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.iapt;
|
11
|
|
12
|
import eu.etaxonomy.cdm.api.facade.DerivedUnitFacade;
|
13
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
14
|
import eu.etaxonomy.cdm.io.mexico.SimpleExcelTaxonImport;
|
15
|
import eu.etaxonomy.cdm.io.mexico.SimpleExcelTaxonImportState;
|
16
|
import eu.etaxonomy.cdm.model.common.*;
|
17
|
import eu.etaxonomy.cdm.model.name.*;
|
18
|
import eu.etaxonomy.cdm.model.occurrence.DerivedUnit;
|
19
|
import eu.etaxonomy.cdm.model.occurrence.FieldUnit;
|
20
|
import eu.etaxonomy.cdm.model.occurrence.SpecimenOrObservationType;
|
21
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
22
|
import eu.etaxonomy.cdm.model.taxon.*;
|
23
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
24
|
import org.apache.commons.lang.ArrayUtils;
|
25
|
import org.apache.commons.lang.StringEscapeUtils;
|
26
|
import org.apache.commons.lang.StringUtils;
|
27
|
import org.apache.log4j.Level;
|
28
|
import org.apache.log4j.Logger;
|
29
|
import org.springframework.stereotype.Component;
|
30
|
|
31
|
import java.util.*;
|
32
|
import java.util.regex.Matcher;
|
33
|
import java.util.regex.Pattern;
|
34
|
|
35
|
/**
|
36
|
* @author a.mueller
|
37
|
* @created 05.01.2016
|
38
|
*/
|
39
|
|
40
|
@Component("iAPTExcelImport")
|
41
|
public class IAPTExcelImport<CONFIG extends IAPTImportConfigurator> extends SimpleExcelTaxonImport<CONFIG> {
|
42
|
private static final long serialVersionUID = -747486709409732371L;
|
43
|
private static final Logger logger = Logger.getLogger(IAPTExcelImport.class);
|
44
|
public static final String ANNOTATION_MARKER_STRING = "[*]";
|
45
|
|
46
|
|
47
|
private static UUID ROOT_UUID = UUID.fromString("4137fd2a-20f6-4e70-80b9-f296daf51d82");
|
48
|
|
49
|
private static NonViralNameParserImpl nameParser = NonViralNameParserImpl.NewInstance();
|
50
|
|
51
|
private final static String REGISTRATIONNO_PK= "RegistrationNo_Pk";
|
52
|
private final static String HIGHERTAXON= "HigherTaxon";
|
53
|
private final static String FULLNAME= "FullName";
|
54
|
private final static String AUTHORSSPELLING= "AuthorsSpelling";
|
55
|
private final static String LITSTRING= "LitString";
|
56
|
private final static String REGISTRATION= "Registration";
|
57
|
private final static String TYPE= "Type";
|
58
|
private final static String CAVEATS= "Caveats";
|
59
|
private final static String FULLBASIONYM= "FullBasionym";
|
60
|
private final static String FULLSYNSUBST= "FullSynSubst";
|
61
|
private final static String NOTESTXT= "NotesTxt";
|
62
|
private final static String REGDATE= "RegDate";
|
63
|
private final static String NAMESTRING= "NameString";
|
64
|
private final static String BASIONYMSTRING= "BasionymString";
|
65
|
private final static String SYNSUBSTSTR= "SynSubstStr";
|
66
|
private final static String AUTHORSTRING= "AuthorString";
|
67
|
|
68
|
private static List<String> expectedKeys= Arrays.asList(new String[]{
|
69
|
REGISTRATIONNO_PK, HIGHERTAXON, FULLNAME, AUTHORSSPELLING, LITSTRING, REGISTRATION, TYPE, CAVEATS, FULLBASIONYM, FULLSYNSUBST, NOTESTXT, REGDATE, NAMESTRING, BASIONYMSTRING, SYNSUBSTSTR, AUTHORSTRING});
|
70
|
|
71
|
private static final Pattern nomRefTokenizeP = Pattern.compile("^(.*):\\s([^\\.:]+)\\.(.*)$");
|
72
|
private static final Pattern nomRefPubYearExtractP = Pattern.compile("(.*?)(1[7,8,9][0-9]{2}).*$|^.*?[0-9]{1,2}([\\./])[0-1]?[0-9]\\3([0-9]{2})\\.$"); // 1700 - 1999
|
73
|
private static final Pattern typeSplitPattern = Pattern.compile("^(?:\"*[Tt]ype: (?<type>.*?))(?:[Hh]olotype:(?<holotype>.*?))?(?:[Ii]sotype[^:]*:(?<isotype>.*))?$");
|
74
|
enum TypesName {
|
75
|
type, holotype, isotype;
|
76
|
|
77
|
public SpecimenTypeDesignationStatus status(){
|
78
|
switch (this) {
|
79
|
case holotype:
|
80
|
return SpecimenTypeDesignationStatus.HOLOTYPE();
|
81
|
case isotype:
|
82
|
return SpecimenTypeDesignationStatus.ISOTYPE();
|
83
|
default:
|
84
|
return null;
|
85
|
}
|
86
|
}
|
87
|
}
|
88
|
|
89
|
private MarkerType markerTypeFossil = null;
|
90
|
private Rank rankUnrankedSupraGeneric = null;
|
91
|
private Rank familyIncertisSedis = null;
|
92
|
private AnnotationType annotationTypeCaveats = null;
|
93
|
|
94
|
private Taxon makeTaxon(HashMap<String, String> record, SimpleExcelTaxonImportState<CONFIG> state,
|
95
|
TaxonNode higherTaxonNode, boolean isFossil) {
|
96
|
|
97
|
String line = state.getCurrentLine() + ": ";
|
98
|
|
99
|
String titleCacheStr = getValue(record, FULLNAME, true);
|
100
|
String nameStr = getValue(record, NAMESTRING, true);
|
101
|
String authorStr = getValue(record, AUTHORSTRING, true);
|
102
|
String nomRefStr = getValue(record, LITSTRING, true);
|
103
|
String authorsSpelling = getValue(record, AUTHORSSPELLING, true);
|
104
|
String notesTxt = getValue(record, NOTESTXT, true);
|
105
|
String caveats = getValue(record, CAVEATS, true);
|
106
|
String fullSynSubstStr = getValue(record, FULLSYNSUBST, true);
|
107
|
String synSubstStr = getValue(record, SYNSUBSTSTR, true);
|
108
|
String typeStr = getValue(record, TYPE, true);
|
109
|
|
110
|
String nomRefTitle = null;
|
111
|
String nomRefDetail = null;
|
112
|
String nomRefPupDate = null;
|
113
|
String nomRefPupYear = null;
|
114
|
|
115
|
// preprocess nomRef: separate citation, reference detail, publishing date
|
116
|
if(!StringUtils.isEmpty(nomRefStr)){
|
117
|
nomRefStr = nomRefStr.trim();
|
118
|
Matcher m = nomRefTokenizeP.matcher(nomRefStr);
|
119
|
if(m.matches()){
|
120
|
nomRefTitle = m.group(1);
|
121
|
nomRefDetail = m.group(2);
|
122
|
nomRefPupDate = m.group(3);
|
123
|
|
124
|
// nomRefDetail.replaceAll("[\\:\\.\\s]", ""); // TODO integrate into nomRefTokenizeP
|
125
|
Matcher m2 = nomRefPubYearExtractP.matcher(nomRefPupDate);
|
126
|
if(m2.matches()){
|
127
|
nomRefPupYear = m2.group(2);
|
128
|
if(nomRefPupYear == null){
|
129
|
nomRefPupYear = m2.group(4);
|
130
|
}
|
131
|
if(nomRefPupYear == null){
|
132
|
logger.error("nomRefPupYear in " + nomRefStr + " is NULL" );
|
133
|
}
|
134
|
if(nomRefPupYear.length() == 2 ){
|
135
|
// it is an abbreviated year from the 19** years
|
136
|
nomRefPupYear = "19" + nomRefPupYear;
|
137
|
}
|
138
|
nomRefTitle = nomRefTitle + ": " + nomRefDetail + ". " + nomRefPupYear + ".";
|
139
|
} else {
|
140
|
logger.warn("Pub year not found in " + nomRefStr );
|
141
|
// FIXME in in J. Eur. Orchideen 30: 128. 30.09.97 (Vorabdr.).
|
142
|
|
143
|
}
|
144
|
|
145
|
} else {
|
146
|
nomRefTitle = nomRefStr;
|
147
|
}
|
148
|
}
|
149
|
|
150
|
BotanicalName taxonName = makeBotanicalName(state, titleCacheStr, nameStr, authorStr, nomRefTitle);
|
151
|
|
152
|
if(!StringUtils.isEmpty(notesTxt)){
|
153
|
notesTxt = notesTxt.replace("Notes: ", "").trim();
|
154
|
taxonName.addAnnotation(Annotation.NewInstance(notesTxt, AnnotationType.EDITORIAL(), Language.DEFAULT()));
|
155
|
}
|
156
|
if(!StringUtils.isEmpty(caveats)){
|
157
|
caveats = caveats.replace("Caveats: ", "").trim();
|
158
|
taxonName.addAnnotation(Annotation.NewInstance(caveats, annotationTypeCaveats(), Language.DEFAULT()));
|
159
|
}
|
160
|
//
|
161
|
|
162
|
// Namerelations
|
163
|
if(!StringUtils.isEmpty(authorsSpelling)){
|
164
|
authorsSpelling = authorsSpelling.replaceFirst("Author's spelling:", "").replaceAll("\"", "").trim();
|
165
|
|
166
|
String[] authorSpellingTokens = StringUtils.split(authorsSpelling, " ");
|
167
|
String[] nameStrTokens = StringUtils.split(nameStr, " ");
|
168
|
|
169
|
ArrayUtils.reverse(authorSpellingTokens);
|
170
|
ArrayUtils.reverse(nameStrTokens);
|
171
|
|
172
|
for (int i = 0; i < nameStrTokens.length; i++){
|
173
|
if(i < authorSpellingTokens.length){
|
174
|
nameStrTokens[i] = authorSpellingTokens[i];
|
175
|
}
|
176
|
}
|
177
|
ArrayUtils.reverse(nameStrTokens);
|
178
|
|
179
|
String misspelledNameStr = StringUtils.join (nameStrTokens, ' ');
|
180
|
// build the fullnameString of the misspelled name
|
181
|
misspelledNameStr = taxonName.getTitleCache().replace(nameStr, misspelledNameStr);
|
182
|
|
183
|
TaxonNameBase misspelledName = (BotanicalName) nameParser.parseReferencedName(misspelledNameStr, NomenclaturalCode.ICNAFP, null);
|
184
|
misspelledName.addRelationshipToName(taxonName, NameRelationshipType.MISSPELLING(), null);
|
185
|
getNameService().save(misspelledName);
|
186
|
}
|
187
|
|
188
|
// Replaced Synonyms
|
189
|
if(!StringUtils.isEmpty(fullSynSubstStr)){
|
190
|
fullSynSubstStr = fullSynSubstStr.replace("Syn. subst.: ", "");
|
191
|
BotanicalName replacedSynonymName = makeBotanicalName(state, fullSynSubstStr, synSubstStr, null, null);
|
192
|
replacedSynonymName.addReplacedSynonym(taxonName, null, null, null);
|
193
|
getNameService().save(replacedSynonymName);
|
194
|
}
|
195
|
|
196
|
Reference sec = state.getConfig().getSecReference();
|
197
|
Taxon taxon = Taxon.NewInstance(taxonName, sec);
|
198
|
|
199
|
// Markers
|
200
|
if(isFossil){
|
201
|
taxon.addMarker(Marker.NewInstance(markerTypeFossil(), true));
|
202
|
}
|
203
|
|
204
|
// Types
|
205
|
if(!StringUtils.isEmpty(typeStr)){
|
206
|
Matcher m = typeSplitPattern.matcher(typeStr);
|
207
|
|
208
|
if(m.matches()){
|
209
|
String typeString = m.group(TypesName.type.name());
|
210
|
boolean isFieldUnit = typeStr.matches(".*([°']|\\d+\\s?m\\s|\\d+\\s?km\\s).*"); // check for location or unit m, km
|
211
|
|
212
|
if(isFieldUnit) {
|
213
|
// type as fieldUnit
|
214
|
FieldUnit fu = FieldUnit.NewInstance();
|
215
|
fu.setTitleCache(typeString, true);
|
216
|
getOccurrenceService().save(fu);
|
217
|
|
218
|
// all others ..
|
219
|
addSpecimenTypes(taxonName, fu, m.group(TypesName.holotype.name()), TypesName.holotype, false);
|
220
|
addSpecimenTypes(taxonName, fu, m.group(TypesName.isotype.name()), TypesName.isotype, true);
|
221
|
} else {
|
222
|
TaxonNameBase typeName = nameParser.parseFullName(typeString);
|
223
|
taxonName.addNameTypeDesignation(typeName, null, null, null, NameTypeDesignationStatus.AUTOMATIC(), true, true, true, true);
|
224
|
}
|
225
|
}
|
226
|
getNameService().save(taxonName);
|
227
|
|
228
|
}
|
229
|
|
230
|
getTaxonService().save(taxon);
|
231
|
if(higherTaxonNode != null){
|
232
|
higherTaxonNode.addChildTaxon(taxon, null, null);
|
233
|
getTaxonNodeService().save(higherTaxonNode);
|
234
|
}
|
235
|
|
236
|
return taxon;
|
237
|
|
238
|
}
|
239
|
|
240
|
private void addSpecimenTypes(BotanicalName taxonName, FieldUnit fieldUnit, String typeStr, TypesName typeName, boolean multiple){
|
241
|
if(StringUtils.isEmpty(typeStr)){
|
242
|
return;
|
243
|
}
|
244
|
typeStr = typeStr.trim().replaceAll("\\.$", "");
|
245
|
|
246
|
List<String> typeData = new ArrayList<>();
|
247
|
if(multiple){
|
248
|
String[] tokens = typeStr.split("\\s?,\\s?");
|
249
|
for (String t : tokens) {
|
250
|
if(!t.isEmpty()){
|
251
|
typeData.add(t.trim());
|
252
|
}
|
253
|
}
|
254
|
} else {
|
255
|
typeData.add(typeStr.trim());
|
256
|
}
|
257
|
|
258
|
for(String type : typeData){
|
259
|
DerivedUnitFacade facade = DerivedUnitFacade.NewInstance(SpecimenOrObservationType.OtherSpecimen, fieldUnit);
|
260
|
facade.setTitleCache(type, true);
|
261
|
DerivedUnit specimen = facade.innerDerivedUnit();
|
262
|
taxonName.addSpecimenTypeDesignation(specimen, typeName.status(), null, null, null, false, true);
|
263
|
}
|
264
|
}
|
265
|
|
266
|
private BotanicalName makeBotanicalName(SimpleExcelTaxonImportState<CONFIG> state, String titleCacheStr, String nameStr, String authorStr, String nomRefTitle) {
|
267
|
|
268
|
BotanicalName taxonName;// cache field for the taxonName.titleCache
|
269
|
String taxonNameTitleCache = null;
|
270
|
Map<String, AnnotationType> nameAnnotations = new HashMap<>();
|
271
|
|
272
|
String line = state.getCurrentLine() + ": ";
|
273
|
|
274
|
// TitleCache preprocessing
|
275
|
if(titleCacheStr.endsWith(ANNOTATION_MARKER_STRING) || (authorStr != null && authorStr.endsWith(ANNOTATION_MARKER_STRING))){
|
276
|
nameAnnotations.put("Author abbreviation not checked.", AnnotationType.EDITORIAL());
|
277
|
titleCacheStr = titleCacheStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
278
|
authorStr = authorStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
279
|
}
|
280
|
|
281
|
// parse the full taxon name
|
282
|
if(!StringUtils.isEmpty(nomRefTitle)){
|
283
|
String referenceSeparator = nomRefTitle.startsWith("in ") ? " " : ", ";
|
284
|
String taxonFullNameStr = titleCacheStr + referenceSeparator + nomRefTitle;
|
285
|
logger.debug(":::::" + taxonFullNameStr);
|
286
|
taxonName = (BotanicalName) nameParser.parseReferencedName(taxonFullNameStr, NomenclaturalCode.ICNAFP, null);
|
287
|
} else {
|
288
|
taxonName = (BotanicalName) nameParser.parseFullName(titleCacheStr, NomenclaturalCode.ICNAFP, null);
|
289
|
}
|
290
|
|
291
|
taxonNameTitleCache = taxonName.getTitleCache().trim();
|
292
|
if (taxonName.isProtectedTitleCache()) {
|
293
|
logger.warn(line + "Name could not be parsed: " + titleCacheStr);
|
294
|
} else {
|
295
|
|
296
|
boolean doRestoreTitleCacheStr = false;
|
297
|
|
298
|
// Check if titleCache and nameCache are plausible
|
299
|
String titleCacheCompareStr = titleCacheStr;
|
300
|
String nameCache = taxonName.getNameCache();
|
301
|
String nameCompareStr = nameStr;
|
302
|
if(taxonName.isBinomHybrid()){
|
303
|
titleCacheCompareStr = titleCacheCompareStr.replace(" x ", " ×");
|
304
|
nameCompareStr = nameCompareStr.replace(" x ", " ×");
|
305
|
}
|
306
|
if(taxonName.isMonomHybrid()){
|
307
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll("^X ", "× ");
|
308
|
nameCompareStr = nameCompareStr.replace("^X ", "× ");
|
309
|
}
|
310
|
if(authorStr != null && authorStr.contains(" et ")){
|
311
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll(" et ", " & ");
|
312
|
}
|
313
|
if (!taxonNameTitleCache.equals(titleCacheCompareStr)) {
|
314
|
logger.warn(line + "The generated titleCache differs from the imported string : " + taxonNameTitleCache + " <> " + titleCacheStr + " will restore original titleCacheStr");
|
315
|
doRestoreTitleCacheStr = true;
|
316
|
}
|
317
|
if (!nameCache.trim().equals(nameCompareStr)) {
|
318
|
logger.warn(line + "The parsed nameCache differs from " + NAMESTRING + " : " + nameCache + " <> " + nameCompareStr);
|
319
|
}
|
320
|
|
321
|
// Author
|
322
|
//nameParser.handleAuthors(taxonName, titleCacheStr, authorStr);
|
323
|
//if (!titleCacheStr.equals(taxonName.getTitleCache())) {
|
324
|
// logger.warn(line + "titleCache has changed after setting authors, will restore original titleCacheStr");
|
325
|
// doRestoreTitleCacheStr = true;
|
326
|
//}
|
327
|
|
328
|
if(doRestoreTitleCacheStr){
|
329
|
taxonName.setTitleCache(titleCacheStr, true);
|
330
|
}
|
331
|
|
332
|
// deduplicate
|
333
|
replaceAuthorNamesAndNomRef(state, taxonName);
|
334
|
}
|
335
|
|
336
|
// Annotations
|
337
|
if(!nameAnnotations.isEmpty()){
|
338
|
for(String text : nameAnnotations.keySet()){
|
339
|
taxonName.addAnnotation(Annotation.NewInstance(text, nameAnnotations.get(text), Language.DEFAULT()));
|
340
|
}
|
341
|
getNameService().save(taxonName);
|
342
|
}
|
343
|
return taxonName;
|
344
|
}
|
345
|
|
346
|
/**
|
347
|
* @param state
|
348
|
* @return
|
349
|
*/
|
350
|
private TaxonNode getClassificationRootNode(IAPTImportState state) {
|
351
|
|
352
|
// Classification classification = state.getClassification();
|
353
|
// if (classification == null){
|
354
|
// IAPTImportConfigurator config = state.getConfig();
|
355
|
// classification = Classification.NewInstance(state.getConfig().getClassificationName());
|
356
|
// classification.setUuid(config.getClassificationUuid());
|
357
|
// classification.setReference(config.getSecReference());
|
358
|
// classification = getClassificationService().find(state.getConfig().getClassificationUuid());
|
359
|
// }
|
360
|
TaxonNode rootNode = state.getRootNode();
|
361
|
if (rootNode == null){
|
362
|
rootNode = getTaxonNodeService().find(ROOT_UUID);
|
363
|
}
|
364
|
if (rootNode == null){
|
365
|
Classification classification = state.getClassification();
|
366
|
if (classification == null){
|
367
|
Reference sec = state.getSecReference();
|
368
|
String classificationName = state.getConfig().getClassificationName();
|
369
|
Language language = Language.DEFAULT();
|
370
|
classification = Classification.NewInstance(classificationName, sec, language);
|
371
|
state.setClassification(classification);
|
372
|
classification.setUuid(state.getConfig().getClassificationUuid());
|
373
|
classification.getRootNode().setUuid(ROOT_UUID);
|
374
|
getClassificationService().save(classification);
|
375
|
}
|
376
|
rootNode = classification.getRootNode();
|
377
|
state.setRootNode(rootNode);
|
378
|
}
|
379
|
return rootNode;
|
380
|
}
|
381
|
|
382
|
|
383
|
/**
|
384
|
* @param record
|
385
|
* @param originalKey
|
386
|
* @param doUnescapeHtmlEntities
|
387
|
* @return
|
388
|
*/
|
389
|
private String getValue(HashMap<String, String> record, String originalKey, boolean doUnescapeHtmlEntities) {
|
390
|
String value = record.get(originalKey);
|
391
|
|
392
|
value = fixCharacters(value);
|
393
|
|
394
|
if (! StringUtils.isBlank(value)) {
|
395
|
if (logger.isDebugEnabled()) {
|
396
|
logger.debug(originalKey + ": " + value);
|
397
|
}
|
398
|
value = CdmUtils.removeDuplicateWhitespace(value.trim()).toString();
|
399
|
if(doUnescapeHtmlEntities){
|
400
|
value = StringEscapeUtils.unescapeHtml(value);
|
401
|
}
|
402
|
return value.trim();
|
403
|
}else{
|
404
|
return null;
|
405
|
}
|
406
|
}
|
407
|
|
408
|
/**
|
409
|
* Fixes broken characters.
|
410
|
* For details see
|
411
|
* http://dev.e-taxonomy.eu/redmine/issues/6035
|
412
|
*
|
413
|
* @param value
|
414
|
* @return
|
415
|
*/
|
416
|
private String fixCharacters(String value) {
|
417
|
|
418
|
value = StringUtils.replace(value, "s$K", "š");
|
419
|
value = StringUtils.replace(value, "n$K", "ň");
|
420
|
value = StringUtils.replace(value, "e$K", "ě");
|
421
|
value = StringUtils.replace(value, "r$K", "ř");
|
422
|
value = StringUtils.replace(value, "c$K", "č");
|
423
|
value = StringUtils.replace(value, "z$K", "ž");
|
424
|
value = StringUtils.replace(value, "S>U$K", "Š");
|
425
|
value = StringUtils.replace(value, "C>U$K", "Č");
|
426
|
value = StringUtils.replace(value, "R>U$K", "Ř");
|
427
|
value = StringUtils.replace(value, "Z>U$K", "Ž");
|
428
|
value = StringUtils.replace(value, "g$K", "ǧ");
|
429
|
value = StringUtils.replace(value, "s$A", "ś");
|
430
|
value = StringUtils.replace(value, "n$A", "ń");
|
431
|
value = StringUtils.replace(value, "c$A", "ć");
|
432
|
value = StringUtils.replace(value, "e$E", "ę");
|
433
|
value = StringUtils.replace(value, "o$H", "õ");
|
434
|
value = StringUtils.replace(value, "s$C", "ş");
|
435
|
value = StringUtils.replace(value, "t$C", "ț");
|
436
|
value = StringUtils.replace(value, "S>U$C", "Ş");
|
437
|
value = StringUtils.replace(value, "a$O", "å");
|
438
|
value = StringUtils.replace(value, "A>U$O", "Å");
|
439
|
value = StringUtils.replace(value, "u$O", "ů");
|
440
|
value = StringUtils.replace(value, "g$B", "ğ");
|
441
|
value = StringUtils.replace(value, "g$B", "ĕ");
|
442
|
value = StringUtils.replace(value, "a$B", "ă");
|
443
|
value = StringUtils.replace(value, "l$/", "ł");
|
444
|
value = StringUtils.replace(value, ">i", "ı");
|
445
|
value = StringUtils.replace(value, "i$U", "ï");
|
446
|
// Special-cases
|
447
|
value = StringUtils.replace(value, "ý", "ý");
|
448
|
value = StringUtils.replace(value, "<L", "Ł");
|
449
|
value = StringUtils.replace(value, "E>U$D", "З");
|
450
|
value = StringUtils.replace(value, "S>U$E", "Ş");
|
451
|
value = StringUtils.replace(value, "s$E", "ş");
|
452
|
|
453
|
return value;
|
454
|
}
|
455
|
|
456
|
|
457
|
/**
|
458
|
* Stores taxa records in DB
|
459
|
*/
|
460
|
@Override
|
461
|
protected void firstPass(SimpleExcelTaxonImportState<CONFIG> state) {
|
462
|
|
463
|
String lineNumber = state.getCurrentLine() + ": ";
|
464
|
logger.setLevel(Level.DEBUG);
|
465
|
HashMap<String, String> record = state.getOriginalRecord();
|
466
|
logger.debug(lineNumber + record.toString());
|
467
|
|
468
|
Set<String> keys = record.keySet();
|
469
|
for (String key: keys) {
|
470
|
if (! expectedKeys.contains(key)){
|
471
|
logger.warn(lineNumber + "Unexpected Key: " + key);
|
472
|
}
|
473
|
}
|
474
|
|
475
|
String reg_id = record.get(REGISTRATIONNO_PK);
|
476
|
|
477
|
//higherTaxon
|
478
|
String higherTaxaString = record.get(HIGHERTAXON);
|
479
|
boolean isFossil = false;
|
480
|
if(higherTaxaString.startsWith("FOSSIL ")){
|
481
|
higherTaxaString = higherTaxaString.replace("FOSSIL ", "");
|
482
|
isFossil = true;
|
483
|
}
|
484
|
TaxonNode higherTaxon = getHigherTaxon(higherTaxaString, (IAPTImportState)state);
|
485
|
|
486
|
//Taxon
|
487
|
Taxon taxon = makeTaxon(record, state, higherTaxon, isFossil);
|
488
|
if (taxon == null){
|
489
|
logger.warn(lineNumber + "taxon could not be created and is null");
|
490
|
return;
|
491
|
}
|
492
|
((IAPTImportState)state).setCurrentTaxon(taxon);
|
493
|
|
494
|
|
495
|
return;
|
496
|
}
|
497
|
|
498
|
private TaxonNode getHigherTaxon(String higherTaxaString, IAPTImportState state) {
|
499
|
String[] higherTaxaNames = higherTaxaString.toLowerCase().replaceAll("[\\[\\]]", "").split(":");
|
500
|
TaxonNode higherTaxonNode = null;
|
501
|
|
502
|
ITaxonTreeNode rootNode = getClassificationRootNode(state);
|
503
|
for (String htn : higherTaxaNames) {
|
504
|
htn = StringUtils.capitalize(htn.trim());
|
505
|
Taxon higherTaxon = state.getHigherTaxon(htn);
|
506
|
if (higherTaxon != null){
|
507
|
higherTaxonNode = higherTaxon.getTaxonNodes().iterator().next();
|
508
|
}else{
|
509
|
BotanicalName name = makeHigherTaxonName(state, htn);
|
510
|
Reference sec = state.getSecReference();
|
511
|
higherTaxon = Taxon.NewInstance(name, sec);
|
512
|
getTaxonService().save(higherTaxon);
|
513
|
higherTaxonNode = rootNode.addChildTaxon(higherTaxon, sec, null);
|
514
|
state.putHigherTaxon(htn, higherTaxon);
|
515
|
getClassificationService().saveTreeNode(higherTaxonNode);
|
516
|
}
|
517
|
rootNode = higherTaxonNode;
|
518
|
}
|
519
|
return higherTaxonNode;
|
520
|
}
|
521
|
|
522
|
private BotanicalName makeHigherTaxonName(IAPTImportState state, String name) {
|
523
|
|
524
|
Rank rank = guessRank(name);
|
525
|
|
526
|
BotanicalName taxonName = BotanicalName.NewInstance(rank);
|
527
|
taxonName.addSource(makeOriginalSource(state));
|
528
|
taxonName.setGenusOrUninomial(StringUtils.capitalize(name));
|
529
|
return taxonName;
|
530
|
}
|
531
|
|
532
|
private Rank guessRank(String name) {
|
533
|
|
534
|
// normalize
|
535
|
name = name.replaceAll("\\(.*\\)", "").trim();
|
536
|
|
537
|
if(name.matches("^Plantae$|^Fungi$")){
|
538
|
return Rank.KINGDOM();
|
539
|
} else if(name.matches("^Incertae sedis$|^No group assigned$")){
|
540
|
return rankFamilyIncertisSedis();
|
541
|
} else if(name.matches(".*phyta$|.*mycota$")){
|
542
|
return Rank.SECTION_BOTANY();
|
543
|
} else if(name.matches(".*phytina$|.*mycotina$")){
|
544
|
return Rank.SUBSECTION_BOTANY();
|
545
|
} else if(name.matches("Gymnospermae$|.*ones$")){ // Monocotyledones, Dicotyledones
|
546
|
return rankUnrankedSupraGeneric();
|
547
|
} else if(name.matches(".*opsida$|.*phyceae$|.*mycetes$|.*ones$|^Musci$|^Hepaticae$")){
|
548
|
return Rank.CLASS();
|
549
|
} else if(name.matches(".*idae$|.*phycidae$|.*mycetidae$")){
|
550
|
return Rank.SUBCLASS();
|
551
|
} else if(name.matches(".*ales$")){
|
552
|
return Rank.ORDER();
|
553
|
} else if(name.matches(".*ineae$")){
|
554
|
return Rank.SUBORDER();
|
555
|
} else if(name.matches(".*aceae$")){
|
556
|
return Rank.FAMILY();
|
557
|
} else if(name.matches(".*oideae$")){
|
558
|
return Rank.SUBFAMILY();
|
559
|
} else
|
560
|
// if(name.matches(".*eae$")){
|
561
|
// return Rank.TRIBE();
|
562
|
// } else
|
563
|
if(name.matches(".*inae$")){
|
564
|
return Rank.SUBTRIBE();
|
565
|
} else if(name.matches(".*ae$")){
|
566
|
return Rank.FAMILY();
|
567
|
}
|
568
|
return Rank.UNKNOWN_RANK();
|
569
|
}
|
570
|
|
571
|
private Rank rankUnrankedSupraGeneric() {
|
572
|
|
573
|
if(rankUnrankedSupraGeneric == null){
|
574
|
rankUnrankedSupraGeneric = Rank.NewInstance(RankClass.Suprageneric, "Unranked supra generic", " ", " ");
|
575
|
getTermService().save(rankUnrankedSupraGeneric);
|
576
|
}
|
577
|
return rankUnrankedSupraGeneric;
|
578
|
}
|
579
|
|
580
|
private Rank rankFamilyIncertisSedis() {
|
581
|
|
582
|
if(familyIncertisSedis == null){
|
583
|
familyIncertisSedis = Rank.NewInstance(RankClass.Suprageneric, "Family incertis sedis", " ", " ");
|
584
|
getTermService().save(familyIncertisSedis);
|
585
|
}
|
586
|
return familyIncertisSedis;
|
587
|
}
|
588
|
|
589
|
private AnnotationType annotationTypeCaveats(){
|
590
|
if(annotationTypeCaveats == null){
|
591
|
annotationTypeCaveats = AnnotationType.NewInstance("Caveats", "Caveats", "");
|
592
|
getTermService().save(annotationTypeCaveats);
|
593
|
}
|
594
|
return annotationTypeCaveats;
|
595
|
}
|
596
|
|
597
|
|
598
|
/**
|
599
|
* @param state
|
600
|
* @return
|
601
|
*/
|
602
|
private IdentifiableSource makeOriginalSource(IAPTImportState state) {
|
603
|
return IdentifiableSource.NewDataImportInstance("line: " + state.getCurrentLine(), null, state.getConfig().getSourceReference());
|
604
|
}
|
605
|
|
606
|
|
607
|
private Reference makeReference(IAPTImportState state, UUID uuidRef) {
|
608
|
Reference ref = state.getReference(uuidRef);
|
609
|
if (ref == null){
|
610
|
ref = getReferenceService().find(uuidRef);
|
611
|
state.putReference(uuidRef, ref);
|
612
|
}
|
613
|
return ref;
|
614
|
}
|
615
|
|
616
|
private MarkerType markerTypeFossil(){
|
617
|
if(this.markerTypeFossil == null){
|
618
|
markerTypeFossil = MarkerType.NewInstance("isFossilTaxon", "isFossil", null);
|
619
|
getTermService().save(this.markerTypeFossil);
|
620
|
}
|
621
|
return markerTypeFossil;
|
622
|
}
|
623
|
|
624
|
|
625
|
}
|