.NewInstance();
|
|
784
|
TaxonName nonViralName = (TaxonName)parser.parseFullName(strScientificName, nomenclaturalCode, rank);
|
|
785
|
if(nonViralName.hasProblem()){
|
|
786
|
for(ParserProblem p: nonViralName.getParsingProblems()){
|
|
787
|
logger.warn(++parsingProblemCounter + " " +nonViralName.getTitleCache() + " " + p.toString());
|
|
788
|
}
|
|
789
|
}
|
|
790
|
//check for parsed rank
|
|
791
|
Rank parsedRank = nonViralName.getRank();
|
|
792
|
if(parsedRank != rank){
|
|
793
|
nonViralName.setRank(rank);
|
|
794
|
}
|
|
795
|
//check for parsed author
|
|
796
|
String parsedAuthor = nonViralName.getAuthorshipCache();
|
|
797
|
strAuthor = StringUtils.trim(strAuthor);
|
|
798
|
parsedAuthor = StringUtils.trim(parsedAuthor);
|
|
799
|
if(parsedAuthor.equalsIgnoreCase(strAuthor)){
|
|
800
|
logger.info("Taxon " + nonViralName.getTitleCache() +":"
|
|
801
|
+"\t Author field: " + strAuthor +" and parsed AuthorshipCache: "+nonViralName.getAuthorshipCache());
|
|
802
|
}
|
|
803
|
taxonNameBase = nonViralName;
|
|
804
|
return taxonNameBase;
|
|
805
|
}
|
|
806
|
|
|
807
|
|
|
808
|
/**
|
|
809
|
* @param strSupplement
|
|
810
|
* @param strScientificName
|
|
811
|
* @return
|
|
812
|
*/
|
|
813
|
protected String normalizeScientificName(String strScientificName, String strSupplement) {
|
|
814
|
// trim strScienctificName because sometimes getTextNormalize() does not removes all the whitespaces
|
|
815
|
strScientificName = StringUtils.trim(strScientificName);
|
|
816
|
strScientificName = StringUtils.remove(strScientificName, "\u00a0");
|
|
817
|
strScientificName = StringUtils.remove(strScientificName, "\uc281");
|
|
818
|
|
|
819
|
if(StringUtils.isNotBlank(strSupplement)){
|
|
820
|
strScientificName = StringUtils.remove(strScientificName, strSupplement);
|
|
821
|
}
|
|
822
|
//Eulenspinner/spanner have different taxon name syntax like "pupillata (Thunberg, 1788); Epirrhoe"
|
|
823
|
if(strScientificName.contains(";")){
|
|
824
|
String[] splits = strScientificName.split(";");
|
|
825
|
if (splits.length != 2){
|
|
826
|
logger.warn("Unexpected length of semicolon scientific name: " + splits.length + "; " + strScientificName);
|
|
827
|
}
|
|
828
|
strScientificName = splits[1].trim() + " " + splits[0].trim();
|
|
829
|
}
|
|
830
|
|
|
831
|
return strScientificName;
|
|
832
|
}
|
|
833
|
|
|
834
|
/**
|
|
835
|
* This method will match the BFN XML status to a distribution status
|
|
836
|
* and map it to the german federal state area. The vocabulary needs to be
|
|
837
|
* created first by the Importer, in order to map the terms correctly. Have a look
|
|
838
|
* for further details at the file BfnXmlImportAdditionalTerms.
|
|
839
|
*
|
|
840
|
*
|
|
841
|
* @param taxon, for saving the distribution and its status
|
|
842
|
* @param elInfoDetail, keeps the details from the import, in this case the distribution detail
|
|
843
|
* @param state, import state
|
|
844
|
* @param germanState, the abbreviated label for the German state
|
|
845
|
*
|
|
846
|
*/
|
|
847
|
private void createDistributionStatus(Element elInfoDetail, BfnXmlImportState state,
|
|
848
|
TaxonDescription taxonDescription){
|
|
849
|
|
|
850
|
String strDistributionValue = elInfoDetail.getChild(BfnXmlConstants.EL_WERT).getValue();
|
|
851
|
if (strDistributionValue.startsWith("#dtpl_RLKat")){
|
|
852
|
try {
|
|
853
|
strDistributionValue = BfnXmlTransformer.redListString2RedListCode(strDistributionValue);
|
|
854
|
} catch (UnknownCdmTypeException e) {
|
|
855
|
logger.warn("RL Kategorie " + strDistributionValue + " konnte nicht gematched werden ");
|
|
856
|
}
|
|
857
|
}
|
|
858
|
String strArea = elInfoDetail.getAttributeValue(BfnXmlConstants.ATT_STANDARDNAME);
|
|
859
|
if (strArea.equals("RL Kat.")){
|
|
860
|
strArea = "Deutschland";
|
|
861
|
}
|
|
862
|
//match DistributionValue
|
|
863
|
UUID matchedDistributionUUID;
|
|
864
|
try {
|
|
865
|
matchedDistributionUUID = BfnXmlTransformer.matchDistributionValue(strDistributionValue);
|
|
866
|
} catch (UnknownCdmTypeException e1) {
|
|
867
|
logger.warn("could not match xml value "+ strDistributionValue +" to distribution status for "+strArea);
|
|
868
|
// e1.printStackTrace();
|
|
869
|
return;
|
|
870
|
}
|
|
871
|
if (matchedDistributionUUID == null){
|
|
872
|
return;
|
|
873
|
}
|
|
874
|
PresenceAbsenceTerm status;
|
|
875
|
DefinedTermBase<?> load = getTermService().load(matchedDistributionUUID);
|
|
876
|
if(load.isInstanceOf(PresenceAbsenceTerm.class)) {
|
|
877
|
status = CdmBase.deproxy(load, PresenceAbsenceTerm.class);
|
|
878
|
}else{
|
|
879
|
logger.warn(strDistributionValue + " is not PresenceAbsence Term " + load.getTitleCache() + " " + load.getTermType().toString());
|
|
880
|
return;
|
|
881
|
}
|
|
882
|
//load vocabulary and german state
|
|
883
|
UUID stateUUID = null;
|
|
884
|
|
|
885
|
try {
|
|
886
|
stateUUID = BfnXmlTransformer.getAreaUUID(strArea);
|
|
887
|
} catch (UnknownCdmTypeException e1) {
|
|
888
|
logger.warn("could not match state" + strArea + " to UUID");
|
|
889
|
e1.printStackTrace();
|
|
890
|
return;
|
|
891
|
}
|
|
892
|
NamedArea area = (NamedArea)getTermService().load(stateUUID);
|
|
893
|
|
|
894
|
// try {
|
|
895
|
// vocabularyUUID = BfnXmlTransformer.getRedlistVocabularyUUID("Bundesländer");
|
|
896
|
// vocabulary = getVocabularyService().load(vocabularyUUID);
|
|
897
|
// } catch (UnknownCdmTypeException e) {
|
|
898
|
// logger.warn("could not load vocabulary");
|
|
899
|
// e.printStackTrace();
|
|
900
|
// return;
|
|
901
|
// }
|
|
902
|
// NamedArea area = null;
|
|
903
|
// for(Object term: vocabulary){
|
|
904
|
// //TODO match german state
|
|
905
|
// NamedArea narea = (NamedArea) term;
|
|
906
|
// Set<Representation> representations = narea.getRepresentations();
|
|
907
|
// for(Representation r:representations){
|
|
908
|
// if(r.getAbbreviatedLabel().equalsIgnoreCase(strGermanState)){
|
|
909
|
// area = narea;
|
|
910
|
// }
|
|
911
|
// }
|
|
912
|
//
|
|
913
|
// }
|
|
914
|
//add to taxon description
|
|
915
|
DescriptionElementBase descriptionElement = Distribution.NewInstance(area, status);
|
|
916
|
taxonDescription.addElement(descriptionElement);
|
|
917
|
}
|
|
918
|
|
|
919
|
|
|
920
|
@Override
|
|
921
|
public boolean doCheck(BfnXmlImportState state){
|
|
922
|
boolean result = true;
|
|
923
|
return result;
|
|
924
|
}
|
|
925
|
|
|
926
|
@Override
|
|
927
|
protected boolean isIgnore(BfnXmlImportState state){
|
|
928
|
return ! state.getConfig().isDoTaxonNames();
|
|
929
|
}
|
|
930
|
}
|