|
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
|
package eu.etaxonomy.cdm.strategy.cache.name;
|
|
10
|
|
|
11
|
import java.util.ArrayList;
|
|
12
|
import java.util.List;
|
|
13
|
import java.util.UUID;
|
|
14
|
import java.util.regex.Matcher;
|
|
15
|
import java.util.regex.Pattern;
|
|
16
|
|
|
17
|
import org.apache.logging.log4j.LogManager;import org.apache.logging.log4j.Logger;
|
|
18
|
|
|
19
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
|
20
|
import eu.etaxonomy.cdm.common.UTF8;
|
|
21
|
import eu.etaxonomy.cdm.model.agent.INomenclaturalAuthor;
|
|
22
|
import eu.etaxonomy.cdm.model.name.HybridRelationship;
|
|
23
|
import eu.etaxonomy.cdm.model.name.INonViralName;
|
|
24
|
import eu.etaxonomy.cdm.model.name.Rank;
|
|
25
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
|
26
|
import eu.etaxonomy.cdm.strategy.cache.TagEnum;
|
|
27
|
import eu.etaxonomy.cdm.strategy.cache.TaggedText;
|
|
28
|
import eu.etaxonomy.cdm.strategy.cache.TaggedTextBuilder;
|
|
29
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
|
30
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImplRegExBase;
|
|
31
|
|
|
32
|
|
|
33
|
/**
|
|
34
|
* This class is a default implementation for the INonViralNameCacheStrategy<T extends NonViralName>
|
|
35
|
* interface.<BR>
|
|
36
|
* The method implements a cache strategy for botanical names so no method has to be overwritten by
|
|
37
|
* a subclass for botanic names.
|
|
38
|
* Where differing from this default botanic name strategy other subclasses should overwrite the
|
|
39
|
* existing methods, e.g. a CacheStrategy for zoological names should overwrite getAuthorAndExAuthor
|
|
40
|
* @author a.mueller
|
|
41
|
*/
|
|
42
|
public class TaxonNameDefaultCacheStrategy
|
|
43
|
extends NameCacheStrategyBase
|
|
44
|
implements INonViralNameCacheStrategy {
|
|
45
|
|
|
46
|
private static final Logger logger = LogManager.getLogger(TaxonNameDefaultCacheStrategy.class);
|
|
47
|
private static final long serialVersionUID = -6577757501563212669L;
|
|
48
|
|
|
49
|
final static UUID uuid = UUID.fromString("1cdda0d1-d5bc-480f-bf08-40a510a2f223");
|
|
50
|
|
|
51
|
protected String nameAuthorSeperator = " ";
|
|
52
|
protected String basionymStart = "(";
|
|
53
|
protected String basionymEnd = ")";
|
|
54
|
protected String exAuthorSeperator = " ex ";
|
|
55
|
private static String NOTHO = "notho";
|
|
56
|
protected CharSequence basionymAuthorCombinationAuthorSeperator = " ";
|
|
57
|
|
|
58
|
protected String zooAuthorYearSeperator = ", ";
|
|
59
|
|
|
60
|
private String cultivarStart = "'";
|
|
61
|
private String cultivarEnd = "'";
|
|
62
|
|
|
63
|
@Override
|
|
64
|
public UUID getUuid(){
|
|
65
|
return uuid;
|
|
66
|
}
|
|
67
|
|
|
68
|
// ************************** FACTORY ******************************/
|
|
69
|
|
|
70
|
public static TaxonNameDefaultCacheStrategy NewInstance(){
|
|
71
|
return new TaxonNameDefaultCacheStrategy();
|
|
72
|
}
|
|
73
|
|
|
74
|
|
|
75
|
// ************ CONSTRUCTOR *******************/
|
|
76
|
|
|
77
|
protected TaxonNameDefaultCacheStrategy(){
|
|
78
|
super();
|
|
79
|
}
|
|
80
|
|
|
81
|
/* **************** GETTER / SETTER **************************************/
|
|
82
|
|
|
83
|
/**
|
|
84
|
* String that separates the NameCache part from the AuthorCache part
|
|
85
|
* @return
|
|
86
|
*/
|
|
87
|
public String getNameAuthorSeperator() {
|
|
88
|
return nameAuthorSeperator;
|
|
89
|
}
|
|
90
|
public void setNameAuthorSeperator(String nameAuthorSeperator) {
|
|
91
|
this.nameAuthorSeperator = nameAuthorSeperator;
|
|
92
|
}
|
|
93
|
|
|
94
|
|
|
95
|
/**
|
|
96
|
* String the basionym author part starts with e.g. '('.
|
|
97
|
* This should correspond with the {@link TaxonNameDefaultCacheStrategy#getBasionymEnd() basionymEnd} attribute
|
|
98
|
* @return
|
|
99
|
*/
|
|
100
|
public String getBasionymStart() {
|
|
101
|
return basionymStart;
|
|
102
|
}
|
|
103
|
public void setBasionymStart(String basionymStart) {
|
|
104
|
this.basionymStart = basionymStart;
|
|
105
|
}
|
|
106
|
|
|
107
|
/**
|
|
108
|
* String the basionym author part ends with e.g. ')'.
|
|
109
|
* This should correspond with the {@link TaxonNameDefaultCacheStrategy#getBasionymStart() basionymStart} attribute
|
|
110
|
* @return
|
|
111
|
*/
|
|
112
|
public String getBasionymEnd() {
|
|
113
|
return basionymEnd;
|
|
114
|
}
|
|
115
|
public void setBasionymEnd(String basionymEnd) {
|
|
116
|
this.basionymEnd = basionymEnd;
|
|
117
|
}
|
|
118
|
|
|
119
|
|
|
120
|
/**
|
|
121
|
* String to separate ex author from author.
|
|
122
|
* @return
|
|
123
|
*/
|
|
124
|
public String getExAuthorSeperator() {
|
|
125
|
return exAuthorSeperator;
|
|
126
|
}
|
|
127
|
public void setExAuthorSeperator(String exAuthorSeperator) {
|
|
128
|
this.exAuthorSeperator = exAuthorSeperator;
|
|
129
|
}
|
|
130
|
|
|
131
|
|
|
132
|
/**
|
|
133
|
* String that separates the basionym/original_combination author part from the combination author part
|
|
134
|
* @return
|
|
135
|
*/
|
|
136
|
public CharSequence getBasionymAuthorCombinationAuthorSeperator() {
|
|
137
|
return basionymAuthorCombinationAuthorSeperator;
|
|
138
|
}
|
|
139
|
|
|
140
|
|
|
141
|
public void setBasionymAuthorCombinationAuthorSeperator( CharSequence basionymAuthorCombinationAuthorSeperator) {
|
|
142
|
this.basionymAuthorCombinationAuthorSeperator = basionymAuthorCombinationAuthorSeperator;
|
|
143
|
}
|
|
144
|
|
|
145
|
public String getZooAuthorYearSeperator() {
|
|
146
|
return zooAuthorYearSeperator;
|
|
147
|
}
|
|
148
|
public void setZooAuthorYearSeperator(String authorYearSeperator) {
|
|
149
|
this.zooAuthorYearSeperator = authorYearSeperator;
|
|
150
|
}
|
|
151
|
|
|
152
|
// ******************* Authorship ******************************/
|
|
153
|
|
|
154
|
@Override
|
|
155
|
public String getAuthorshipCache(TaxonName taxonName) {
|
|
156
|
if (taxonName == null){
|
|
157
|
return null;
|
|
158
|
}else if (taxonName.isViral()){
|
|
159
|
return null;
|
|
160
|
}else if(taxonName.isProtectedAuthorshipCache() == true) {
|
|
161
|
//cache protected
|
|
162
|
return taxonName.getAuthorshipCache();
|
|
163
|
}else{
|
|
164
|
return getNonCacheAuthorshipCache(taxonName);
|
|
165
|
}
|
|
166
|
}
|
|
167
|
|
|
168
|
/**
|
|
169
|
* Returns the authorshipcache string for the atomized authorship fields. Does not use the authorship field.
|
|
170
|
* @throws NullPointerException if nonViralName is null.
|
|
171
|
* @param taxonName
|
|
172
|
* @return
|
|
173
|
*/
|
|
174
|
protected String getNonCacheAuthorshipCache(TaxonName nonViralName){
|
|
175
|
if (nonViralName.getNameType().isZoological()){
|
|
176
|
return this.getZoologicalNonCacheAuthorshipCache(nonViralName);
|
|
177
|
}else{
|
|
178
|
String result = "";
|
|
179
|
INomenclaturalAuthor combinationAuthor = nonViralName.getCombinationAuthorship();
|
|
180
|
INomenclaturalAuthor exCombinationAuthor = nonViralName.getExCombinationAuthorship();
|
|
181
|
INomenclaturalAuthor basionymAuthor = nonViralName.getBasionymAuthorship();
|
|
182
|
INomenclaturalAuthor exBasionymAuthor = nonViralName.getExBasionymAuthorship();
|
|
183
|
if (isCultivar(nonViralName) ){
|
|
184
|
exCombinationAuthor = null;
|
|
185
|
basionymAuthor = null;
|
|
186
|
exBasionymAuthor = null;
|
|
187
|
}
|
|
188
|
|
|
189
|
String basionymPart = "";
|
|
190
|
String authorPart = "";
|
|
191
|
//basionym
|
|
192
|
if (basionymAuthor != null || exBasionymAuthor != null){
|
|
193
|
basionymPart = basionymStart + getAuthorAndExAuthor(basionymAuthor, exBasionymAuthor) + basionymEnd;
|
|
194
|
}
|
|
195
|
if (combinationAuthor != null || exCombinationAuthor != null){
|
|
196
|
authorPart = getAuthorAndExAuthor(combinationAuthor, exCombinationAuthor);
|
|
197
|
}
|
|
198
|
result = CdmUtils.concat(basionymAuthorCombinationAuthorSeperator, basionymPart, authorPart);
|
|
199
|
// if ("".equals(result)){
|
|
200
|
// result = null;
|
|
201
|
// }
|
|
202
|
return result;
|
|
203
|
}
|
|
204
|
}
|
|
205
|
|
|
206
|
private boolean isCultivar(TaxonName name) {
|
|
207
|
return name.isCultivar() || isNotBlank(name.getCultivarEpithet()) || isNotBlank(name.getCultivarGroupEpithet());
|
|
208
|
}
|
|
209
|
|
|
210
|
protected String getZoologicalNonCacheAuthorshipCache(TaxonName nonViralName) {
|
|
211
|
if (nonViralName == null){
|
|
212
|
return null;
|
|
213
|
}
|
|
214
|
String result = "";
|
|
215
|
INomenclaturalAuthor combinationAuthor = nonViralName.getCombinationAuthorship();
|
|
216
|
INomenclaturalAuthor exCombinationAuthor = nonViralName.getExCombinationAuthorship();
|
|
217
|
INomenclaturalAuthor basionymAuthor = nonViralName.getBasionymAuthorship();
|
|
218
|
INomenclaturalAuthor exBasionymAuthor = nonViralName.getExBasionymAuthorship();
|
|
219
|
Integer publicationYear = nonViralName.getPublicationYear();
|
|
220
|
Integer originalPublicationYear = nonViralName.getOriginalPublicationYear();
|
|
221
|
|
|
222
|
String basionymPart = "";
|
|
223
|
String authorPart = "";
|
|
224
|
//basionym
|
|
225
|
if (basionymAuthor != null || exBasionymAuthor != null || originalPublicationYear != null ){
|
|
226
|
String authorAndEx = getAuthorAndExAuthor(basionymAuthor, exBasionymAuthor);
|
|
227
|
String originalPublicationYearString = originalPublicationYear == null ? null : String.valueOf(originalPublicationYear);
|
|
228
|
String authorAndExAndYear = CdmUtils.concat(zooAuthorYearSeperator, authorAndEx, originalPublicationYearString );
|
|
229
|
basionymPart = basionymStart + authorAndExAndYear + basionymEnd;
|
|
230
|
}
|
|
231
|
if (combinationAuthor != null || exCombinationAuthor != null){
|
|
232
|
String authorAndEx = getAuthorAndExAuthor(combinationAuthor, exCombinationAuthor);
|
|
233
|
String publicationYearString = publicationYear == null ? null : String.valueOf(publicationYear);
|
|
234
|
authorPart = CdmUtils.concat(zooAuthorYearSeperator, authorAndEx, publicationYearString);
|
|
235
|
}
|
|
236
|
result = CdmUtils.concat(basionymAuthorCombinationAuthorSeperator, basionymPart, authorPart);
|
|
237
|
if (result == null){
|
|
238
|
result = "";
|
|
239
|
}
|
|
240
|
return result;
|
|
241
|
}
|
|
242
|
|
|
243
|
|
|
244
|
/**
|
|
245
|
* Returns the AuthorCache part for a combination of an author and an ex author. This applies on
|
|
246
|
* combination authors as well as on basionym/orginal combination authors.
|
|
247
|
* The correct order is exAuthor ex author though some botanist do not know about and do it the
|
|
248
|
* other way round. (see 46.4-46.6 ICBN (Vienna Code, 2006))
|
|
249
|
*/
|
|
250
|
protected String getAuthorAndExAuthor(INomenclaturalAuthor author, INomenclaturalAuthor exAuthor){
|
|
251
|
String authorString = "";
|
|
252
|
String exAuthorString = "";
|
|
253
|
if (author != null){
|
|
254
|
authorString = getNomAuthorTitle(author);
|
|
255
|
}
|
|
256
|
if (exAuthor != null){
|
|
257
|
exAuthorString = getNomAuthorTitle(exAuthor);
|
|
258
|
exAuthorString += exAuthorSeperator;
|
|
259
|
}
|
|
260
|
String result = exAuthorString + authorString;
|
|
261
|
return result;
|
|
262
|
}
|
|
263
|
|
|
264
|
private String getNomAuthorTitle(INomenclaturalAuthor author) {
|
|
265
|
return CdmUtils.Nz(author.getNomenclaturalTitleCache());
|
|
266
|
}
|
|
267
|
|
|
268
|
/**
|
|
269
|
* Checks if the given name should include the author in it's cached version.<BR>
|
|
270
|
* This is usually the case but not for <i>species aggregates</i>.
|
|
271
|
* @param nonViralName
|
|
272
|
* @return
|
|
273
|
*/
|
|
274
|
protected boolean nameIncludesAuthorship(INonViralName nonViralName){
|
|
275
|
Rank rank = nonViralName.getRank();
|
|
276
|
if (rank != null && rank.isSpeciesAggregate()){
|
|
277
|
return false;
|
|
278
|
}else{
|
|
279
|
return true;
|
|
280
|
}
|
|
281
|
}
|
|
282
|
|
|
283
|
// ************* TAGGED NAME ***************************************/
|
|
284
|
|
|
285
|
@Override
|
|
286
|
protected List<TaggedText> doGetTaggedTitle(TaxonName taxonName) {
|
|
287
|
List<TaggedText> tags = new ArrayList<>();
|
|
288
|
if (taxonName.getNameType().isViral()){
|
|
289
|
String acronym = taxonName.getAcronym();
|
|
290
|
if (isNotBlank(taxonName.getAcronym())){
|
|
291
|
//this is not according to the code
|
|
292
|
tags.add(new TaggedText(TagEnum.name, acronym));
|
|
293
|
}
|
|
294
|
return tags;
|
|
295
|
}else if (taxonName.isHybridFormula()){
|
|
296
|
//hybrid formula
|
|
297
|
String hybridSeparator = NonViralNameParserImplRegExBase.hybridSign;
|
|
298
|
boolean isFirst = true;
|
|
299
|
List<HybridRelationship> rels = taxonName.getOrderedChildRelationships();
|
|
300
|
for (HybridRelationship rel: rels){
|
|
301
|
if (! isFirst){
|
|
302
|
tags.add(new TaggedText(TagEnum.hybridSign, hybridSeparator));
|
|
303
|
}
|
|
304
|
isFirst = false;
|
|
305
|
tags.addAll(getTaggedTitle(rel.getParentName()));
|
|
306
|
}
|
|
307
|
return tags;
|
|
308
|
}else if (taxonName.isAutonym()){
|
|
309
|
//Autonym
|
|
310
|
tags.addAll(handleTaggedAutonym(taxonName, true));
|
|
311
|
}else{ //not Autonym
|
|
312
|
List<TaggedText> nameTags = getTaggedName(taxonName);
|
|
313
|
tags.addAll(nameTags);
|
|
314
|
String authorCache = getAuthorshipCache(taxonName);
|
|
315
|
if (isNotBlank(authorCache)){
|
|
316
|
tags.add(new TaggedText(TagEnum.authors, authorCache));
|
|
317
|
}
|
|
318
|
}
|
|
319
|
return tags;
|
|
320
|
}
|
|
321
|
|
|
322
|
/**
|
|
323
|
* Returns the tag list of the name part (without author and reference).
|
|
324
|
* @param taxonName
|
|
325
|
* @return
|
|
326
|
*/
|
|
327
|
@Override
|
|
328
|
public List<TaggedText> getTaggedName(TaxonName taxonName) {
|
|
329
|
if (taxonName == null){
|
|
330
|
return null;
|
|
331
|
}else if (taxonName.isViral()){
|
|
332
|
return null;
|
|
333
|
}
|
|
334
|
List<TaggedText> tags = new ArrayList<>();
|
|
335
|
Rank rank = taxonName.getRank();
|
|
336
|
|
|
337
|
if (taxonName.isProtectedNameCache()){
|
|
338
|
tags.add(new TaggedText(TagEnum.name, taxonName.getNameCache()));
|
|
339
|
}else if (taxonName.isHybridFormula()){
|
|
340
|
//hybrid formula
|
|
341
|
//TODO graft-chimera (see also cultivars)
|
|
342
|
String hybridSeparator = NonViralNameParserImplRegExBase.hybridSign;
|
|
343
|
boolean isFirst = true;
|
|
344
|
List<HybridRelationship> rels = taxonName.getOrderedChildRelationships();
|
|
345
|
for (HybridRelationship rel: rels){
|
|
346
|
if (! isFirst){
|
|
347
|
tags.add(new TaggedText(TagEnum.hybridSign, hybridSeparator));
|
|
348
|
}
|
|
349
|
isFirst = false;
|
|
350
|
tags.addAll(getTaggedName(rel.getParentName()));
|
|
351
|
}
|
|
352
|
return tags;
|
|
353
|
|
|
354
|
}else if (rank == null){
|
|
355
|
tags = getRanklessTaggedNameCache(taxonName, true);
|
|
356
|
}else if (rank.isCultivar()){
|
|
357
|
tags = getCultivarTaggedNameCache(taxonName);
|
|
358
|
}else if (rank.isInfraSpecific()){
|
|
359
|
tags = getInfraSpeciesTaggedNameCache(taxonName);
|
|
360
|
}else if (rank.isSpecies() || isAggregateWithAuthorship(taxonName, rank) ){ //exception see #4288
|
|
361
|
tags = getSpeciesTaggedNameCache(taxonName, true);
|
|
362
|
}else if (rank.isInfraGeneric()){
|
|
363
|
tags = getInfraGenusTaggedNameCache(taxonName, true);
|
|
364
|
}else if (rank.isGenus()){
|
|
365
|
tags = getGenusOrUninomialTaggedNameCache(taxonName, true);
|
|
366
|
}else if (rank.isSupraGeneric()){
|
|
367
|
tags = getGenusOrUninomialTaggedNameCache(taxonName, true);
|
|
368
|
}else{
|
|
369
|
tags = getRanklessTaggedNameCache(taxonName, true);
|
|
370
|
logger.warn("Rank does not belong to a rank class: " + rank.getTitleCache() + ". Used rankless nameCache for name " + taxonName.getUuid());
|
|
371
|
}
|
|
372
|
//TODO handle appended phrase here instead of different places, check first if this is true for all
|
|
373
|
//cases
|
|
374
|
|
|
375
|
return tags;
|
|
376
|
}
|
|
377
|
|
|
378
|
//***************************** PRIVATES ***************************************/
|
|
379
|
|
|
380
|
private List<TaggedText> getCultivarTaggedNameCache(TaxonName taxonName) {
|
|
381
|
List<TaggedText> scientificNameTags;
|
|
382
|
TaggedTextBuilder builder = TaggedTextBuilder.NewInstance();
|
|
383
|
if (isNotBlank(taxonName.getInfraSpecificEpithet())){
|
|
384
|
scientificNameTags = getInfraSpeciesTaggedNameCache(taxonName, false, false);
|
|
385
|
} else if (isNotBlank(taxonName.getSpecificEpithet())){
|
|
386
|
scientificNameTags = getSpeciesTaggedNameCache(taxonName, false);
|
|
387
|
} else if (isNotBlank(taxonName.getInfraGenericEpithet())){
|
|
388
|
scientificNameTags = getInfraGenusTaggedNameCache(taxonName, false);
|
|
389
|
} else /*if (isNotBlank(taxonName.getGenusOrUninomial())) */{
|
|
390
|
scientificNameTags = getGenusOrUninomialTaggedNameCache(taxonName, false);
|
|
391
|
}
|
|
392
|
|
|
393
|
UUID rankUuid = taxonName.getRank().getUuid();
|
|
394
|
boolean rankIsHandled = true;
|
|
395
|
String cultivarStr = null;
|
|
396
|
String groupStr = taxonName.getCultivarGroupEpithet();
|
|
397
|
if (rankUuid.equals(Rank.uuidCultivar)){
|
|
398
|
cultivarStr = surroundedCultivarEpithet(taxonName.getCultivarEpithet());
|
|
399
|
if (isNotBlank(cultivarStr) && isNotBlank(groupStr)){
|
|
400
|
groupStr = surroundGroupWithBracket(groupStr);
|
|
401
|
}
|
|
402
|
cultivarStr = CdmUtils.concat(" ", groupStr, cultivarStr);
|
|
403
|
}else if (rankUuid.equals(Rank.uuidCultivarGroup)){
|
|
404
|
cultivarStr = CdmUtils.concat(" ", groupStr, checkHasGroupEpithet(groupStr)? null: "Group");
|
|
405
|
}else if (rankUuid.equals(Rank.uuidGrexICNCP)){
|
|
406
|
cultivarStr = CdmUtils.concat(" ", groupStr, checkHasGrexEpithet(groupStr)? null: "grex");
|
|
407
|
}else{
|
|
408
|
rankIsHandled = false;
|
|
409
|
}
|
|
410
|
if (rankIsHandled){
|
|
411
|
builder.addAll(scientificNameTags);
|
|
412
|
}else if (rankUuid.equals(Rank.uuidGraftChimaera)){
|
|
413
|
//TODO not yet fully implemented
|
|
414
|
cultivarStr = "+ " + CdmUtils.concat(" ", taxonName.getGenusOrUninomial(), surroundedCultivarEpithet(taxonName.getCultivarEpithet()));
|
|
415
|
}else if (rankUuid.equals(Rank.uuidDenominationClass)){
|
|
416
|
//TODO dummy implementation
|
|
417
|
cultivarStr = CdmUtils.concat(" ", taxonName.getGenusOrUninomial(), surroundedCultivarEpithet(taxonName.getCultivarEpithet()));
|
|
418
|
} else { //(!rankIsHandled)
|
|
419
|
throw new IllegalStateException("Unsupported rank " + taxonName.getRank().getTitleCache() + " for cultivar.");
|
|
420
|
}
|
|
421
|
if (isNotBlank(cultivarStr)){
|
|
422
|
builder.add(TagEnum.cultivar, cultivarStr);
|
|
423
|
}
|
|
424
|
|
|
425
|
List<TaggedText> tags = builder.getTaggedText();
|
|
426
|
addAppendedTaggedPhrase(tags, taxonName, true);
|
|
427
|
return tags;
|
|
428
|
}
|
|
429
|
|
|
430
|
private String surroundGroupWithBracket(String groupStr) {
|
|
431
|
if (groupStr.matches(NonViralNameParserImplRegExBase.grex + "$")){
|
|
432
|
return groupStr;
|
|
433
|
}else if (groupStr.matches(".*" + NonViralNameParserImplRegExBase.grex + ".+")){
|
|
434
|
Matcher matcher = Pattern.compile(NonViralNameParserImplRegExBase.grex + "\\s*" ).matcher(groupStr);
|
|
435
|
matcher.find();
|
|
436
|
return groupStr.substring(0, matcher.end()) + "("+ groupStr.substring(matcher.end())+ ")";
|
|
437
|
}else{
|
|
438
|
return "("+ groupStr + ")";
|
|
439
|
}
|
|
440
|
}
|
|
441
|
|
|
442
|
private boolean checkHasGroupEpithet(String group) {
|
|
443
|
|
|
444
|
String[] splits = group == null? new String[0]: group.split("\\s+");
|
|
445
|
if (splits.length <= 1){
|
|
446
|
return false;
|
|
447
|
}else if (splits[0].matches(NonViralNameParserImplRegExBase.group)
|
|
448
|
|| splits[splits.length-1].matches(NonViralNameParserImplRegExBase.group)){
|
|
449
|
return true;
|
|
450
|
}else{
|
|
451
|
return false;
|
|
452
|
}
|
|
453
|
}
|
|
454
|
|
|
455
|
private boolean checkHasGrexEpithet(String grex) {
|
|
456
|
String[] splits = grex == null? new String[0]: grex.split("\\s+");
|
|
457
|
if (splits.length <= 1){
|
|
458
|
return false;
|
|
459
|
}else if (splits[splits.length-1].matches(NonViralNameParserImplRegExBase.grex)){
|
|
460
|
return true;
|
|
461
|
}else{
|
|
462
|
return false;
|
|
463
|
}
|
|
464
|
}
|
|
465
|
|
|
466
|
private String surroundedCultivarEpithet(String cultivarEpi) {
|
|
467
|
return cultivarStart + CdmUtils.Nz(cultivarEpi) + cultivarEnd;
|
|
468
|
}
|
|
469
|
|
|
470
|
private boolean isAggregateWithAuthorship(TaxonName nonViralName, Rank rank) {
|
|
471
|
if (rank == null){
|
|
472
|
return false;
|
|
473
|
}else{
|
|
474
|
return rank.isSpeciesAggregate() && ( isNotBlank(nonViralName.getAuthorshipCache()) || nonViralName.getNomenclaturalReference() != null );
|
|
475
|
}
|
|
476
|
}
|
|
477
|
|
|
478
|
/**
|
|
479
|
* Returns the tag list for an autonym taxon.
|
|
480
|
*
|
|
481
|
* @see NonViralName#isAutonym()
|
|
482
|
* @see BotanicalName#isAutonym()
|
|
483
|
* @param nonViralName
|
|
484
|
* @return
|
|
485
|
*/
|
|
486
|
private List<TaggedText> handleTaggedAutonym(TaxonName nonViralName, boolean addAppended) {
|
|
487
|
List<TaggedText> tags = null;
|
|
488
|
if (nonViralName.isInfraSpecific()){
|
|
489
|
//species part
|
|
490
|
tags = getSpeciesTaggedNameCache(nonViralName, addAppended);
|
|
491
|
|
|
492
|
//author
|
|
493
|
String authorCache = getAuthorshipCache(nonViralName);
|
|
494
|
if (isNotBlank(authorCache)){
|
|
495
|
tags.add(new TaggedText(TagEnum.authors, authorCache));
|
|
496
|
}
|
|
497
|
|
|
498
|
//infra species marker
|
|
499
|
if (nonViralName.getRank() == null || !nonViralName.getRank().isInfraSpecific()){
|
|
500
|
//TODO handle exception
|
|
501
|
logger.warn("Rank for autonym does not exist or is not lower than species !!");
|
|
502
|
}else{
|
|
503
|
String infraSpeciesMarker = nonViralName.getRank().getAbbreviation();
|
|
504
|
if (nonViralName.isTrinomHybrid()){
|
|
505
|
infraSpeciesMarker = CdmUtils.concat("", NOTHO, infraSpeciesMarker);
|
|
506
|
}
|
|
507
|
if (isNotBlank(infraSpeciesMarker)){
|
|
508
|
tags.add(new TaggedText(TagEnum.rank, infraSpeciesMarker));
|
|
509
|
}
|
|
510
|
}
|
|
511
|
|
|
512
|
//infra species
|
|
513
|
String infraSpeciesPart = CdmUtils.Nz(nonViralName.getInfraSpecificEpithet()).trim();
|
|
514
|
if (isNotBlank(infraSpeciesPart)){
|
|
515
|
tags.add(new TaggedText(TagEnum.name, infraSpeciesPart));
|
|
516
|
}
|
|
517
|
|
|
518
|
} else if (nonViralName.isInfraGeneric()){
|
|
519
|
//genus part
|
|
520
|
tags =getGenusOrUninomialTaggedNameCache(nonViralName, addAppended);
|
|
521
|
|
|
522
|
//author
|
|
523
|
String authorCache = getAuthorshipCache(nonViralName);
|
|
524
|
if (isNotBlank(authorCache)){
|
|
525
|
tags.add(new TaggedText(TagEnum.authors, authorCache));
|
|
526
|
}
|
|
527
|
|
|
528
|
//infra species marker
|
|
529
|
if (nonViralName.getRank() == null || !nonViralName.getRank().isInfraGeneric()){
|
|
530
|
//TODO handle exception
|
|
531
|
logger.warn("Rank for autonym does not exist or is not lower than species !!");
|
|
532
|
}else{
|
|
533
|
Rank rank = nonViralName.getRank();
|
|
534
|
String infraGenericMarker = rank.getAbbreviation();
|
|
535
|
if (rank.equals(Rank.SECTION_BOTANY()) || rank.equals(Rank.SUBSECTION_BOTANY())){
|
|
536
|
infraGenericMarker = infraGenericMarker.replace("(bot.)", "");
|
|
537
|
}
|
|
538
|
if (isNotBlank(infraGenericMarker)){
|
|
539
|
tags.add(new TaggedText(TagEnum.rank, infraGenericMarker));
|
|
540
|
}
|
|
541
|
}
|
|
542
|
|
|
543
|
//infra genus
|
|
544
|
String infraGenericPart = CdmUtils.Nz(nonViralName.getInfraGenericEpithet()).trim();
|
|
545
|
if (isNotBlank(infraGenericPart)){
|
|
546
|
tags.add(new TaggedText(TagEnum.name, infraGenericPart));
|
|
547
|
}
|
|
548
|
}
|
|
549
|
|
|
550
|
return tags;
|
|
551
|
}
|
|
552
|
|
|
553
|
|
|
554
|
|
|
555
|
/**
|
|
556
|
* Returns the tag list for rankless taxa.
|
|
557
|
* @param nonViralName
|
|
558
|
* @return
|
|
559
|
*/
|
|
560
|
protected List<TaggedText> getRanklessTaggedNameCache(INonViralName nonViralName, boolean addAppended){
|
|
561
|
List<TaggedText> tags = getUninomialTaggedPart(nonViralName);
|
|
562
|
String speciesEpi = CdmUtils.Nz(nonViralName.getSpecificEpithet()).trim();
|
|
563
|
if (isNotBlank(speciesEpi)){
|
|
564
|
tags.add(new TaggedText(TagEnum.name, speciesEpi));
|
|
565
|
}
|
|
566
|
|
|
567
|
String infraSpeciesEpi = CdmUtils.Nz(nonViralName.getInfraSpecificEpithet());
|
|
568
|
if (isNotBlank(infraSpeciesEpi)){
|
|
569
|
tags.add(new TaggedText(TagEnum.name, infraSpeciesEpi));
|
|
570
|
}
|
|
571
|
|
|
572
|
//result += " (rankless)";
|
|
573
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
574
|
return tags;
|
|
575
|
}
|
|
576
|
|
|
577
|
/**
|
|
578
|
* Returns the tag list for the first epithet (including a hybrid sign if required).
|
|
579
|
* @param nonViralName
|
|
580
|
* @return
|
|
581
|
*/
|
|
582
|
private List<TaggedText> getUninomialTaggedPart(INonViralName nonViralName) {
|
|
583
|
List<TaggedText> tags = new ArrayList<>();
|
|
584
|
|
|
585
|
if (nonViralName.isMonomHybrid()){
|
|
586
|
addHybridPrefix(tags);
|
|
587
|
}
|
|
588
|
|
|
589
|
String uninomial = CdmUtils.Nz(nonViralName.getGenusOrUninomial()).trim();
|
|
590
|
if (isNotBlank(uninomial)){
|
|
591
|
tags.add(new TaggedText(TagEnum.name, uninomial));
|
|
592
|
}
|
|
593
|
|
|
594
|
return tags;
|
|
595
|
}
|
|
596
|
|
|
597
|
/**
|
|
598
|
* Returns the tag list for an genus or higher taxon.
|
|
599
|
*
|
|
600
|
* @param nonViralName
|
|
601
|
* @return
|
|
602
|
*/
|
|
603
|
protected List<TaggedText> getGenusOrUninomialTaggedNameCache(INonViralName nonViralName, boolean addAppended){
|
|
604
|
List<TaggedText> tags = getUninomialTaggedPart(nonViralName);
|
|
605
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
606
|
return tags;
|
|
607
|
}
|
|
608
|
|
|
609
|
/**
|
|
610
|
* Returns the tag list for an infrageneric taxon (including species aggregates).
|
|
611
|
*
|
|
612
|
* @see #getSpeciesAggregateTaggedCache(NonViralName)
|
|
613
|
* @param nonViralName
|
|
614
|
* @return
|
|
615
|
*/
|
|
616
|
protected List<TaggedText> getInfraGenusTaggedNameCache(INonViralName nonViralName, boolean addAppended){
|
|
617
|
Rank rank = nonViralName.getRank();
|
|
618
|
if (rank != null && rank.isSpeciesAggregate() && isBlank(nonViralName.getAuthorshipCache())){
|
|
619
|
return getSpeciesAggregateTaggedCache(nonViralName, addAppended);
|
|
620
|
}
|
|
621
|
|
|
622
|
//genus
|
|
623
|
List<TaggedText> tags = getUninomialTaggedPart(nonViralName);
|
|
624
|
|
|
625
|
//marker
|
|
626
|
String infraGenericMarker;
|
|
627
|
if (rank != null){
|
|
628
|
try {
|
|
629
|
infraGenericMarker = rank.getInfraGenericMarker();
|
|
630
|
if (rank.equals(Rank.SECTION_BOTANY()) || rank.equals(Rank.SUBSECTION_BOTANY())){
|
|
631
|
infraGenericMarker = infraGenericMarker.replace("(bot.)", "");
|
|
632
|
}
|
|
633
|
} catch (UnknownCdmTypeException e) {
|
|
634
|
infraGenericMarker = "'unhandled infrageneric rank'";
|
|
635
|
}
|
|
636
|
}else{
|
|
637
|
infraGenericMarker = "'undefined infrageneric rank'";
|
|
638
|
}
|
|
639
|
String infraGenEpi = CdmUtils.Nz(nonViralName.getInfraGenericEpithet()).trim();
|
|
640
|
if (nonViralName.isBinomHybrid()){
|
|
641
|
infraGenericMarker = CdmUtils.concat("", NOTHO, infraGenericMarker);
|
|
642
|
}
|
|
643
|
|
|
644
|
addInfraGenericPart(nonViralName, tags, infraGenericMarker, infraGenEpi);
|
|
645
|
|
|
646
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
647
|
return tags;
|
|
648
|
}
|
|
649
|
|
|
650
|
|
|
651
|
/**
|
|
652
|
* Default implementation for the infrageneric part of a name.
|
|
653
|
* This is usually the infrageneric marker and the infrageneric epitheton. But may be
|
|
654
|
* implemented differently e.g. for zoological names the infrageneric epitheton
|
|
655
|
* may be surrounded by brackets and the marker left out.
|
|
656
|
* @param nonViralName
|
|
657
|
* @param tags
|
|
658
|
* @param infraGenericMarker
|
|
659
|
*/
|
|
660
|
protected void addInfraGenericPart(
|
|
661
|
@SuppressWarnings("unused") INonViralName name,
|
|
662
|
List<TaggedText> tags,
|
|
663
|
String infraGenericMarker,
|
|
664
|
String infraGenEpi) {
|
|
665
|
//add marker
|
|
666
|
tags.add(new TaggedText(TagEnum.rank, infraGenericMarker));
|
|
667
|
|
|
668
|
//add epitheton
|
|
669
|
if (isNotBlank(infraGenEpi)){
|
|
670
|
tags.add(new TaggedText(TagEnum.name, infraGenEpi));
|
|
671
|
}
|
|
672
|
}
|
|
673
|
|
|
674
|
/**
|
|
675
|
* Returns the tag list for a species aggregate (or similar) taxon.<BR>
|
|
676
|
* Possible ranks for a <i>species aggregate</i> are "aggr.", "species group", ...
|
|
677
|
* @param nonViralName
|
|
678
|
* @return
|
|
679
|
*/
|
|
680
|
protected List<TaggedText> getSpeciesAggregateTaggedCache(INonViralName nonViralName, boolean addAppended){
|
|
681
|
if (! isBlank(nonViralName.getAuthorshipCache())){
|
|
682
|
List<TaggedText> result = getSpeciesTaggedNameCache(nonViralName, addAppended);
|
|
683
|
return result;
|
|
684
|
}
|
|
685
|
|
|
686
|
List<TaggedText> tags = getGenusAndSpeciesTaggedPart(nonViralName);
|
|
687
|
|
|
688
|
addSpeciesAggregateTaggedEpithet(tags, nonViralName);
|
|
689
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
690
|
return tags;
|
|
691
|
}
|
|
692
|
|
|
693
|
/**
|
|
694
|
* Adds the aggregate tag to the tag list.
|
|
695
|
*/
|
|
696
|
private void addSpeciesAggregateTaggedEpithet(List<TaggedText> tags, INonViralName nonViralName) {
|
|
697
|
String marker;
|
|
698
|
try {
|
|
699
|
marker = nonViralName.getRank().getInfraGenericMarker();
|
|
700
|
} catch (UnknownCdmTypeException e) {
|
|
701
|
marker = "'unknown aggregat type'";
|
|
702
|
}
|
|
703
|
if (isNotBlank(marker)){
|
|
704
|
tags.add(new TaggedText(TagEnum.rank, marker));
|
|
705
|
}
|
|
706
|
}
|
|
707
|
|
|
708
|
/**
|
|
709
|
* Returns the tag list for a species taxon.
|
|
710
|
*/
|
|
711
|
protected List<TaggedText> getSpeciesTaggedNameCache(INonViralName nonViralName, boolean addAppended){
|
|
712
|
List<TaggedText> tags = getGenusAndSpeciesTaggedPart(nonViralName);
|
|
713
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
714
|
return tags;
|
|
715
|
}
|
|
716
|
|
|
717
|
protected List<TaggedText> getInfraSpeciesTaggedNameCache(TaxonName name){
|
|
718
|
if (name.getNameType().isZoological()){
|
|
719
|
boolean includeMarker = includeInfraSpecificMarkerForZooNames(name);
|
|
720
|
return getInfraSpeciesTaggedNameCache(name, includeMarker, true);
|
|
721
|
}else{
|
|
722
|
return getInfraSpeciesTaggedNameCache(name, true, true);
|
|
723
|
}
|
|
724
|
}
|
|
725
|
|
|
726
|
protected boolean includeInfraSpecificMarkerForZooNames(TaxonName name){
|
|
727
|
return ! (name.isAutonym()); //only exclude marker if autonym, see also ZooNameNoMarkerCacheStrategy
|
|
728
|
}
|
|
729
|
|
|
730
|
/**
|
|
731
|
* Creates the tag list for an infraspecific taxon. If include is true the result will contain
|
|
732
|
* the infraspecific marker (e.g. "var.")
|
|
733
|
* @param nonViralName
|
|
734
|
* @param includeMarker
|
|
735
|
* @return
|
|
736
|
*/
|
|
737
|
protected List<TaggedText> getInfraSpeciesTaggedNameCache(INonViralName nonViralName,
|
|
738
|
boolean includeMarker, boolean addAppended){
|
|
739
|
List<TaggedText> tags = getGenusAndSpeciesTaggedPart(nonViralName);
|
|
740
|
if (includeMarker || nonViralName.isTrinomHybrid()){
|
|
741
|
String marker = (nonViralName.getRank().getAbbreviation()).trim().replace("null", "");
|
|
742
|
if (nonViralName.isTrinomHybrid()){
|
|
743
|
marker = CdmUtils.concat("", NOTHO, marker);
|
|
744
|
}
|
|
745
|
if (isNotBlank(marker)){
|
|
746
|
tags.add(new TaggedText(TagEnum.rank, marker));
|
|
747
|
}
|
|
748
|
|
|
749
|
}
|
|
750
|
String infrSpecEpi = CdmUtils.Nz(nonViralName.getInfraSpecificEpithet());
|
|
751
|
|
|
752
|
infrSpecEpi = infrSpecEpi.trim().replace("null", "");
|
|
753
|
|
|
754
|
if (isNotBlank(infrSpecEpi)){
|
|
755
|
tags.add(new TaggedText(TagEnum.name, infrSpecEpi));
|
|
756
|
}
|
|
757
|
|
|
758
|
addAppendedTaggedPhrase(tags, nonViralName, addAppended);
|
|
759
|
return tags;
|
|
760
|
}
|
|
761
|
|
|
762
|
|
|
763
|
/**
|
|
764
|
* Adds a tag for the hybrid sign and an empty separator to avoid trailing whitespaces.
|
|
765
|
* @param tags
|
|
766
|
*/
|
|
767
|
private void addHybridPrefix(List<TaggedText> tags) {
|
|
768
|
tags.add(new TaggedText(TagEnum.hybridSign, NonViralNameParserImplRegExBase.hybridSign));
|
|
769
|
tags.add(new TaggedText(TagEnum.separator, "")); //no whitespace separator
|
|
770
|
}
|
|
771
|
|
|
772
|
/**
|
|
773
|
* Creates the tag list for the genus and species part.
|
|
774
|
* @param nonViralName
|
|
775
|
* @return
|
|
776
|
*/
|
|
777
|
private List<TaggedText> getGenusAndSpeciesTaggedPart(INonViralName nonViralName) {
|
|
778
|
//Uninomial
|
|
779
|
List<TaggedText> tags = getUninomialTaggedPart(nonViralName);
|
|
780
|
|
|
781
|
//InfraGenericEpi
|
|
782
|
boolean hasInfraGenericEpi = isNotBlank(nonViralName.getInfraGenericEpithet());
|
|
783
|
if (hasInfraGenericEpi){
|
|
784
|
String infrGenEpi = nonViralName.getInfraGenericEpithet().trim();
|
|
785
|
if (nonViralName.isBinomHybrid()){
|
|
786
|
//maybe not correct but not really expected to happen
|
|
787
|
infrGenEpi = UTF8.HYBRID + infrGenEpi;
|
|
788
|
}
|
|
789
|
infrGenEpi = "(" + infrGenEpi + ")";
|
|
790
|
tags.add(new TaggedText(TagEnum.name, infrGenEpi));
|
|
791
|
}
|
|
792
|
|
|
793
|
//Species Epi
|
|
794
|
String specEpi = CdmUtils.Nz(nonViralName.getSpecificEpithet()).trim();
|
|
795
|
if (! hasInfraGenericEpi && nonViralName.isBinomHybrid() ||
|
|
796
|
hasInfraGenericEpi && nonViralName.isTrinomHybrid()){
|
|
797
|
addHybridPrefix(tags);
|
|
798
|
}
|
|
799
|
if (isNotBlank(specEpi)){
|
|
800
|
tags.add(new TaggedText(TagEnum.name, specEpi));
|
|
801
|
}
|
|
802
|
return tags;
|
|
803
|
}
|
|
804
|
|
|
805
|
/**
|
|
806
|
* Adds the tag for the appended phrase if an appended phrase exists
|
|
807
|
* @param tags
|
|
808
|
* @param nonViralName
|
|
809
|
* @param addAppended
|
|
810
|
*/
|
|
811
|
protected void addAppendedTaggedPhrase(List<TaggedText> tags, INonViralName nonViralName, boolean addAppended){
|
|
812
|
if (!addAppended){
|
|
813
|
return;
|
|
814
|
}
|
|
815
|
String appendedPhrase = nonViralName ==null ? null : nonViralName.getAppendedPhrase();
|
|
816
|
if (isNotBlank(appendedPhrase)){
|
|
817
|
tags.add(new TaggedText(TagEnum.name, appendedPhrase));
|
|
818
|
}
|
|
819
|
}
|
|
820
|
|
|
821
|
@Override
|
|
822
|
public String getLastEpithet(TaxonName taxonName) {
|
|
823
|
Rank rank = taxonName.getRank();
|
|
824
|
if(rank.isGenus() || rank.isSupraGeneric()) {
|
|
825
|
return taxonName.getGenusOrUninomial();
|
|
826
|
} else if(rank.isInfraGeneric()) {
|
|
827
|
return taxonName.getInfraGenericEpithet();
|
|
828
|
} else if(rank.isSpecies()) {
|
|
829
|
return taxonName.getSpecificEpithet();
|
|
830
|
} else {
|
|
831
|
return taxonName.getInfraSpecificEpithet();
|
|
832
|
}
|
|
833
|
}
|
|
834
|
|
|
835
|
|
|
836
|
}
|