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.agent.Institution;
|
17
|
import eu.etaxonomy.cdm.model.agent.Person;
|
18
|
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
|
19
|
import eu.etaxonomy.cdm.model.common.*;
|
20
|
import eu.etaxonomy.cdm.model.name.*;
|
21
|
import eu.etaxonomy.cdm.model.occurrence.*;
|
22
|
import eu.etaxonomy.cdm.model.occurrence.Collection;
|
23
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
24
|
import eu.etaxonomy.cdm.model.taxon.*;
|
25
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
26
|
import org.apache.commons.lang.ArrayUtils;
|
27
|
import org.apache.commons.lang.StringEscapeUtils;
|
28
|
import org.apache.commons.lang.StringUtils;
|
29
|
import org.apache.log4j.Level;
|
30
|
import org.apache.log4j.Logger;
|
31
|
import org.joda.time.DateTimeFieldType;
|
32
|
import org.joda.time.Partial;
|
33
|
import org.joda.time.format.DateTimeFormat;
|
34
|
import org.joda.time.format.DateTimeFormatter;
|
35
|
import org.springframework.stereotype.Component;
|
36
|
|
37
|
import java.util.*;
|
38
|
import java.util.regex.Matcher;
|
39
|
import java.util.regex.Pattern;
|
40
|
|
41
|
/**
|
42
|
* @author a.mueller
|
43
|
* @created 05.01.2016
|
44
|
*/
|
45
|
|
46
|
@Component("iAPTExcelImport")
|
47
|
public class IAPTExcelImport<CONFIG extends IAPTImportConfigurator> extends SimpleExcelTaxonImport<CONFIG> {
|
48
|
private static final long serialVersionUID = -747486709409732371L;
|
49
|
private static final Logger logger = Logger.getLogger(IAPTExcelImport.class);
|
50
|
public static final String ANNOTATION_MARKER_STRING = "[*]";
|
51
|
|
52
|
|
53
|
private static UUID ROOT_UUID = UUID.fromString("4137fd2a-20f6-4e70-80b9-f296daf51d82");
|
54
|
|
55
|
private static NonViralNameParserImpl nameParser = NonViralNameParserImpl.NewInstance();
|
56
|
|
57
|
private final static String REGISTRATIONNO_PK= "RegistrationNo_Pk";
|
58
|
private final static String HIGHERTAXON= "HigherTaxon";
|
59
|
private final static String FULLNAME= "FullName";
|
60
|
private final static String AUTHORSSPELLING= "AuthorsSpelling";
|
61
|
private final static String LITSTRING= "LitString";
|
62
|
private final static String REGISTRATION= "Registration";
|
63
|
private final static String TYPE= "Type";
|
64
|
private final static String CAVEATS= "Caveats";
|
65
|
private final static String FULLBASIONYM= "FullBasionym";
|
66
|
private final static String FULLSYNSUBST= "FullSynSubst";
|
67
|
private final static String NOTESTXT= "NotesTxt";
|
68
|
private final static String REGDATE= "RegDate";
|
69
|
private final static String NAMESTRING= "NameString";
|
70
|
private final static String BASIONYMSTRING= "BasionymString";
|
71
|
private final static String SYNSUBSTSTR= "SynSubstStr";
|
72
|
private final static String AUTHORSTRING= "AuthorString";
|
73
|
|
74
|
private static List<String> expectedKeys= Arrays.asList(new String[]{
|
75
|
REGISTRATIONNO_PK, HIGHERTAXON, FULLNAME, AUTHORSSPELLING, LITSTRING, REGISTRATION, TYPE, CAVEATS, FULLBASIONYM, FULLSYNSUBST, NOTESTXT, REGDATE, NAMESTRING, BASIONYMSTRING, SYNSUBSTSTR, AUTHORSTRING});
|
76
|
|
77
|
private static final Pattern nomRefTokenizeP = Pattern.compile("^(.*):\\s([^\\.:]+)\\.(.*?)\\.?$");
|
78
|
private static final Pattern[] datePatterns = new Pattern[]{
|
79
|
// NOTE:
|
80
|
// The order of the patterns is extremely important!!!
|
81
|
//
|
82
|
// all patterns cover the years 1700 - 1999
|
83
|
Pattern.compile("^(?<year>1[7,8,9][0-9]{2})$"), // only year, like '1969'
|
84
|
Pattern.compile("^(?<monthName>\\p{L}+\\.?)\\s(?<day>[0-9]{1,2})(?:st|rd|th)?\\.?,?\\s(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like April 12, 1969 or april 12th 1999
|
85
|
Pattern.compile("^(?<monthName>\\p{L}+\\.?),?\\s?(?<year>(?:1[7,8,9])?[0-9]{2})$"), // April 99 or April, 1999 or Apr. 12
|
86
|
Pattern.compile("^(?<day>[0-9]{1,2})([\\.\\-/])(\\s?)(?<month>[0-1]?[0-9])\\2\\3(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like 12.04.1969 or 12. 04. 1969 or 12/04/1969 or 12-04-1969
|
87
|
Pattern.compile("^(?<day>[0-9]{1,2})([\\.\\-/])(?<month>[IVX]{1,2})\\2(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like 12-VI-1969
|
88
|
Pattern.compile("^(?:(?<day>[0-9]{1,2})(?:\\sde)\\s)(?<monthName>\\p{L}+)\\sde\\s(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full and partial date like 12 de Enero de 1999 or Enero de 1999
|
89
|
Pattern.compile("^(?<month>[0-1]?[0-9])([\\.\\-/])(?<year>(?:1[7,8,9])?[0-9]{2})$"), // partial date like 04.1969 or 04/1969 or 04-1969
|
90
|
Pattern.compile("^(?<year>(?:1[7,8,9])?[0-9]{2})([\\.\\-/])(?<month>[0-1]?[0-9])$"),// partial date like 1999-04
|
91
|
Pattern.compile("^(?<month>[IVX]{1,2})([\\.\\-/])(?<year>(?:1[7,8,9])?[0-9]{2})$"), // partial date like VI-1969
|
92
|
Pattern.compile("^(?<day>[0-9]{1,2})(?:[\\./]|th|rd|st)?\\s(?<monthName>\\p{L}+\\.?),?\\s?(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like 12. April 1969 or april 1999 or 22 Dec.1999
|
93
|
};
|
94
|
private static final Pattern typeSplitPattern = Pattern.compile("^(?:\"*[Tt]ype: (?<fieldUnit>.*?))(?:[Hh]olotype:(?<holotype>.*?)\\.?)?(?:[Ii]sotype[^:]*:(?<isotype>.*)\\.?)?\\.?$");
|
95
|
|
96
|
private static final Pattern collectorPattern = Pattern.compile(".*?\\(leg\\.\\s+([^\\)]*)\\)|.*?\\sleg\\.\\s+(.*?)\\.?$");
|
97
|
private static final Pattern collectionDataPattern = Pattern.compile("^(?<collector>[^,]*),\\s?(?<detail>.*?)\\.?$");
|
98
|
private static final Pattern collectorsNumber = Pattern.compile("^([nN]o\\.\\s.*)$");
|
99
|
|
100
|
// AccessionNumbers: , #.*, n°:?, 96/3293, No..*, -?\w{1,3}-[0-9\-/]*
|
101
|
private static final Pattern accessionNumberOnlyPattern = Pattern.compile("^(?<accNumber>(?:n°\\:?\\s?|#|No\\.?\\s?)?[\\d\\w\\-/]*)$");
|
102
|
|
103
|
private static final Pattern[] specimenTypePatterns = new Pattern[]{
|
104
|
Pattern.compile("^(?<colCode>[A-Z]+|CPC Micropaleontology Lab\\.?)\\s+(?:\\((?<institute>.*[^\\)])\\))(?<accNumber>.*)?$"), // like: GAUF (Gansu Agricultural University) No. 1207-1222
|
105
|
Pattern.compile("^(?<colCode>[A-Z]+|CPC Micropaleontology Lab\\.?)\\s+(?:Coll\\.\\s(?<subCollection>[^\\.,;]*)(.))(?<accNumber>.*)?$"), // like KASSEL Coll. Krasske, Praep. DII 78
|
106
|
Pattern.compile("^(?:Coll\\.\\s(?<subCollection>[^\\.,;]*)(.))(?<institute>.*?)(?<accNumber>Praep\\..*)?$"), // like Coll. Lange-Bertalot, Bot. Inst., Univ. Frankfurt/Main, Germany Praep. Neukaledonien OTL 62
|
107
|
Pattern.compile("^(?<colCode>[A-Z]+)(?:\\s+(?<accNumber>.*))?$"), // identifies the Collection code and takes the rest as accessionNumber if any
|
108
|
};
|
109
|
|
110
|
private static Map<String, Integer> monthFromNameMap = new HashMap<>();
|
111
|
|
112
|
static {
|
113
|
String[] ck = new String[]{"leden", "únor", "březen", "duben", "květen", "červen", "červenec ", "srpen", "září", "říjen", "listopad", "prosinec"};
|
114
|
String[] fr = new String[]{"janvier", "février", "mars", "avril", "mai", "juin", "juillet", "août", "septembre", "octobre", "novembre", "décembre"};
|
115
|
String[] de = new String[]{"januar", "februar", "märz", "april", "mai", "juni", "juli", "august", "september", "oktober", "november", "dezember"};
|
116
|
String[] en = new String[]{"january", "february", "march", "april", "may", "june", "july", "august", "september", "october", "november", "december"};
|
117
|
String[] it = new String[]{"gennaio", "febbraio", "marzo", "aprile", "maggio", "giugno", "luglio", "agosto", "settembre", "ottobre", "novembre", "dicembre"};
|
118
|
String[] sp = new String[]{"enero", "febrero", "marzo", "abril", "mayo", "junio", "julio", "agosto", "septiembre", "octubre", "noviembre", "diciembre"};
|
119
|
String[] de_abbrev = new String[]{"jan.", "feb.", "märz", "apr.", "mai", "jun.", "jul.", "aug.", "sept.", "okt.", "nov.", "dez."};
|
120
|
String[] en_abbrev = new String[]{"jan.", "feb.", "mar.", "apr.", "may", "jun.", "jul.", "aug.", "sep.", "oct.", "nov.", "dec."};
|
121
|
String[] port = new String[]{"Janeiro", "Fevereiro", "Março", "Abril", "Maio", "Junho", "Julho", "Agosto", "Setembro", "Outubro", "Novembro", "Dezembro"};
|
122
|
String[] rom_num = new String[]{"i", "ii", "iii", "iv", "v", "vi", "vii", "viii", "ix", "x", "xi", "xii"};
|
123
|
|
124
|
String[][] perLang = new String[][]{ck, de, fr, en, it, sp, port, de_abbrev, en_abbrev, rom_num};
|
125
|
|
126
|
for (String[] months: perLang) {
|
127
|
for(int m = 1; m < 13; m++){
|
128
|
monthFromNameMap.put(months[m - 1].toLowerCase(), m);
|
129
|
}
|
130
|
}
|
131
|
|
132
|
// special cases
|
133
|
monthFromNameMap.put("mar", 3);
|
134
|
monthFromNameMap.put("dec", 12);
|
135
|
monthFromNameMap.put("Februari", 2);
|
136
|
}
|
137
|
|
138
|
|
139
|
DateTimeFormatter formatterYear = DateTimeFormat.forPattern("yyyy");
|
140
|
|
141
|
private Map<String, Collection> collectionMap = new HashMap<>();
|
142
|
|
143
|
|
144
|
enum TypesName {
|
145
|
fieldUnit, holotype, isotype;
|
146
|
|
147
|
public SpecimenTypeDesignationStatus status(){
|
148
|
switch (this) {
|
149
|
case holotype:
|
150
|
return SpecimenTypeDesignationStatus.HOLOTYPE();
|
151
|
case isotype:
|
152
|
return SpecimenTypeDesignationStatus.ISOTYPE();
|
153
|
default:
|
154
|
return null;
|
155
|
}
|
156
|
}
|
157
|
}
|
158
|
|
159
|
private MarkerType markerTypeFossil = null;
|
160
|
private Rank rankUnrankedSupraGeneric = null;
|
161
|
private Rank familyIncertisSedis = null;
|
162
|
private AnnotationType annotationTypeCaveats = null;
|
163
|
|
164
|
private Taxon makeTaxon(HashMap<String, String> record, SimpleExcelTaxonImportState<CONFIG> state,
|
165
|
TaxonNode higherTaxonNode, boolean isFossil) {
|
166
|
|
167
|
String line = state.getCurrentLine() + ": ";
|
168
|
|
169
|
String regNumber = getValue(record, REGISTRATIONNO_PK, false);
|
170
|
String regStr = getValue(record, REGISTRATION, true);
|
171
|
String titleCacheStr = getValue(record, FULLNAME, true);
|
172
|
String nameStr = getValue(record, NAMESTRING, true);
|
173
|
String authorStr = getValue(record, AUTHORSTRING, true);
|
174
|
String nomRefStr = getValue(record, LITSTRING, true);
|
175
|
String authorsSpelling = getValue(record, AUTHORSSPELLING, true);
|
176
|
String notesTxt = getValue(record, NOTESTXT, true);
|
177
|
String caveats = getValue(record, CAVEATS, true);
|
178
|
String fullSynSubstStr = getValue(record, FULLSYNSUBST, true);
|
179
|
String synSubstStr = getValue(record, SYNSUBSTSTR, true);
|
180
|
String typeStr = getValue(record, TYPE, true);
|
181
|
|
182
|
|
183
|
String nomRefTitle = null;
|
184
|
String nomRefDetail;
|
185
|
String nomRefPupDate = null;
|
186
|
Partial pupDate = null;
|
187
|
|
188
|
// preprocess nomRef: separate citation, reference detail, publishing date
|
189
|
if(!StringUtils.isEmpty(nomRefStr)){
|
190
|
nomRefStr = nomRefStr.trim();
|
191
|
Matcher m = nomRefTokenizeP.matcher(nomRefStr);
|
192
|
if(m.matches()){
|
193
|
nomRefTitle = m.group(1);
|
194
|
nomRefDetail = m.group(2);
|
195
|
nomRefPupDate = m.group(3).trim();
|
196
|
|
197
|
pupDate = parseDate(regNumber, nomRefPupDate);
|
198
|
if (pupDate != null) {
|
199
|
nomRefTitle = nomRefTitle + ": " + nomRefDetail + ". " + pupDate.toString(formatterYear) + ".";
|
200
|
} else {
|
201
|
logger.warn(csvReportLine(regNumber, "Pub date", nomRefPupDate, "in", nomRefStr, "not parsable"));
|
202
|
}
|
203
|
} else {
|
204
|
nomRefTitle = nomRefStr;
|
205
|
}
|
206
|
}
|
207
|
|
208
|
BotanicalName taxonName = makeBotanicalName(state, regNumber, titleCacheStr, nameStr, authorStr, nomRefTitle);
|
209
|
|
210
|
// always add the original strings of parsed data as annotation
|
211
|
taxonName.addAnnotation(Annotation.NewInstance("imported and parsed data strings:" +
|
212
|
"\n - '" + LITSTRING + "': "+ nomRefStr +
|
213
|
"\n - '" + TYPE + "': " + typeStr +
|
214
|
"\n - '" + REGISTRATION + "': " + regStr
|
215
|
, AnnotationType.TECHNICAL(), Language.DEFAULT()));
|
216
|
|
217
|
if(pupDate != null) {
|
218
|
taxonName.getNomenclaturalReference().setDatePublished(TimePeriod.NewInstance(pupDate));
|
219
|
}
|
220
|
|
221
|
if(!StringUtils.isEmpty(notesTxt)){
|
222
|
notesTxt = notesTxt.replace("Notes: ", "").trim();
|
223
|
taxonName.addAnnotation(Annotation.NewInstance(notesTxt, AnnotationType.EDITORIAL(), Language.DEFAULT()));
|
224
|
}
|
225
|
if(!StringUtils.isEmpty(caveats)){
|
226
|
caveats = caveats.replace("Caveats: ", "").trim();
|
227
|
taxonName.addAnnotation(Annotation.NewInstance(caveats, annotationTypeCaveats(), Language.DEFAULT()));
|
228
|
}
|
229
|
//
|
230
|
|
231
|
// Namerelations
|
232
|
if(!StringUtils.isEmpty(authorsSpelling)){
|
233
|
authorsSpelling = authorsSpelling.replaceFirst("Author's spelling:", "").replaceAll("\"", "").trim();
|
234
|
|
235
|
String[] authorSpellingTokens = StringUtils.split(authorsSpelling, " ");
|
236
|
String[] nameStrTokens = StringUtils.split(nameStr, " ");
|
237
|
|
238
|
ArrayUtils.reverse(authorSpellingTokens);
|
239
|
ArrayUtils.reverse(nameStrTokens);
|
240
|
|
241
|
for (int i = 0; i < nameStrTokens.length; i++){
|
242
|
if(i < authorSpellingTokens.length){
|
243
|
nameStrTokens[i] = authorSpellingTokens[i];
|
244
|
}
|
245
|
}
|
246
|
ArrayUtils.reverse(nameStrTokens);
|
247
|
|
248
|
String misspelledNameStr = StringUtils.join (nameStrTokens, ' ');
|
249
|
// build the fullnameString of the misspelled name
|
250
|
misspelledNameStr = taxonName.getTitleCache().replace(nameStr, misspelledNameStr);
|
251
|
|
252
|
TaxonNameBase misspelledName = (BotanicalName) nameParser.parseReferencedName(misspelledNameStr, NomenclaturalCode.ICNAFP, null);
|
253
|
misspelledName.addRelationshipToName(taxonName, NameRelationshipType.MISSPELLING(), null);
|
254
|
getNameService().save(misspelledName);
|
255
|
}
|
256
|
|
257
|
// Replaced Synonyms
|
258
|
if(!StringUtils.isEmpty(fullSynSubstStr)){
|
259
|
fullSynSubstStr = fullSynSubstStr.replace("Syn. subst.: ", "");
|
260
|
BotanicalName replacedSynonymName = makeBotanicalName(state, regNumber, fullSynSubstStr, synSubstStr, null, null);
|
261
|
replacedSynonymName.addReplacedSynonym(taxonName, null, null, null);
|
262
|
getNameService().save(replacedSynonymName);
|
263
|
}
|
264
|
|
265
|
Reference sec = state.getConfig().getSecReference();
|
266
|
Taxon taxon = Taxon.NewInstance(taxonName, sec);
|
267
|
|
268
|
// Markers
|
269
|
if(isFossil){
|
270
|
taxon.addMarker(Marker.NewInstance(markerTypeFossil(), true));
|
271
|
}
|
272
|
|
273
|
// Types
|
274
|
if(!StringUtils.isEmpty(typeStr)){
|
275
|
makeTypeData(typeStr, taxonName, regNumber, state);
|
276
|
}
|
277
|
|
278
|
getTaxonService().save(taxon);
|
279
|
if(higherTaxonNode != null){
|
280
|
higherTaxonNode.addChildTaxon(taxon, null, null);
|
281
|
getTaxonNodeService().save(higherTaxonNode);
|
282
|
}
|
283
|
|
284
|
return taxon;
|
285
|
|
286
|
}
|
287
|
|
288
|
private void makeTypeData(String typeStr, BotanicalName taxonName, String regNumber, SimpleExcelTaxonImportState<CONFIG> state) {
|
289
|
|
290
|
Matcher m = typeSplitPattern.matcher(typeStr);
|
291
|
|
292
|
if(m.matches()){
|
293
|
String fieldUnitStr = m.group(TypesName.fieldUnit.name());
|
294
|
// boolean isFieldUnit = typeStr.matches(".*([°']|\\d+\\s?m\\s|\\d+\\s?km\\s).*"); // check for location or unit m, km // makes no sense!!!!
|
295
|
FieldUnit fieldUnit = parseFieldUnit(fieldUnitStr, regNumber, state);
|
296
|
if(fieldUnit == null) {
|
297
|
// create a field unit with only a titleCache using the fieldUnitStr substring
|
298
|
logger.warn(csvReportLine(regNumber, "Type: fielUnitStr can not be parsed", fieldUnitStr));
|
299
|
fieldUnit = FieldUnit.NewInstance();
|
300
|
fieldUnit.setTitleCache(fieldUnitStr, true);
|
301
|
getOccurrenceService().save(fieldUnit);
|
302
|
}
|
303
|
getOccurrenceService().save(fieldUnit);
|
304
|
|
305
|
// all others ..
|
306
|
addSpecimenTypes(taxonName, fieldUnit, m.group(TypesName.holotype.name()), TypesName.holotype, false, regNumber);
|
307
|
addSpecimenTypes(taxonName, fieldUnit, m.group(TypesName.isotype.name()), TypesName.isotype, true, regNumber);
|
308
|
|
309
|
} else {
|
310
|
// create a field unit with only a titleCache using the full typeStr
|
311
|
FieldUnit fieldUnit = FieldUnit.NewInstance();
|
312
|
fieldUnit.setTitleCache(typeStr, true);
|
313
|
getOccurrenceService().save(fieldUnit);
|
314
|
logger.warn(csvReportLine(regNumber, "Type: field 'Type' can not be parsed", typeStr));
|
315
|
}
|
316
|
getNameService().save(taxonName);
|
317
|
}
|
318
|
|
319
|
/**
|
320
|
* Currently only parses the collector, fieldNumber and the collection date.
|
321
|
*
|
322
|
* @param fieldUnitStr
|
323
|
* @param regNumber
|
324
|
* @param state
|
325
|
* @return null if the fieldUnitStr could not be parsed
|
326
|
*/
|
327
|
private FieldUnit parseFieldUnit(String fieldUnitStr, String regNumber, SimpleExcelTaxonImportState<CONFIG> state) {
|
328
|
|
329
|
FieldUnit fieldUnit = null;
|
330
|
|
331
|
Matcher m1 = collectorPattern.matcher(fieldUnitStr);
|
332
|
if(m1.matches()){
|
333
|
String collectionData = m1.group(1); // like (leg. Metzeltin, 30. 9. 1996)
|
334
|
if(collectionData == null){
|
335
|
collectionData = m1.group(2); // like leg. Metzeltin, 30. 9. 1996
|
336
|
}
|
337
|
if(collectionData == null){
|
338
|
return null;
|
339
|
}
|
340
|
|
341
|
String collectorStr = null;
|
342
|
String detailStr = null;
|
343
|
Partial date = null;
|
344
|
String fieldNumber = null;
|
345
|
|
346
|
Matcher m2 = collectionDataPattern.matcher(collectionData);
|
347
|
if(m2.matches()){
|
348
|
collectorStr = m2.group("collector");
|
349
|
detailStr = m2.group("detail");
|
350
|
|
351
|
// Try to make sense of the detailStr
|
352
|
if(detailStr != null){
|
353
|
detailStr = detailStr.trim();
|
354
|
// 1. try to parse as date
|
355
|
date = parseDate(regNumber, detailStr);
|
356
|
if(date == null){
|
357
|
// 2. try to parse as number
|
358
|
if(collectorsNumber.matcher(detailStr).matches()){
|
359
|
fieldNumber = detailStr;
|
360
|
}
|
361
|
}
|
362
|
}
|
363
|
if(date == null && fieldNumber == null){
|
364
|
// detailed parsing not possible, so need fo fallback
|
365
|
collectorStr = collectionData;
|
366
|
}
|
367
|
}
|
368
|
|
369
|
if(collectorStr != null) {
|
370
|
fieldUnit = FieldUnit.NewInstance();
|
371
|
GatheringEvent ge = GatheringEvent.NewInstance();
|
372
|
|
373
|
TeamOrPersonBase agent = state.getAgentBase(collectorStr);
|
374
|
if(agent == null) {
|
375
|
agent = Person.NewTitledInstance(collectorStr);
|
376
|
getAgentService().save(agent);
|
377
|
state.putAgentBase(collectorStr, agent);
|
378
|
}
|
379
|
ge.setCollector(agent);
|
380
|
|
381
|
if(date != null){
|
382
|
ge.setGatheringDate(date);
|
383
|
}
|
384
|
|
385
|
getEventBaseService().save(ge);
|
386
|
fieldUnit.setGatheringEvent(ge);
|
387
|
|
388
|
if(fieldNumber != null) {
|
389
|
fieldUnit.setFieldNumber(fieldNumber);
|
390
|
}
|
391
|
getOccurrenceService().save(fieldUnit);
|
392
|
}
|
393
|
}
|
394
|
|
395
|
return fieldUnit;
|
396
|
}
|
397
|
|
398
|
private Partial parseDate(String regNumber, String dateStr) {
|
399
|
|
400
|
Partial pupDate = null;
|
401
|
boolean parseError = false;
|
402
|
|
403
|
String day = null;
|
404
|
String month = null;
|
405
|
String monthName = null;
|
406
|
String year = null;
|
407
|
|
408
|
for(Pattern p : datePatterns){
|
409
|
Matcher m2 = p.matcher(dateStr);
|
410
|
if(m2.matches()){
|
411
|
try {
|
412
|
year = m2.group("year");
|
413
|
} catch (IllegalArgumentException e){
|
414
|
// named capture group not found
|
415
|
}
|
416
|
try {
|
417
|
month = m2.group("month");
|
418
|
} catch (IllegalArgumentException e){
|
419
|
// named capture group not found
|
420
|
}
|
421
|
|
422
|
try {
|
423
|
monthName = m2.group("monthName");
|
424
|
month = monthFromName(monthName, regNumber);
|
425
|
if(month == null){
|
426
|
parseError = true;
|
427
|
}
|
428
|
} catch (IllegalArgumentException e){
|
429
|
// named capture group not found
|
430
|
}
|
431
|
try {
|
432
|
day = m2.group("day");
|
433
|
} catch (IllegalArgumentException e){
|
434
|
// named capture group not found
|
435
|
}
|
436
|
|
437
|
if(year != null){
|
438
|
if (year.length() == 2) {
|
439
|
// it is an abbreviated year from the 19** years
|
440
|
year = "19" + year;
|
441
|
}
|
442
|
break;
|
443
|
} else {
|
444
|
parseError = true;
|
445
|
}
|
446
|
}
|
447
|
}
|
448
|
if(year == null){
|
449
|
parseError = true;
|
450
|
}
|
451
|
List<DateTimeFieldType> types = new ArrayList<>();
|
452
|
List<Integer> values = new ArrayList<>();
|
453
|
if(!parseError) {
|
454
|
types.add(DateTimeFieldType.year());
|
455
|
values.add(Integer.parseInt(year));
|
456
|
if (month != null) {
|
457
|
types.add(DateTimeFieldType.monthOfYear());
|
458
|
values.add(Integer.parseInt(month));
|
459
|
}
|
460
|
if (day != null) {
|
461
|
types.add(DateTimeFieldType.dayOfMonth());
|
462
|
values.add(Integer.parseInt(day));
|
463
|
}
|
464
|
pupDate = new Partial(types.toArray(new DateTimeFieldType[types.size()]), ArrayUtils.toPrimitive(values.toArray(new Integer[values.size()])));
|
465
|
}
|
466
|
return pupDate;
|
467
|
}
|
468
|
|
469
|
private String monthFromName(String monthName, String regNumber) {
|
470
|
|
471
|
Integer month = monthFromNameMap.get(monthName.toLowerCase());
|
472
|
if(month == null){
|
473
|
logger.warn(csvReportLine(regNumber, "Unknown month name", monthName));
|
474
|
return null;
|
475
|
} else {
|
476
|
return month.toString();
|
477
|
}
|
478
|
}
|
479
|
|
480
|
|
481
|
private void addSpecimenTypes(BotanicalName taxonName, FieldUnit fieldUnit, String typeStr, TypesName typeName, boolean multiple, String regNumber){
|
482
|
|
483
|
if(StringUtils.isEmpty(typeStr)){
|
484
|
return;
|
485
|
}
|
486
|
typeStr = typeStr.trim().replaceAll("\\.$", "");
|
487
|
|
488
|
Collection collection = null;
|
489
|
DerivedUnit specimen = null;
|
490
|
|
491
|
List<DerivedUnit> specimens = new ArrayList<>();
|
492
|
if(multiple){
|
493
|
String[] tokens = typeStr.split("\\s?,\\s?");
|
494
|
for (String t : tokens) {
|
495
|
// command to list all complex parsabel types:
|
496
|
// csvcut -t -c RegistrationNo_Pk,Type iapt.csv | csvgrep -c Type -m "Holotype" | egrep -o 'Holotype:\s([A-Z]*\s)[^.]*?'
|
497
|
// csvcut -t -c RegistrationNo_Pk,Type iapt.csv | csvgrep -c Type -m "Holotype" | egrep -o 'Isotype[^:]*:\s([A-Z]*\s)[^.]*?'
|
498
|
|
499
|
if(!t.isEmpty()){
|
500
|
// trying to parse the string
|
501
|
specimen = parseSpecimenType(fieldUnit, typeName, collection, t, regNumber);
|
502
|
if(specimen != null){
|
503
|
specimens.add(specimen);
|
504
|
} else {
|
505
|
// parsing was not successful make simple specimen
|
506
|
specimens.add(makeSpecimenType(fieldUnit, t));
|
507
|
}
|
508
|
}
|
509
|
}
|
510
|
} else {
|
511
|
specimen = parseSpecimenType(fieldUnit, typeName, collection, typeStr, regNumber);
|
512
|
if(specimen != null) {
|
513
|
specimens.add(specimen);
|
514
|
// remember current collection
|
515
|
collection = specimen.getCollection();
|
516
|
} else {
|
517
|
// parsing was not successful make simple specimen
|
518
|
specimens.add(makeSpecimenType(fieldUnit, typeStr));
|
519
|
}
|
520
|
}
|
521
|
|
522
|
for(DerivedUnit s : specimens){
|
523
|
taxonName.addSpecimenTypeDesignation(s, typeName.status(), null, null, null, false, true);
|
524
|
}
|
525
|
}
|
526
|
|
527
|
private DerivedUnit makeSpecimenType(FieldUnit fieldUnit, String titleCache) {
|
528
|
DerivedUnit specimen;DerivedUnitFacade facade = DerivedUnitFacade.NewInstance(SpecimenOrObservationType.PreservedSpecimen, fieldUnit);
|
529
|
facade.setTitleCache(titleCache.trim(), true);
|
530
|
specimen = facade.innerDerivedUnit();
|
531
|
return specimen;
|
532
|
}
|
533
|
|
534
|
/**
|
535
|
*
|
536
|
* @param fieldUnit
|
537
|
* @param typeName
|
538
|
* @param collection
|
539
|
* @param text
|
540
|
* @param regNumber
|
541
|
* @return
|
542
|
*/
|
543
|
private DerivedUnit parseSpecimenType(FieldUnit fieldUnit, TypesName typeName, Collection collection, String text, String regNumber) {
|
544
|
|
545
|
DerivedUnit specimen = null;
|
546
|
|
547
|
String collectionCode = null;
|
548
|
String subCollectionStr = null;
|
549
|
String instituteStr = null;
|
550
|
String accessionNumber = null;
|
551
|
|
552
|
boolean unusualAccessionNumber = false;
|
553
|
|
554
|
text = text.trim();
|
555
|
|
556
|
// 1. For Isotypes often the accession number is noted alone if the
|
557
|
// preceeding entry has a collection code.
|
558
|
if(typeName .equals(TypesName.isotype) && collection != null){
|
559
|
Matcher m = accessionNumberOnlyPattern.matcher(text);
|
560
|
if(m.matches()){
|
561
|
try {
|
562
|
accessionNumber = m.group("accNumber");
|
563
|
specimen = makeSpecimenType(fieldUnit, collection, accessionNumber);
|
564
|
} catch (IllegalArgumentException e){
|
565
|
// match group acc_number not found
|
566
|
}
|
567
|
}
|
568
|
}
|
569
|
|
570
|
//2. try it the 'normal' way
|
571
|
if(specimen == null) {
|
572
|
for (Pattern p : specimenTypePatterns) {
|
573
|
Matcher m = p.matcher(text);
|
574
|
if (m.matches()) {
|
575
|
// collection code is mandatory
|
576
|
try {
|
577
|
collectionCode = m.group("colCode");
|
578
|
} catch (IllegalArgumentException e){
|
579
|
// match group colCode not found
|
580
|
}
|
581
|
try {
|
582
|
subCollectionStr = m.group("subCollection");
|
583
|
} catch (IllegalArgumentException e){
|
584
|
// match group subCollection not found
|
585
|
}
|
586
|
try {
|
587
|
instituteStr = m.group("institute");
|
588
|
} catch (IllegalArgumentException e){
|
589
|
// match group col_name not found
|
590
|
}
|
591
|
try {
|
592
|
accessionNumber = m.group("accNumber");
|
593
|
|
594
|
// try to improve the accessionNumber
|
595
|
if(accessionNumber!= null) {
|
596
|
accessionNumber = accessionNumber.trim();
|
597
|
Matcher m2 = accessionNumberOnlyPattern.matcher(accessionNumber);
|
598
|
String betterAccessionNumber = null;
|
599
|
if (m2.matches()) {
|
600
|
try {
|
601
|
betterAccessionNumber = m.group("accNumber");
|
602
|
} catch (IllegalArgumentException e) {
|
603
|
// match group acc_number not found
|
604
|
}
|
605
|
}
|
606
|
if (betterAccessionNumber != null) {
|
607
|
accessionNumber = betterAccessionNumber;
|
608
|
} else {
|
609
|
unusualAccessionNumber = true;
|
610
|
}
|
611
|
}
|
612
|
|
613
|
} catch (IllegalArgumentException e){
|
614
|
// match group acc_number not found
|
615
|
}
|
616
|
|
617
|
if(collectionCode == null && instituteStr == null){
|
618
|
logger.warn(csvReportLine(regNumber, "Type: neither 'collectionCode' nor 'institute' found in ", text));
|
619
|
continue;
|
620
|
}
|
621
|
collection = getCollection(collectionCode, instituteStr, subCollectionStr);
|
622
|
specimen = makeSpecimenType(fieldUnit, collection, accessionNumber);
|
623
|
break;
|
624
|
}
|
625
|
}
|
626
|
}
|
627
|
if(specimen == null) {
|
628
|
logger.warn(csvReportLine(regNumber, "Type: Could not parse specimen", typeName.name().toString(), text));
|
629
|
}
|
630
|
if(unusualAccessionNumber){
|
631
|
logger.warn(csvReportLine(regNumber, "Type: Unusual accession number", typeName.name().toString(), text, accessionNumber));
|
632
|
}
|
633
|
return specimen;
|
634
|
}
|
635
|
|
636
|
private DerivedUnit makeSpecimenType(FieldUnit fieldUnit, Collection collection, String accessionNumber) {
|
637
|
|
638
|
DerivedUnitFacade facade = DerivedUnitFacade.NewInstance(SpecimenOrObservationType.PreservedSpecimen, fieldUnit);
|
639
|
facade.setCollection(collection);
|
640
|
if(accessionNumber != null){
|
641
|
facade.setAccessionNumber(accessionNumber);
|
642
|
}
|
643
|
return facade.innerDerivedUnit();
|
644
|
}
|
645
|
|
646
|
private BotanicalName makeBotanicalName(SimpleExcelTaxonImportState<CONFIG> state, String regNumber, String titleCacheStr, String nameStr,
|
647
|
String authorStr, String nomRefTitle) {
|
648
|
|
649
|
BotanicalName taxonName;// cache field for the taxonName.titleCache
|
650
|
String taxonNameTitleCache = null;
|
651
|
Map<String, AnnotationType> nameAnnotations = new HashMap<>();
|
652
|
|
653
|
// TitleCache preprocessing
|
654
|
if(titleCacheStr.endsWith(ANNOTATION_MARKER_STRING) || (authorStr != null && authorStr.endsWith(ANNOTATION_MARKER_STRING))){
|
655
|
nameAnnotations.put("Author abbreviation not checked.", AnnotationType.EDITORIAL());
|
656
|
titleCacheStr = titleCacheStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
657
|
authorStr = authorStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
658
|
}
|
659
|
|
660
|
// parse the full taxon name
|
661
|
if(!StringUtils.isEmpty(nomRefTitle)){
|
662
|
String referenceSeparator = nomRefTitle.startsWith("in ") ? " " : ", ";
|
663
|
String taxonFullNameStr = titleCacheStr + referenceSeparator + nomRefTitle;
|
664
|
logger.debug(":::::" + taxonFullNameStr);
|
665
|
taxonName = (BotanicalName) nameParser.parseReferencedName(taxonFullNameStr, NomenclaturalCode.ICNAFP, null);
|
666
|
} else {
|
667
|
taxonName = (BotanicalName) nameParser.parseFullName(titleCacheStr, NomenclaturalCode.ICNAFP, null);
|
668
|
}
|
669
|
|
670
|
taxonNameTitleCache = taxonName.getTitleCache().trim();
|
671
|
if (taxonName.isProtectedTitleCache()) {
|
672
|
logger.warn(csvReportLine(regNumber, "Name could not be parsed", titleCacheStr));
|
673
|
} else {
|
674
|
|
675
|
boolean doRestoreTitleCacheStr = false;
|
676
|
|
677
|
// Check if titleCache and nameCache are plausible
|
678
|
String titleCacheCompareStr = titleCacheStr;
|
679
|
String nameCache = taxonName.getNameCache();
|
680
|
String nameCompareStr = nameStr;
|
681
|
if(taxonName.isBinomHybrid()){
|
682
|
titleCacheCompareStr = titleCacheCompareStr.replace(" x ", " ×");
|
683
|
nameCompareStr = nameCompareStr.replace(" x ", " ×");
|
684
|
}
|
685
|
if(taxonName.isMonomHybrid()){
|
686
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll("^X ", "× ");
|
687
|
nameCompareStr = nameCompareStr.replace("^X ", "× ");
|
688
|
}
|
689
|
if(authorStr != null && authorStr.contains(" et ")){
|
690
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll(" et ", " & ");
|
691
|
}
|
692
|
if (!taxonNameTitleCache.equals(titleCacheCompareStr)) {
|
693
|
logger.warn(csvReportLine(regNumber, "The generated titleCache differs from the imported string", taxonNameTitleCache, " != ", titleCacheStr, " ==> original titleCacheStr has been restored"));
|
694
|
doRestoreTitleCacheStr = true;
|
695
|
}
|
696
|
if (!nameCache.trim().equals(nameCompareStr)) {
|
697
|
logger.warn(csvReportLine(regNumber, "The parsed nameCache differs from field '" + NAMESTRING + "'", nameCache, " != ", nameCompareStr));
|
698
|
}
|
699
|
|
700
|
// Author
|
701
|
//nameParser.handleAuthors(taxonName, titleCacheStr, authorStr);
|
702
|
//if (!titleCacheStr.equals(taxonName.getTitleCache())) {
|
703
|
// logger.warn(regNumber + ": titleCache has changed after setting authors, will restore original titleCacheStr");
|
704
|
// doRestoreTitleCacheStr = true;
|
705
|
//}
|
706
|
|
707
|
if(doRestoreTitleCacheStr){
|
708
|
taxonName.setTitleCache(titleCacheStr, true);
|
709
|
}
|
710
|
|
711
|
// deduplicate
|
712
|
replaceAuthorNamesAndNomRef(state, taxonName);
|
713
|
}
|
714
|
|
715
|
// Annotations
|
716
|
if(!nameAnnotations.isEmpty()){
|
717
|
for(String text : nameAnnotations.keySet()){
|
718
|
taxonName.addAnnotation(Annotation.NewInstance(text, nameAnnotations.get(text), Language.DEFAULT()));
|
719
|
}
|
720
|
getNameService().save(taxonName);
|
721
|
}
|
722
|
return taxonName;
|
723
|
}
|
724
|
|
725
|
/**
|
726
|
* @param state
|
727
|
* @return
|
728
|
*/
|
729
|
private TaxonNode getClassificationRootNode(IAPTImportState state) {
|
730
|
|
731
|
// Classification classification = state.getClassification();
|
732
|
// if (classification == null){
|
733
|
// IAPTImportConfigurator config = state.getConfig();
|
734
|
// classification = Classification.NewInstance(state.getConfig().getClassificationName());
|
735
|
// classification.setUuid(config.getClassificationUuid());
|
736
|
// classification.setReference(config.getSecReference());
|
737
|
// classification = getClassificationService().find(state.getConfig().getClassificationUuid());
|
738
|
// }
|
739
|
TaxonNode rootNode = state.getRootNode();
|
740
|
if (rootNode == null){
|
741
|
rootNode = getTaxonNodeService().find(ROOT_UUID);
|
742
|
}
|
743
|
if (rootNode == null){
|
744
|
Classification classification = state.getClassification();
|
745
|
if (classification == null){
|
746
|
Reference sec = state.getSecReference();
|
747
|
String classificationName = state.getConfig().getClassificationName();
|
748
|
Language language = Language.DEFAULT();
|
749
|
classification = Classification.NewInstance(classificationName, sec, language);
|
750
|
state.setClassification(classification);
|
751
|
classification.setUuid(state.getConfig().getClassificationUuid());
|
752
|
classification.getRootNode().setUuid(ROOT_UUID);
|
753
|
getClassificationService().save(classification);
|
754
|
}
|
755
|
rootNode = classification.getRootNode();
|
756
|
state.setRootNode(rootNode);
|
757
|
}
|
758
|
return rootNode;
|
759
|
}
|
760
|
|
761
|
private Collection getCollection(String collectionCode, String instituteStr, String subCollectionStr){
|
762
|
|
763
|
Collection superCollection = null;
|
764
|
if(subCollectionStr != null){
|
765
|
superCollection = getCollection(collectionCode, instituteStr, null);
|
766
|
collectionCode = subCollectionStr;
|
767
|
instituteStr = null;
|
768
|
}
|
769
|
|
770
|
final String key = collectionCode + "-#i:" + StringUtils.defaultString(instituteStr);
|
771
|
|
772
|
Collection collection = collectionMap.get(key);
|
773
|
|
774
|
if(collection == null) {
|
775
|
collection = Collection.NewInstance();
|
776
|
collection.setCode(collectionCode);
|
777
|
if(instituteStr != null){
|
778
|
collection.setInstitute(Institution.NewNamedInstance(instituteStr));
|
779
|
}
|
780
|
if(superCollection != null){
|
781
|
collection.setSuperCollection(superCollection);
|
782
|
}
|
783
|
collectionMap.put(key, collection);
|
784
|
getCollectionService().save(collection);
|
785
|
}
|
786
|
|
787
|
return collection;
|
788
|
}
|
789
|
|
790
|
|
791
|
/**
|
792
|
* @param record
|
793
|
* @param originalKey
|
794
|
* @param doUnescapeHtmlEntities
|
795
|
* @return
|
796
|
*/
|
797
|
private String getValue(HashMap<String, String> record, String originalKey, boolean doUnescapeHtmlEntities) {
|
798
|
String value = record.get(originalKey);
|
799
|
|
800
|
value = fixCharacters(value);
|
801
|
|
802
|
if (! StringUtils.isBlank(value)) {
|
803
|
if (logger.isDebugEnabled()) {
|
804
|
logger.debug(originalKey + ": " + value);
|
805
|
}
|
806
|
value = CdmUtils.removeDuplicateWhitespace(value.trim()).toString();
|
807
|
if(doUnescapeHtmlEntities){
|
808
|
value = StringEscapeUtils.unescapeHtml(value);
|
809
|
}
|
810
|
return value.trim();
|
811
|
}else{
|
812
|
return null;
|
813
|
}
|
814
|
}
|
815
|
|
816
|
/**
|
817
|
* Fixes broken characters.
|
818
|
* For details see
|
819
|
* http://dev.e-taxonomy.eu/redmine/issues/6035
|
820
|
*
|
821
|
* @param value
|
822
|
* @return
|
823
|
*/
|
824
|
private String fixCharacters(String value) {
|
825
|
|
826
|
value = StringUtils.replace(value, "s$K", "š");
|
827
|
value = StringUtils.replace(value, "n$K", "ň");
|
828
|
value = StringUtils.replace(value, "e$K", "ě");
|
829
|
value = StringUtils.replace(value, "r$K", "ř");
|
830
|
value = StringUtils.replace(value, "c$K", "č");
|
831
|
value = StringUtils.replace(value, "z$K", "ž");
|
832
|
value = StringUtils.replace(value, "S>U$K", "Š");
|
833
|
value = StringUtils.replace(value, "C>U$K", "Č");
|
834
|
value = StringUtils.replace(value, "R>U$K", "Ř");
|
835
|
value = StringUtils.replace(value, "Z>U$K", "Ž");
|
836
|
value = StringUtils.replace(value, "g$K", "ǧ");
|
837
|
value = StringUtils.replace(value, "s$A", "ś");
|
838
|
value = StringUtils.replace(value, "n$A", "ń");
|
839
|
value = StringUtils.replace(value, "c$A", "ć");
|
840
|
value = StringUtils.replace(value, "e$E", "ę");
|
841
|
value = StringUtils.replace(value, "o$H", "õ");
|
842
|
value = StringUtils.replace(value, "s$C", "ş");
|
843
|
value = StringUtils.replace(value, "t$C", "ț");
|
844
|
value = StringUtils.replace(value, "S>U$C", "Ş");
|
845
|
value = StringUtils.replace(value, "a$O", "å");
|
846
|
value = StringUtils.replace(value, "A>U$O", "Å");
|
847
|
value = StringUtils.replace(value, "u$O", "ů");
|
848
|
value = StringUtils.replace(value, "g$B", "ğ");
|
849
|
value = StringUtils.replace(value, "g$B", "ĕ");
|
850
|
value = StringUtils.replace(value, "a$B", "ă");
|
851
|
value = StringUtils.replace(value, "l$/", "ł");
|
852
|
value = StringUtils.replace(value, ">i", "ı");
|
853
|
value = StringUtils.replace(value, "i$U", "ï");
|
854
|
// Special-cases
|
855
|
value = StringUtils.replace(value, "ý", "ý");
|
856
|
value = StringUtils.replace(value, ">L", "Ł"); // corrected rule
|
857
|
value = StringUtils.replace(value, "E>U$D", "З");
|
858
|
value = StringUtils.replace(value, "S>U$E", "Ş");
|
859
|
value = StringUtils.replace(value, "s$E", "ş");
|
860
|
|
861
|
value = StringUtils.replace(value, "c$k", "č");
|
862
|
value = StringUtils.replace(value, " U$K", " Š");
|
863
|
|
864
|
return value;
|
865
|
}
|
866
|
|
867
|
|
868
|
/**
|
869
|
* Stores taxa records in DB
|
870
|
*/
|
871
|
@Override
|
872
|
protected void firstPass(SimpleExcelTaxonImportState<CONFIG> state) {
|
873
|
|
874
|
String lineNumber = "L#" + state.getCurrentLine() + ": ";
|
875
|
logger.setLevel(Level.DEBUG);
|
876
|
HashMap<String, String> record = state.getOriginalRecord();
|
877
|
logger.debug(lineNumber + record.toString());
|
878
|
|
879
|
Set<String> keys = record.keySet();
|
880
|
for (String key: keys) {
|
881
|
if (! expectedKeys.contains(key)){
|
882
|
logger.warn(lineNumber + "Unexpected Key: " + key);
|
883
|
}
|
884
|
}
|
885
|
|
886
|
String reg_id = record.get(REGISTRATIONNO_PK);
|
887
|
|
888
|
//higherTaxon
|
889
|
String higherTaxaString = record.get(HIGHERTAXON);
|
890
|
boolean isFossil = false;
|
891
|
if(higherTaxaString.startsWith("FOSSIL ")){
|
892
|
higherTaxaString = higherTaxaString.replace("FOSSIL ", "");
|
893
|
isFossil = true;
|
894
|
}
|
895
|
TaxonNode higherTaxon = getHigherTaxon(higherTaxaString, (IAPTImportState)state);
|
896
|
|
897
|
//Taxon
|
898
|
Taxon taxon = makeTaxon(record, state, higherTaxon, isFossil);
|
899
|
if (taxon == null){
|
900
|
logger.warn(lineNumber + "taxon could not be created and is null");
|
901
|
return;
|
902
|
}
|
903
|
((IAPTImportState)state).setCurrentTaxon(taxon);
|
904
|
|
905
|
|
906
|
return;
|
907
|
}
|
908
|
|
909
|
private TaxonNode getHigherTaxon(String higherTaxaString, IAPTImportState state) {
|
910
|
String[] higherTaxaNames = higherTaxaString.toLowerCase().replaceAll("[\\[\\]]", "").split(":");
|
911
|
TaxonNode higherTaxonNode = null;
|
912
|
|
913
|
ITaxonTreeNode rootNode = getClassificationRootNode(state);
|
914
|
for (String htn : higherTaxaNames) {
|
915
|
htn = StringUtils.capitalize(htn.trim());
|
916
|
Taxon higherTaxon = state.getHigherTaxon(htn);
|
917
|
if (higherTaxon != null){
|
918
|
higherTaxonNode = higherTaxon.getTaxonNodes().iterator().next();
|
919
|
}else{
|
920
|
BotanicalName name = makeHigherTaxonName(state, htn);
|
921
|
Reference sec = state.getSecReference();
|
922
|
higherTaxon = Taxon.NewInstance(name, sec);
|
923
|
getTaxonService().save(higherTaxon);
|
924
|
higherTaxonNode = rootNode.addChildTaxon(higherTaxon, sec, null);
|
925
|
state.putHigherTaxon(htn, higherTaxon);
|
926
|
getClassificationService().saveTreeNode(higherTaxonNode);
|
927
|
}
|
928
|
rootNode = higherTaxonNode;
|
929
|
}
|
930
|
return higherTaxonNode;
|
931
|
}
|
932
|
|
933
|
private BotanicalName makeHigherTaxonName(IAPTImportState state, String name) {
|
934
|
|
935
|
Rank rank = guessRank(name);
|
936
|
|
937
|
BotanicalName taxonName = BotanicalName.NewInstance(rank);
|
938
|
taxonName.addSource(makeOriginalSource(state));
|
939
|
taxonName.setGenusOrUninomial(StringUtils.capitalize(name));
|
940
|
return taxonName;
|
941
|
}
|
942
|
|
943
|
private Rank guessRank(String name) {
|
944
|
|
945
|
// normalize
|
946
|
name = name.replaceAll("\\(.*\\)", "").trim();
|
947
|
|
948
|
if(name.matches("^Plantae$|^Fungi$")){
|
949
|
return Rank.KINGDOM();
|
950
|
} else if(name.matches("^Incertae sedis$|^No group assigned$")){
|
951
|
return rankFamilyIncertisSedis();
|
952
|
} else if(name.matches(".*phyta$|.*mycota$")){
|
953
|
return Rank.SECTION_BOTANY();
|
954
|
} else if(name.matches(".*phytina$|.*mycotina$")){
|
955
|
return Rank.SUBSECTION_BOTANY();
|
956
|
} else if(name.matches("Gymnospermae$|.*ones$")){ // Monocotyledones, Dicotyledones
|
957
|
return rankUnrankedSupraGeneric();
|
958
|
} else if(name.matches(".*opsida$|.*phyceae$|.*mycetes$|.*ones$|^Musci$|^Hepaticae$")){
|
959
|
return Rank.CLASS();
|
960
|
} else if(name.matches(".*idae$|.*phycidae$|.*mycetidae$")){
|
961
|
return Rank.SUBCLASS();
|
962
|
} else if(name.matches(".*ales$")){
|
963
|
return Rank.ORDER();
|
964
|
} else if(name.matches(".*ineae$")){
|
965
|
return Rank.SUBORDER();
|
966
|
} else if(name.matches(".*aceae$")){
|
967
|
return Rank.FAMILY();
|
968
|
} else if(name.matches(".*oideae$")){
|
969
|
return Rank.SUBFAMILY();
|
970
|
} else
|
971
|
// if(name.matches(".*eae$")){
|
972
|
// return Rank.TRIBE();
|
973
|
// } else
|
974
|
if(name.matches(".*inae$")){
|
975
|
return Rank.SUBTRIBE();
|
976
|
} else if(name.matches(".*ae$")){
|
977
|
return Rank.FAMILY();
|
978
|
}
|
979
|
return Rank.UNKNOWN_RANK();
|
980
|
}
|
981
|
|
982
|
private Rank rankUnrankedSupraGeneric() {
|
983
|
|
984
|
if(rankUnrankedSupraGeneric == null){
|
985
|
rankUnrankedSupraGeneric = Rank.NewInstance(RankClass.Suprageneric, "Unranked supra generic", " ", " ");
|
986
|
getTermService().save(rankUnrankedSupraGeneric);
|
987
|
}
|
988
|
return rankUnrankedSupraGeneric;
|
989
|
}
|
990
|
|
991
|
private Rank rankFamilyIncertisSedis() {
|
992
|
|
993
|
if(familyIncertisSedis == null){
|
994
|
familyIncertisSedis = Rank.NewInstance(RankClass.Suprageneric, "Family incertis sedis", " ", " ");
|
995
|
getTermService().save(familyIncertisSedis);
|
996
|
}
|
997
|
return familyIncertisSedis;
|
998
|
}
|
999
|
|
1000
|
private AnnotationType annotationTypeCaveats(){
|
1001
|
if(annotationTypeCaveats == null){
|
1002
|
annotationTypeCaveats = AnnotationType.NewInstance("Caveats", "Caveats", "");
|
1003
|
getTermService().save(annotationTypeCaveats);
|
1004
|
}
|
1005
|
return annotationTypeCaveats;
|
1006
|
}
|
1007
|
|
1008
|
|
1009
|
/**
|
1010
|
* @param state
|
1011
|
* @return
|
1012
|
*/
|
1013
|
private IdentifiableSource makeOriginalSource(IAPTImportState state) {
|
1014
|
return IdentifiableSource.NewDataImportInstance("line: " + state.getCurrentLine(), null, state.getConfig().getSourceReference());
|
1015
|
}
|
1016
|
|
1017
|
|
1018
|
private Reference makeReference(IAPTImportState state, UUID uuidRef) {
|
1019
|
Reference ref = state.getReference(uuidRef);
|
1020
|
if (ref == null){
|
1021
|
ref = getReferenceService().find(uuidRef);
|
1022
|
state.putReference(uuidRef, ref);
|
1023
|
}
|
1024
|
return ref;
|
1025
|
}
|
1026
|
|
1027
|
private MarkerType markerTypeFossil(){
|
1028
|
if(this.markerTypeFossil == null){
|
1029
|
markerTypeFossil = MarkerType.NewInstance("isFossilTaxon", "isFossil", null);
|
1030
|
getTermService().save(this.markerTypeFossil);
|
1031
|
}
|
1032
|
return markerTypeFossil;
|
1033
|
}
|
1034
|
|
1035
|
private String csvReportLine(String regId, String message, String ... fields){
|
1036
|
StringBuilder out = new StringBuilder("regID#");
|
1037
|
out.append(regId).append(",\"").append(message).append('"');
|
1038
|
|
1039
|
for(String f : fields){
|
1040
|
out.append(",\"").append(f).append('"');
|
1041
|
}
|
1042
|
return out.toString();
|
1043
|
}
|
1044
|
|
1045
|
|
1046
|
}
|