bfa597cf246845db67700654ac6bd4bc114ddee1
[cdmlib-apps.git] / app-import / src / main / java / eu / etaxonomy / cdm / io / redlist / gefaesspflanzen / RedListGefaesspflanzenImportNames.java
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.gefaesspflanzen;
11
12 import java.sql.ResultSet;
13 import java.sql.SQLException;
14 import java.util.HashMap;
15 import java.util.HashSet;
16 import java.util.Map;
17 import java.util.Set;
18 import java.util.regex.Matcher;
19 import java.util.regex.Pattern;
20
21 import org.apache.log4j.Logger;
22 import org.springframework.stereotype.Component;
23
24 import eu.etaxonomy.cdm.common.CdmUtils;
25 import eu.etaxonomy.cdm.hibernate.HibernateProxyHelper;
26 import eu.etaxonomy.cdm.io.common.DbImportBase;
27 import eu.etaxonomy.cdm.io.common.IPartitionedIO;
28 import eu.etaxonomy.cdm.io.common.ImportHelper;
29 import eu.etaxonomy.cdm.io.common.ResultSetPartitioner;
30 import eu.etaxonomy.cdm.io.common.mapping.UndefinedTransformerMethodException;
31 import eu.etaxonomy.cdm.model.agent.AgentBase;
32 import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
33 import eu.etaxonomy.cdm.model.common.AnnotatableEntity;
34 import eu.etaxonomy.cdm.model.common.Annotation;
35 import eu.etaxonomy.cdm.model.common.AnnotationType;
36 import eu.etaxonomy.cdm.model.common.CdmBase;
37 import eu.etaxonomy.cdm.model.common.Language;
38 import eu.etaxonomy.cdm.model.common.OrderedTermVocabulary;
39 import eu.etaxonomy.cdm.model.description.CommonTaxonName;
40 import eu.etaxonomy.cdm.model.description.TaxonDescription;
41 import eu.etaxonomy.cdm.model.name.BotanicalName;
42 import eu.etaxonomy.cdm.model.name.CultivarPlantName;
43 import eu.etaxonomy.cdm.model.name.NomenclaturalCode;
44 import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
45 import eu.etaxonomy.cdm.model.name.NomenclaturalStatusType;
46 import eu.etaxonomy.cdm.model.name.NonViralName;
47 import eu.etaxonomy.cdm.model.name.Rank;
48 import eu.etaxonomy.cdm.model.name.RankClass;
49 import eu.etaxonomy.cdm.model.name.TaxonNameBase;
50 import eu.etaxonomy.cdm.model.taxon.Synonym;
51 import eu.etaxonomy.cdm.model.taxon.Taxon;
52 import eu.etaxonomy.cdm.model.taxon.TaxonBase;
53 import eu.etaxonomy.cdm.model.taxon.TaxonRelationship;
54 import eu.etaxonomy.cdm.model.taxon.TaxonRelationshipType;
55 import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
56
57 /**
58 *
59 * @author pplitzner
60 * @date Mar 1, 2016
61 *
62 */
63
64 @Component
65 @SuppressWarnings("serial")
66 public class RedListGefaesspflanzenImportNames extends DbImportBase<RedListGefaesspflanzenImportState, RedListGefaesspflanzenImportConfigurator> {
67
68 private static final Logger logger = Logger.getLogger(RedListGefaesspflanzenImportNames.class);
69
70 private static final String tableName = "Rote Liste Gefäßpflanzen";
71
72 private static final String pluralString = "names";
73
74 private static final boolean STRICT_TITLE_CHECK = false;
75
76 public RedListGefaesspflanzenImportNames() {
77 super(tableName, pluralString);
78 }
79
80 @Override
81 protected String getIdQuery(RedListGefaesspflanzenImportState state) {
82 return "SELECT SEQNUM "
83 + "FROM V_TAXATLAS_D20_EXPORT t "
84 + " ORDER BY SEQNUM";
85 }
86
87 @Override
88 protected String getRecordQuery(RedListGefaesspflanzenImportConfigurator config) {
89 String result = " SELECT * "
90 + " FROM V_TAXATLAS_D20_EXPORT t "
91 + " WHERE t.SEQNUM IN (@IDSET)";
92 result = result.replace("@IDSET", IPartitionedIO.ID_LIST_TOKEN);
93 return result;
94 }
95
96 @Override
97 protected void doInvoke(RedListGefaesspflanzenImportState state) {
98 super.doInvoke(state);
99 }
100
101
102 @Override
103 public boolean doPartition(ResultSetPartitioner partitioner, RedListGefaesspflanzenImportState state) {
104 ResultSet rs = partitioner.getResultSet();
105 Set<TaxonNameBase> namesToSave = new HashSet<TaxonNameBase>();
106 Set<TaxonBase> taxaToSave = new HashSet<TaxonBase>();
107 try {
108 while (rs.next()){
109 makeSingleNameAndTaxon(state, rs, namesToSave, taxaToSave);
110
111 }
112 } catch (SQLException e) {
113 e.printStackTrace();
114 }
115
116 getNameService().saveOrUpdate(namesToSave);
117 getTaxonService().saveOrUpdate(taxaToSave);
118 return true;
119 }
120
121 private void makeSingleNameAndTaxon(RedListGefaesspflanzenImportState state, ResultSet rs, Set<TaxonNameBase> namesToSave, Set<TaxonBase> taxaToSave)
122 throws SQLException {
123 long id = rs.getLong(RedListUtil.NAMNR);
124 String clTaxonString = rs.getString(RedListUtil.CL_TAXON);
125 String relationE = rs.getString(RedListUtil.E);
126 String relationW = rs.getString(RedListUtil.W);
127 String relationK = rs.getString(RedListUtil.K);
128 String relationAW = rs.getString(RedListUtil.AW);
129 String relationAO = rs.getString(RedListUtil.AO);
130 String relationR = rs.getString(RedListUtil.R);
131 String relationO = rs.getString(RedListUtil.O);
132 String relationS = rs.getString(RedListUtil.S);
133
134 //---NAME---
135 NonViralName<?> name = importName(state, rs, namesToSave);
136
137
138 //--- AUTHORS ---
139 importAuthors(state, rs, name);
140
141 //---TAXON---
142 TaxonBase<?> taxonBase = importTaxon(rs, name, state);
143 if(taxonBase==null){
144 RedListUtil.logMessage(id, "Taxon for name "+name+" could not be created.", logger);
145 return;
146 }
147
148 //---CONCEPT RELATIONSHIPS---
149 //E, W, K, AW, AO, R, O, S
150 cloneTaxon(taxonBase, relationE, RedListUtil.CLASSIFICATION_NAMESPACE_E, taxaToSave, id, state);
151 cloneTaxon(taxonBase, relationW, RedListUtil.CLASSIFICATION_NAMESPACE_W, taxaToSave, id, state);
152 cloneTaxon(taxonBase, relationK, RedListUtil.CLASSIFICATION_NAMESPACE_K, taxaToSave, id, state);
153 cloneTaxon(taxonBase, relationAW, RedListUtil.CLASSIFICATION_NAMESPACE_AW, taxaToSave, id, state);
154 cloneTaxon(taxonBase, relationAO, RedListUtil.CLASSIFICATION_NAMESPACE_AO, taxaToSave, id, state);
155 cloneTaxon(taxonBase, relationR, RedListUtil.CLASSIFICATION_NAMESPACE_R, taxaToSave, id, state);
156 cloneTaxon(taxonBase, relationO, RedListUtil.CLASSIFICATION_NAMESPACE_O, taxaToSave, id, state);
157 cloneTaxon(taxonBase, relationS, RedListUtil.CLASSIFICATION_NAMESPACE_S, taxaToSave, id, state);
158 //checklist
159 TaxonBase<?> checklistTaxon = null;
160 if(CdmUtils.isNotBlank(clTaxonString) && !clTaxonString.trim().equals("-")){
161 checklistTaxon = (TaxonBase<?>) taxonBase.clone();
162 if(checklistTaxon.isInstanceOf(Taxon.class)){
163 TaxonRelationship relation = HibernateProxyHelper.deproxy(checklistTaxon, Taxon.class).addTaxonRelation(HibernateProxyHelper.deproxy(taxonBase, Taxon.class), TaxonRelationshipType.CONGRUENT_TO(), null, null);
164 relation.setDoubtful(true);
165 }
166
167 ImportHelper.setOriginalSource(checklistTaxon, state.getTransactionalSourceReference(), id, RedListUtil.TAXON_CHECKLISTE_NAMESPACE);
168 taxaToSave.add(checklistTaxon);
169 }
170
171 //NOTE: the source has to be added after cloning or otherwise the clone would also get the source
172 ImportHelper.setOriginalSource(taxonBase, state.getTransactionalSourceReference(), id, RedListUtil.TAXON_GESAMTLISTE_NAMESPACE);
173 taxaToSave.add(taxonBase);
174 }
175
176 private void cloneTaxon(final TaxonBase<?> gesamtListeTaxon, String relationString, String sourceNameSpace, Set<TaxonBase> taxaToSave, long id, RedListGefaesspflanzenImportState state){
177 if(CdmUtils.isNotBlank(relationString) && !relationString.equals(".")){
178 Taxon clonedTaxon = null;
179
180 if(gesamtListeTaxon.isInstanceOf(Taxon.class)){
181 clonedTaxon = HibernateProxyHelper.deproxy(gesamtListeTaxon.clone(), Taxon.class);
182 }
183 else if(gesamtListeTaxon.isInstanceOf(Synonym.class)){
184 clonedTaxon = Taxon.NewInstance(gesamtListeTaxon.getName(), gesamtListeTaxon.getSec());
185 }
186 else{
187 RedListUtil.logMessage(id, "Taxon base "+gesamtListeTaxon+" is neither taxon nor synonym! Taxon could not be cloned", logger);
188 return;
189 }
190 ImportHelper.setOriginalSource(clonedTaxon, state.getTransactionalSourceReference(), id, sourceNameSpace);
191 taxaToSave.add(clonedTaxon);
192 }
193 }
194
195 private TaxonBase<?> importTaxon(ResultSet rs, NonViralName<?> name, RedListGefaesspflanzenImportState state) throws SQLException {
196
197 long id = rs.getLong(RedListUtil.NAMNR);
198 String taxNameString = rs.getString(RedListUtil.TAXNAME);
199 String epi1String = rs.getString(RedListUtil.EPI1);
200 String epi2String = rs.getString(RedListUtil.EPI2);
201 String epi3String = rs.getString(RedListUtil.EPI3);
202 String gueltString = rs.getString(RedListUtil.GUELT);
203 String trivialString = rs.getString(RedListUtil.TRIVIAL);
204 String authorBasiString = rs.getString(RedListUtil.AUTOR_BASI);
205 String hybString = rs.getString(RedListUtil.HYB);
206 String florString = rs.getString(RedListUtil.FLOR);
207 String atlasIdxString = rs.getString(RedListUtil.ATLAS_IDX);
208 String kartString = rs.getString(RedListUtil.KART);
209 String rl2015String = rs.getString(RedListUtil.RL2015);
210 String ehrdString = rs.getString(RedListUtil.EHRD);
211 String wisskString = rs.getString(RedListUtil.WISSK);
212
213 TaxonBase<?> taxonBase = null;
214 if(authorBasiString.trim().contains(RedListUtil.AUCT)){
215 taxonBase = Taxon.NewInstance(name, null);
216 taxonBase.setAppendedPhrase(RedListUtil.AUCT);
217 }
218 else if(gueltString.equals(RedListUtil.GUELT_ACCEPTED_TAXON)){
219 taxonBase = Taxon.NewInstance(name, null);
220 }
221 else if(gueltString.equals(RedListUtil.GUELT_SYNONYM) || gueltString.equals(RedListUtil.GUELT_BASIONYM)){
222 taxonBase = Synonym.NewInstance(name, null);
223 }
224 else{
225 return null;
226 }
227
228 //common name
229 if(taxonBase.isInstanceOf(Taxon.class) && trivialString!=null){
230 Taxon taxon = HibernateProxyHelper.deproxy(taxonBase, Taxon.class);
231 TaxonDescription description = TaxonDescription.NewInstance(taxon);
232 description.addElement(CommonTaxonName.NewInstance(trivialString, Language.GERMAN()));
233 }
234
235 //add annotations
236 addAnnotation(RedListUtil.FLOR+": "+florString, taxonBase);
237 addAnnotation(RedListUtil.ATLAS_IDX+": "+atlasIdxString, taxonBase);
238 addAnnotation(RedListUtil.KART+": "+kartString, taxonBase);
239 addAnnotation(RedListUtil.RL2015+": "+rl2015String, taxonBase);
240 addAnnotation(RedListUtil.EHRD+": "+ehrdString, taxonBase);
241 addAnnotation(RedListUtil.WISSK+": "+wisskString, taxonBase);
242
243 //check taxon name consistency
244 checkTaxonConsistency(id, taxNameString, hybString, epi1String, epi2String, epi3String, taxonBase, state);
245 return taxonBase;
246 }
247
248 private void addAnnotation(String string, AnnotatableEntity entity) {
249 if(CdmUtils.isNotBlank(string)){
250 entity.addAnnotation(Annotation.NewInstance(string, AnnotationType.TECHNICAL(), Language.GERMAN()));
251 }
252 }
253
254 private void importAuthors(RedListGefaesspflanzenImportState state, ResultSet rs, NonViralName<?> name) throws SQLException {
255
256 long id = rs.getLong(RedListUtil.NAMNR);
257 String nomZusatzString = rs.getString(RedListUtil.NOM_ZUSATZ);
258 String taxZusatzString = rs.getString(RedListUtil.TAX_ZUSATZ);
259 String zusatzString = rs.getString(RedListUtil.ZUSATZ);
260 String authorKombString = rs.getString(RedListUtil.AUTOR_KOMB);
261 String authorBasiString = rs.getString(RedListUtil.AUTOR_BASI);
262 String hybString = rs.getString(RedListUtil.HYB);
263
264 //combination author
265 if(authorKombString.contains(RedListUtil.EX)){
266 //TODO: what happens with multiple ex authors??
267 String[] kombSplit = authorKombString.split(RedListUtil.EX);
268 if(kombSplit.length!=2){
269 RedListUtil.logMessage(id, "Multiple ex combination authors found", logger);
270 }
271 for (int i = 0; i < kombSplit.length; i++) {
272 if(i==0){
273 //first author is ex author
274 TeamOrPersonBase<?> authorKomb = (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, kombSplit[i]);
275 name.setExCombinationAuthorship(authorKomb);
276 }
277 else{
278 TeamOrPersonBase<?> authorKomb = (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, kombSplit[i]);
279 name.setCombinationAuthorship(authorKomb);
280 }
281 }
282 }
283 else if(authorKombString.trim().contains(RedListUtil.AUCT)){
284 RedListUtil.logMessage(id, "AUCT information in "+RedListUtil.AUTOR_KOMB+" column", logger);
285 }
286 else if(CdmUtils.isNotBlank(authorKombString)){
287 TeamOrPersonBase<?> authorKomb = (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, authorKombString);
288 name.setCombinationAuthorship(authorKomb);
289 }
290 //basionym author
291 if(authorBasiString.contains(RedListUtil.EX)){
292 String[] basiSplit = authorBasiString.split(RedListUtil.EX);
293 for (int i = 0; i < basiSplit.length; i++) {
294 if(basiSplit.length!=2){
295 RedListUtil.logMessage(id, "Multiple ex basionymn authors found", logger);
296 }
297 if(i==0){
298 TeamOrPersonBase<?> authorBasi= (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, basiSplit[i]);
299 if(CdmUtils.isBlank(authorKombString)){
300 name.setExCombinationAuthorship(authorBasi);
301 }
302 else{
303 name.setExBasionymAuthorship(authorBasi);
304 }
305 }
306 else{
307 TeamOrPersonBase<?> authorBasi= (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, basiSplit[i]);
308 if(CdmUtils.isBlank(authorKombString)){
309 name.setCombinationAuthorship(authorBasi);
310 }
311 else{
312 name.setBasionymAuthorship(authorBasi);
313 }
314 }
315 }
316 }
317 else if(CdmUtils.isNotBlank(authorBasiString)){
318 //this seems to be a convention in the source database: When there is only a single author then only the "AUTOR_BASI" column is used
319 TeamOrPersonBase<?> authorBasi= (TeamOrPersonBase<?>) state.getRelatedObject(RedListUtil.AUTHOR_NAMESPACE, authorBasiString);
320 if(CdmUtils.isBlank(authorKombString)){
321 name.setCombinationAuthorship(authorBasi);
322 }
323 else{
324 name.setBasionymAuthorship(authorBasi);
325 }
326 }
327
328 //check authorship consistency
329 String authorString = rs.getString(RedListUtil.AUTOR);
330 checkNameConsistency(id, nomZusatzString, taxZusatzString, zusatzString, authorString, hybString, name);
331 }
332
333 private NonViralName<?> importName(RedListGefaesspflanzenImportState state, ResultSet rs, Set<TaxonNameBase> namesToSave) throws SQLException {
334
335 long id = rs.getLong(RedListUtil.NAMNR);
336 String taxNameString = rs.getString(RedListUtil.TAXNAME);
337 String rangString = rs.getString(RedListUtil.RANG);
338 String ep1String = rs.getString(RedListUtil.EPI1);
339 String ep2String = rs.getString(RedListUtil.EPI2);
340 String ep3String = rs.getString(RedListUtil.EPI3);
341 String nomZusatzString = rs.getString(RedListUtil.NOM_ZUSATZ);
342 String hybString = rs.getString(RedListUtil.HYB);
343 String formelString = rs.getString(RedListUtil.FORMEL);
344
345 if(CdmUtils.isBlank(taxNameString) && CdmUtils.isBlank(ep1String)){
346 RedListUtil.logMessage(id, "No name found!", logger);
347 }
348
349 NonViralName<?> name = null;
350 Rank rank = makeRank(id, state, rangString, CdmUtils.isNotBlank(ep3String));
351 //cultivar
352 if(rank!= null && rank.equals(Rank.CULTIVAR())){
353 CultivarPlantName cultivar = CultivarPlantName.NewInstance(rank);
354 cultivar.setGenusOrUninomial(ep1String);
355 cultivar.setSpecificEpithet(ep2String);
356 cultivar.setCultivarName(ep3String);
357 name = cultivar;
358 }
359 //botanical names
360 else{
361 name = BotanicalName.NewInstance(rank);
362
363 //ep1 should always be present
364 if(CdmUtils.isBlank(ep1String)){
365 RedListUtil.logMessage(id, RedListUtil.EPI1+" is empty!", logger);
366 }
367 name.setGenusOrUninomial(ep1String);
368 if(CdmUtils.isNotBlank(ep2String)){
369 if(rank!=null && rank.isInfraGenericButNotSpeciesGroup()){
370 name.setInfraGenericEpithet(ep2String);
371 }
372 else{
373 name.setSpecificEpithet(ep2String);
374 }
375 }
376 if(CdmUtils.isNotBlank(ep3String)){
377 name.setInfraSpecificEpithet(ep3String);
378 }
379
380
381 //nomenclatural status
382 if(CdmUtils.isNotBlank(nomZusatzString)){
383 NomenclaturalStatusType statusType = makeNomenclaturalStatus(id, state, nomZusatzString);
384 if(statusType!=null){
385 NomenclaturalStatus status = NomenclaturalStatus.NewInstance(statusType);
386 //special case for invalid names where the DB entry contains
387 //additional information in brackets e.g. "nom. inval. (sine basion.)"
388 if(statusType.equals(NomenclaturalStatusType.INVALID()) || statusType.equals(NomenclaturalStatusType.REJECTED()) ){
389 Pattern pattern = Pattern.compile("\\((.*?)\\)");
390 Matcher matcher = pattern.matcher(nomZusatzString);
391 if (matcher.find()){
392 status.setRuleConsidered(matcher.group(1));
393 }
394 }
395 name.addStatus(status);
396 }
397 }
398 //hybrid
399 if(CdmUtils.isNotBlank(hybString)){
400 //more than two hybrids not yet handled by name parser
401 //TODO: use parser when implemented to fully support hybrids
402 if(taxNameString.split(RedListUtil.HYB_SIGN).length>2){
403 name = BotanicalName.NewInstance(rank);
404 name.setTitleCache(taxNameString, true);
405 }
406 else if(hybString.equals(RedListUtil.HYB_X)){
407 name.setBinomHybrid(true);
408 }
409 else if(hybString.equals(RedListUtil.HYB_G)){
410 name.setMonomHybrid(true);
411 }
412 else if(hybString.equals(RedListUtil.HYB_XF) || hybString.equals(RedListUtil.HYB_XU)){
413 name.setHybridFormula(true);
414 String fullFormula = buildHybridFormula(ep1String, ep2String, ep3String, rank);
415 name = NonViralNameParserImpl.NewInstance().parseFullName(fullFormula, NomenclaturalCode.ICNAFP, rank);
416 }
417 else if(hybString.equals(RedListUtil.HYB_N)){
418 name = NonViralNameParserImpl.NewInstance().parseFullName(taxNameString, NomenclaturalCode.ICNAFP, rank);
419 }
420 else if(hybString.equals(RedListUtil.HYB_GF)){
421 if(ep1String.contains(RedListUtil.HYB_SIGN)){
422 name = NonViralNameParserImpl.NewInstance().parseFullName(ep1String, NomenclaturalCode.ICNAFP, rank);
423 }
424 else{
425 RedListUtil.logMessage(id, "HYB is "+hybString+" but "+RedListUtil.HYB+" does not contain "+RedListUtil.HYB_SIGN, logger);
426 }
427 }
428 else if(hybString.equals(RedListUtil.HYB_XS)){
429 //nothing to do
430 }
431 else{
432 logger.error("HYB value "+hybString+" not yet handled");
433 }
434 //save hybrid formula
435 if(CdmUtils.isNotBlank(formelString)){
436 Annotation annotation = Annotation.NewDefaultLanguageInstance(formelString);
437 annotation.setAnnotationType(AnnotationType.TECHNICAL());
438 name.addAnnotation(annotation);
439 }
440 }
441 }
442
443 //add source
444 ImportHelper.setOriginalSource(name, state.getTransactionalSourceReference(), id, RedListUtil.NAME_NAMESPACE);
445
446 namesToSave.add(name);
447 return name;
448 }
449
450 private String buildHybridFormula(String ep1String, String ep2String, String ep3String, Rank rank) {
451 String fullFormula = null;
452 if(ep1String.contains(RedListUtil.HYB_SIGN)){
453 fullFormula = ep1String;
454 }
455 else if(ep2String.contains(RedListUtil.HYB_SIGN)){
456 String[] split = ep2String.split(RedListUtil.HYB_SIGN);
457 String hybridFormula1 = ep1String+" "+split[0].trim();
458 String hybridFormula2 = ep1String+" "+split[1].trim();
459 //check if the genus is mentioned in EP2 or not
460 String[] secondHybrid = split[1].trim().split(" ");
461 //check if the genus is abbreviated like e.g. Centaurea jacea × C. decipiens
462 if(secondHybrid.length>1 && secondHybrid[0].matches("[A-Z]\\.")){
463 hybridFormula2 = ep1String+" "+split[1].trim().substring(3);
464 }
465 else if(secondHybrid.length>1 && secondHybrid[0].matches("[A-Z].*")){
466 hybridFormula2 = split[1].trim();
467 }
468 if(CdmUtils.isNotBlank(ep3String)){
469 hybridFormula1 += " "+rank.getAbbreviation()+" "+ep3String;
470 hybridFormula2 += " "+rank.getAbbreviation()+" "+ep3String;
471 }
472 fullFormula = hybridFormula1+" "+RedListUtil.HYB_SIGN+" "+hybridFormula2;
473 }
474 else if(ep3String.contains(RedListUtil.HYB_SIGN)){
475 String[] split = ep3String.split(RedListUtil.HYB_SIGN);
476 String hybridFormula1 = ep1String+" "+ep2String+" "+rank.getAbbreviation()+" "+split[0].trim();
477 String hybridFormula2 = ep1String+" "+ep2String+" "+rank.getAbbreviation()+" "+split[1].trim();
478 //check if the genus is mentioned in EP3 or not
479 String[] secondHybrid = split[1].trim().split(" ");
480 //check if the genus is abbreviated like e.g. Centaurea jacea jacea × C. jacea subsp. decipiens
481 if(secondHybrid.length>1 && secondHybrid[0].matches("[A-Z]\\.")){
482 hybridFormula2 = ep1String+" "+split[1].trim().substring(3);
483 }
484 else if(secondHybrid.length>1 && secondHybrid[0].matches("[A-Z].*")){
485 hybridFormula2 = split[1].trim();
486 }
487 fullFormula = hybridFormula1+" "+RedListUtil.HYB_SIGN+" "+hybridFormula2;
488 }
489 return fullFormula;
490 }
491
492 private void checkNameConsistency(long id, String nomZusatzString, String taxZusatzString,
493 String zusatzString, String authorString, String hybString, NonViralName<?> name) {
494 String authorshipCache = name.getAuthorshipCache();
495 //FIXME: remove split length check when name parser can parse multiple hybrid parents
496 if(hybString.equals(RedListUtil.HYB_XF) && name.getTitleCache().split(RedListUtil.HYB_SIGN).length==2){
497 if(name.getHybridChildRelations().isEmpty()){
498 RedListUtil.logMessage(id, "Hybrid formula but no hybrid child relations: "+name.getTitleCache(), logger);
499 return;
500 }
501 return;
502 }
503
504 if(CdmUtils.isNotBlank(zusatzString)){
505 authorString = authorString.replace(", "+zusatzString, "");
506 }
507 if(CdmUtils.isNotBlank(nomZusatzString)){
508 authorString = authorString.replace(", "+nomZusatzString, "");
509 }
510 if(CdmUtils.isNotBlank(taxZusatzString)){
511 authorString = authorString.replace(", "+taxZusatzString, "");
512 }
513 if(authorString.equals(RedListUtil.AUCT)){
514 authorString = "";
515 }
516 if(STRICT_TITLE_CHECK){
517 if(!authorString.equals(authorshipCache)){
518 RedListUtil.logMessage(id, "Authorship inconsistent! name.authorhshipCache <-> Column "+RedListUtil.AUTOR+": "+authorshipCache+" <-> "+authorString, logger);
519 }
520 }
521 else{
522 if(CdmUtils.isNotBlank(authorString) && !authorString.startsWith(authorshipCache)){
523 RedListUtil.logMessage(id, "Authorship inconsistent! name.authorhshipCache <-> Column "+RedListUtil.AUTOR+": "+authorshipCache+" <-> "+authorString, logger);
524 }
525 }
526 }
527
528 private void checkTaxonConsistency(long id, String taxNameString, String hybString, String epi1String, String epi2String, String epi3String, TaxonBase<?> taxonBase, RedListGefaesspflanzenImportState state) {
529 if(taxNameString.split(RedListUtil.HYB_SIGN).length>2){
530 RedListUtil.logInfoMessage(id, "multiple hybrid signs. No name check for "+taxNameString, logger);
531 return;
532 }
533
534 String nameCache = HibernateProxyHelper.deproxy(taxonBase.getName(), NonViralName.class).getNameCache().trim();
535 taxNameString = taxNameString.trim();
536 taxNameString = taxNameString.replaceAll(" +", " ");
537
538
539 if(hybString.equals(RedListUtil.HYB_X) || hybString.equals(RedListUtil.HYB_N)){
540 taxNameString = taxNameString.replace(" "+RedListUtil.HYB_SIGN+" ", " "+RedListUtil.HYB_SIGN);//hybrid sign has no space after it in titleCache for binomial hybrids
541 taxNameString = taxNameString.replace(" x ", " "+RedListUtil.HYB_SIGN);//in some cases a standard 'x' is used
542 }
543 else if(hybString.equals(RedListUtil.HYB_G)){
544 taxNameString = taxNameString.replace("X ", RedListUtil.HYB_SIGN);
545 }
546 else if(hybString.equals(RedListUtil.HYB_GF)){
547 taxNameString = taxNameString.replace(" "+RedListUtil.HYB_SIGN+" ", " "+RedListUtil.HYB_SIGN);
548 }
549 else if(hybString.equals(RedListUtil.HYB_XF)){
550 nameCache = taxonBase.getName().getTitleCache();
551 if(nameCache.contains("sec")){
552 nameCache = nameCache.substring(0, nameCache.indexOf("sec"));
553 }
554 if(!STRICT_TITLE_CHECK){
555 taxNameString = buildHybridFormula(epi1String, epi2String, epi3String, taxonBase.getName().getRank());
556 }
557 if(taxNameString.split(RedListUtil.HYB_SIGN).length==1){
558 taxNameString = taxNameString.replace(RedListUtil.HYB_SIGN+" ", RedListUtil.HYB_SIGN);
559 }
560 }
561
562 if(taxNameString.endsWith("- Gruppe")){
563 taxNameString = taxNameString.replaceAll("- Gruppe", "species group");
564 }
565 if(taxNameString.endsWith("- group")){
566 taxNameString = taxNameString.replaceAll("- group", "species group");
567 }
568
569 taxNameString = taxNameString.replace("agg.", "aggr.");
570 taxNameString = taxNameString.replace("[ranglos]", "[unranked]");
571
572 if(taxonBase.getName().getRank()!=null){
573 if(taxonBase.getName().getRank().equals(Rank.PROLES())){
574 taxNameString = taxNameString.replace("proles", "prol.");
575 }
576 else if(taxonBase.getName().getRank().equals(state.getRank(RedListUtil.uuidRankCollectionSpecies))){
577 taxNameString = taxNameString.replace("\"Sammelart\"", "\"Coll. Species\"");
578 }
579 }
580 if(STRICT_TITLE_CHECK){
581 if(!taxNameString.trim().equals(nameCache)){
582 RedListUtil.logMessage(id, "Taxon name inconsistent! taxon.nameCache <-> Column "+RedListUtil.TAXNAME+": "+nameCache+" <-> "+taxNameString, logger);
583 }
584 }
585 else{
586 if(!taxNameString.startsWith(nameCache)){
587 RedListUtil.logMessage(id, "Taxon name inconsistent! taxon.nameCache <-> Column "+RedListUtil.TAXNAME+": "+nameCache+" <-> "+taxNameString, logger);
588 }
589 }
590 }
591
592 private Rank makeRank(long id, RedListGefaesspflanzenImportState state, String rankStr, boolean hasSpecificEpithet) {
593 Rank rank = null;
594 try {
595 if(rankStr.equals("ORA")){
596 //special handling for ORA because of two possibilities
597 if(hasSpecificEpithet){
598 return Rank.UNRANKED_INFRASPECIFIC();
599 }
600 else{
601 return Rank.UNRANKED_INFRAGENERIC();
602 }
603 }
604 else if(rankStr.equals("SAM")){
605 return getRank(state, RedListUtil.uuidRankCollectionSpecies, "Collective Species", "Collective Species", "\"Coll. Species\"", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.SpeciesGroup);
606 }
607 else if(rankStr.equals("SPR")){
608 return getRank(state, RedListUtil.uuidRankSubproles, "Subproles", "Subproles", "subproles", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.Infraspecific);
609 }
610 else if(rankStr.equals("MOD")){
611 return getRank(state, RedListUtil.uuidRankModification, "Modification", "Modification", "modificatio", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.Infraspecific);
612 }
613 else if(rankStr.equals("LUS")){
614 return getRank(state, RedListUtil.uuidRankLusus, "Lusus", "Lusus", "lusus", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.Infraspecific);
615 }
616 else if(rankStr.equals("SPI")){
617 return getRank(state, RedListUtil.uuidRankSubspeciesPrincipes, "Subspecies principes", "Subspecies principes", "subsp. princ.", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.Infraspecific);
618 }
619 else if(rankStr.equals("KMB")){
620 return getRank(state, RedListUtil.uuidRankCombination, "Combination", "Combination", "", (OrderedTermVocabulary<Rank>) Rank.GENUS().getVocabulary(), null, RankClass.Infraspecific);
621 }
622 else{
623 rank = state.getTransformer().getRankByKey(rankStr);
624 }
625 } catch (UndefinedTransformerMethodException e) {
626 e.printStackTrace();
627 }
628 if(rank==null){
629 RedListUtil.logMessage(id, rankStr+" could not be associated to a known rank.", logger);
630 }
631 return rank;
632 }
633
634 private NomenclaturalStatusType makeNomenclaturalStatus(long id, RedListGefaesspflanzenImportState state, String nomZusatzString) {
635 NomenclaturalStatusType status = null;
636 try {
637 status = state.getTransformer().getNomenclaturalStatusByKey(nomZusatzString);
638 } catch (UndefinedTransformerMethodException e) {
639 e.printStackTrace();
640 }
641 if(status==null){
642 RedListUtil.logMessage(id, nomZusatzString+" could not be associated to a known nomenclatural status.", logger);
643 }
644 return status;
645 }
646
647
648
649 @Override
650 public Map<Object, Map<String, ? extends CdmBase>> getRelatedObjectsForPartition(ResultSet rs,
651 RedListGefaesspflanzenImportState state) {
652 Map<Object, Map<String, ? extends CdmBase>> result = new HashMap<>();
653 Map<String, AgentBase<?>> authorMap = new HashMap<String, AgentBase<?>>();
654
655 try {
656 while (rs.next()){
657 String authorKombString = rs.getString(RedListUtil.AUTOR_KOMB);
658
659 if(authorKombString.contains(RedListUtil.EX)){
660 String[] kombSplit = authorKombString.split(RedListUtil.EX);
661 for (int i = 0; i < kombSplit.length; i++) {
662 if(!authorMap.containsKey(kombSplit[i])){
663 authorMap.put(kombSplit[i], getAgentService().load(state.getAuthorMap().get(kombSplit[i])));
664 }
665 }
666 }
667 else if(CdmUtils.isNotBlank(authorKombString) && !authorMap.containsKey(authorKombString)){
668 authorMap.put(authorKombString, getAgentService().load(state.getAuthorMap().get(authorKombString)));
669 }
670
671 String authorBasiString = rs.getString(RedListUtil.AUTOR_BASI);
672 //basionym author
673 if(authorBasiString.contains(RedListUtil.EX)){
674 String[] basiSplit = authorBasiString.split(RedListUtil.EX);
675 for (int i = 0; i < basiSplit.length; i++) {
676 if(!authorMap.containsKey(basiSplit[i])){
677 authorMap.put(basiSplit[i], getAgentService().load(state.getAuthorMap().get(basiSplit[i])));
678 }
679 }
680 }
681 else if(CdmUtils.isNotBlank(authorBasiString) && !authorMap.containsKey(authorBasiString)){
682 authorMap.put(authorBasiString, getAgentService().load(state.getAuthorMap().get(authorBasiString)));
683 }
684 }
685 } catch (SQLException e) {
686 e.printStackTrace();
687 }
688 result.put(RedListUtil.AUTHOR_NAMESPACE, authorMap);
689
690 return result;
691 }
692
693 @Override
694 protected boolean doCheck(RedListGefaesspflanzenImportState state) {
695 return false;
696 }
697
698 @Override
699 protected boolean isIgnore(RedListGefaesspflanzenImportState state) {
700 return false;
701 }
702
703 }