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.joda.time.DateTimeFieldType;
|
30
|
import org.joda.time.Partial;
|
31
|
import org.springframework.stereotype.Component;
|
32
|
|
33
|
import java.util.*;
|
34
|
import java.util.regex.Matcher;
|
35
|
import java.util.regex.Pattern;
|
36
|
|
37
|
/**
|
38
|
* @author a.mueller
|
39
|
* @created 05.01.2016
|
40
|
*/
|
41
|
|
42
|
@Component("iAPTExcelImport")
|
43
|
public class IAPTExcelImport<CONFIG extends IAPTImportConfigurator> extends SimpleExcelTaxonImport<CONFIG> {
|
44
|
private static final long serialVersionUID = -747486709409732371L;
|
45
|
private static final Logger logger = Logger.getLogger(IAPTExcelImport.class);
|
46
|
public static final String ANNOTATION_MARKER_STRING = "[*]";
|
47
|
|
48
|
|
49
|
private static UUID ROOT_UUID = UUID.fromString("4137fd2a-20f6-4e70-80b9-f296daf51d82");
|
50
|
|
51
|
private static NonViralNameParserImpl nameParser = NonViralNameParserImpl.NewInstance();
|
52
|
|
53
|
private final static String REGISTRATIONNO_PK= "RegistrationNo_Pk";
|
54
|
private final static String HIGHERTAXON= "HigherTaxon";
|
55
|
private final static String FULLNAME= "FullName";
|
56
|
private final static String AUTHORSSPELLING= "AuthorsSpelling";
|
57
|
private final static String LITSTRING= "LitString";
|
58
|
private final static String REGISTRATION= "Registration";
|
59
|
private final static String TYPE= "Type";
|
60
|
private final static String CAVEATS= "Caveats";
|
61
|
private final static String FULLBASIONYM= "FullBasionym";
|
62
|
private final static String FULLSYNSUBST= "FullSynSubst";
|
63
|
private final static String NOTESTXT= "NotesTxt";
|
64
|
private final static String REGDATE= "RegDate";
|
65
|
private final static String NAMESTRING= "NameString";
|
66
|
private final static String BASIONYMSTRING= "BasionymString";
|
67
|
private final static String SYNSUBSTSTR= "SynSubstStr";
|
68
|
private final static String AUTHORSTRING= "AuthorString";
|
69
|
|
70
|
private static List<String> expectedKeys= Arrays.asList(new String[]{
|
71
|
REGISTRATIONNO_PK, HIGHERTAXON, FULLNAME, AUTHORSSPELLING, LITSTRING, REGISTRATION, TYPE, CAVEATS, FULLBASIONYM, FULLSYNSUBST, NOTESTXT, REGDATE, NAMESTRING, BASIONYMSTRING, SYNSUBSTSTR, AUTHORSTRING});
|
72
|
|
73
|
private static final Pattern nomRefTokenizeP = Pattern.compile("^(.*):\\s([^\\.:]+)\\.(.*?)\\.?$");
|
74
|
private static final Pattern[] nomRefPubDatePs = new Pattern[]{
|
75
|
// NOTE:
|
76
|
// The order of the patterns is extremely important!!!
|
77
|
//
|
78
|
// all patterns cover the years 1700 - 1999
|
79
|
Pattern.compile("^(?<year>1[7,8,9][0-9]{2})$"), // only year, like '1969'
|
80
|
Pattern.compile("^(?<monthName>\\p{L}+\\.?)\\s(?<day>[0-9]{1,2})(?:st|rd|th)?\\.?,?\\s(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like April 12, 1969 or april 12th 1999
|
81
|
Pattern.compile("^(?<monthName>\\p{L}+\\.?),?\\s(?<year>(?:1[7,8,9])?[0-9]{2})$"), // April 99 or April, 1999 or Apr. 12
|
82
|
Pattern.compile("^(?<day>[0-9]{1,2})([\\.\\-/])(?<month>[0-1]?[0-9])\\2(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like 12.04.1969 or 12/04/1969 or 12-04-1969
|
83
|
Pattern.compile("^(?<month>[0-1]?[0-9])([\\.\\-/])(?<year>(?:1[7,8,9])?[0-9]{2})$"), // partial date like 04.1969 or 04/1969 or 04-1969
|
84
|
Pattern.compile("^(?<day>[0-9]{1,2})(?:[\\./]|th|rd)?\\s(?<monthName>\\p{L}+\\.?),?\\s(?<year>(?:1[7,8,9])?[0-9]{2})$"), // full date like 12. April 1969 or april 1999 or 22 Dec.1999
|
85
|
};
|
86
|
private static final Pattern typeSplitPattern = Pattern.compile("^(?:\"*[Tt]ype: (?<type>.*?))(?:[Hh]olotype:(?<holotype>.*?))?(?:[Ii]sotype[^:]*:(?<isotype>.*))?$");
|
87
|
|
88
|
private static Map<String, Integer> monthFromNameMap = new HashMap<>();
|
89
|
static {
|
90
|
String[] ck = new String[]{"leden", "únor", "březen", "duben", "květen", "červen", "červenec ", "srpen", "září", "říjen", "listopad", "prosinec"};
|
91
|
String[] fr = new String[]{"janvier", "février", "mars", "avril", "mai", "juin", "juillet", "août", "septembre", "octobre", "novembre", "décembre"};
|
92
|
String[] de = new String[]{"januar", "februar", "märz", "april", "mai", "juni", "juli", "august", "september", "oktober", "november", "dezember"};
|
93
|
String[] en = new String[]{"january", "february", "march", "april", "may", "june", "july", "august", "september", "october", "november", "december"};
|
94
|
String[] it = new String[]{"gennaio", "febbraio", "marzo", "aprile", "maggio", "giugno", "luglio", "agosto", "settembre", "ottobre", "novembre", "dicembre"};
|
95
|
String[] sp = new String[]{"enero", "febrero", "marzo", "abril", "mayo", "junio", "julio", "agosto", "septiembre", "octubre", "noviembre", "diciembre"};
|
96
|
String[] de_abbrev = new String[]{"jan.", "feb.", "märz", "apr.", "mai", "jun.", "jul.", "aug.", "sept.", "okt.", "nov.", "dez."};
|
97
|
String[] en_abbrev = new String[]{"jan.", "feb.", "mar.", "apr.", "may", "jun.", "jul.", "aug.", "sep.", "oct.", "nov.", "dec."};
|
98
|
String[] port = new String[]{"Janeiro", "Fevereiro", "Março", "Abril", "Maio", "Junho", "Julho", "Agosto", "Setembro", "Outubro", "Novembro", "Dezembro"};
|
99
|
String[] rom_num = new String[]{"i", "ii", "iii", "iv", "v", "vi", "vii", "viii", "ix", "x", "xi", "xii"};
|
100
|
|
101
|
String[][] perLang = new String[][]{ck, de, fr, en, it, sp, port, de_abbrev, en_abbrev, rom_num};
|
102
|
|
103
|
for (String[] months: perLang) {
|
104
|
for(int m = 1; m < 13; m++){
|
105
|
monthFromNameMap.put(months[m - 1].toLowerCase(), m);
|
106
|
}
|
107
|
}
|
108
|
|
109
|
// special cases
|
110
|
monthFromNameMap.put("mar", 3);
|
111
|
monthFromNameMap.put("dec", 12);
|
112
|
monthFromNameMap.put("Februari", 2);
|
113
|
}
|
114
|
|
115
|
enum TypesName {
|
116
|
type, holotype, isotype;
|
117
|
|
118
|
public SpecimenTypeDesignationStatus status(){
|
119
|
switch (this) {
|
120
|
case holotype:
|
121
|
return SpecimenTypeDesignationStatus.HOLOTYPE();
|
122
|
case isotype:
|
123
|
return SpecimenTypeDesignationStatus.ISOTYPE();
|
124
|
default:
|
125
|
return null;
|
126
|
}
|
127
|
}
|
128
|
}
|
129
|
|
130
|
private MarkerType markerTypeFossil = null;
|
131
|
private Rank rankUnrankedSupraGeneric = null;
|
132
|
private Rank familyIncertisSedis = null;
|
133
|
private AnnotationType annotationTypeCaveats = null;
|
134
|
|
135
|
private Taxon makeTaxon(HashMap<String, String> record, SimpleExcelTaxonImportState<CONFIG> state,
|
136
|
TaxonNode higherTaxonNode, boolean isFossil) {
|
137
|
|
138
|
String line = state.getCurrentLine() + ": ";
|
139
|
|
140
|
String regNumber = getValue(record, REGISTRATIONNO_PK, false);
|
141
|
String titleCacheStr = getValue(record, FULLNAME, true);
|
142
|
String nameStr = getValue(record, NAMESTRING, true);
|
143
|
String authorStr = getValue(record, AUTHORSTRING, true);
|
144
|
String nomRefStr = getValue(record, LITSTRING, true);
|
145
|
String authorsSpelling = getValue(record, AUTHORSSPELLING, true);
|
146
|
String notesTxt = getValue(record, NOTESTXT, true);
|
147
|
String caveats = getValue(record, CAVEATS, true);
|
148
|
String fullSynSubstStr = getValue(record, FULLSYNSUBST, true);
|
149
|
String synSubstStr = getValue(record, SYNSUBSTSTR, true);
|
150
|
String typeStr = getValue(record, TYPE, true);
|
151
|
|
152
|
String nomRefTitle = null;
|
153
|
String nomRefDetail = null;
|
154
|
String nomRefPupDate = null;
|
155
|
String nomRefPupDay = null;
|
156
|
String nomRefPupMonth = null;
|
157
|
String nomRefPupMonthName = null;
|
158
|
String nomRefPupYear = null;
|
159
|
|
160
|
// preprocess nomRef: separate citation, reference detail, publishing date
|
161
|
if(!StringUtils.isEmpty(nomRefStr)){
|
162
|
nomRefStr = nomRefStr.trim();
|
163
|
Matcher m = nomRefTokenizeP.matcher(nomRefStr);
|
164
|
if(m.matches()){
|
165
|
nomRefTitle = m.group(1);
|
166
|
nomRefDetail = m.group(2);
|
167
|
nomRefPupDate = m.group(3).trim();
|
168
|
|
169
|
// nomRefDetail.replaceAll("[\\:\\.\\s]", ""); // TODO integrate into nomRefTokenizeP
|
170
|
for(Pattern p : nomRefPubDatePs){
|
171
|
Matcher m2 = p.matcher(nomRefPupDate);
|
172
|
if(m2.matches()){
|
173
|
try {
|
174
|
nomRefPupYear = m2.group("year");
|
175
|
} catch (IllegalArgumentException e){
|
176
|
// named capture group not found
|
177
|
}
|
178
|
try {
|
179
|
nomRefPupMonth = m2.group("month");
|
180
|
} catch (IllegalArgumentException e){
|
181
|
// named capture group not found
|
182
|
}
|
183
|
try {
|
184
|
nomRefPupMonthName = m2.group("monthName");
|
185
|
nomRefPupMonth = monthFromName(nomRefPupMonthName, regNumber);
|
186
|
} catch (IllegalArgumentException e){
|
187
|
// named capture group not found
|
188
|
}
|
189
|
try {
|
190
|
nomRefPupDay = m2.group("day");
|
191
|
} catch (IllegalArgumentException e){
|
192
|
// named capture group not found
|
193
|
}
|
194
|
|
195
|
if(nomRefPupYear == null){
|
196
|
logger.error("nomRefPupYear in " + nomRefStr + " is NULL" );
|
197
|
}
|
198
|
if(nomRefPupYear.length() == 2 ){
|
199
|
// it is an abbreviated year from the 19** years
|
200
|
nomRefPupYear = "19" + nomRefPupYear;
|
201
|
}
|
202
|
nomRefTitle = nomRefTitle + ": " + nomRefDetail + ". " + nomRefPupYear + ".";
|
203
|
break;
|
204
|
}
|
205
|
}
|
206
|
if(nomRefPupYear == null){
|
207
|
logger.warn("Pub date not found in [" + regNumber + "]: " + nomRefPupDate + " from " + nomRefStr );
|
208
|
}
|
209
|
List<DateTimeFieldType> types = new ArrayList<>();
|
210
|
List<Integer> values = new ArrayList<>();
|
211
|
if(nomRefPupYear != null){
|
212
|
types.add(DateTimeFieldType.year());
|
213
|
values.add(Integer.parseInt(nomRefPupYear));
|
214
|
}
|
215
|
if(nomRefPupMonth != null){
|
216
|
types.add(DateTimeFieldType.monthOfYear());
|
217
|
values.add(Integer.parseInt(nomRefPupMonth));
|
218
|
}
|
219
|
if(nomRefPupDay != null){
|
220
|
types.add(DateTimeFieldType.dayOfMonth());
|
221
|
values.add(Integer.parseInt(nomRefPupDay));
|
222
|
}
|
223
|
Partial pupDate = new Partial(types.toArray(new DateTimeFieldType[types.size()]), ArrayUtils.toPrimitive(values.toArray(new Integer[values.size()])));
|
224
|
|
225
|
} else {
|
226
|
nomRefTitle = nomRefStr;
|
227
|
}
|
228
|
}
|
229
|
|
230
|
BotanicalName taxonName = makeBotanicalName(state, titleCacheStr, nameStr, authorStr, nomRefTitle);
|
231
|
|
232
|
if(!StringUtils.isEmpty(notesTxt)){
|
233
|
notesTxt = notesTxt.replace("Notes: ", "").trim();
|
234
|
taxonName.addAnnotation(Annotation.NewInstance(notesTxt, AnnotationType.EDITORIAL(), Language.DEFAULT()));
|
235
|
}
|
236
|
if(!StringUtils.isEmpty(caveats)){
|
237
|
caveats = caveats.replace("Caveats: ", "").trim();
|
238
|
taxonName.addAnnotation(Annotation.NewInstance(caveats, annotationTypeCaveats(), Language.DEFAULT()));
|
239
|
}
|
240
|
//
|
241
|
|
242
|
// Namerelations
|
243
|
if(!StringUtils.isEmpty(authorsSpelling)){
|
244
|
authorsSpelling = authorsSpelling.replaceFirst("Author's spelling:", "").replaceAll("\"", "").trim();
|
245
|
|
246
|
String[] authorSpellingTokens = StringUtils.split(authorsSpelling, " ");
|
247
|
String[] nameStrTokens = StringUtils.split(nameStr, " ");
|
248
|
|
249
|
ArrayUtils.reverse(authorSpellingTokens);
|
250
|
ArrayUtils.reverse(nameStrTokens);
|
251
|
|
252
|
for (int i = 0; i < nameStrTokens.length; i++){
|
253
|
if(i < authorSpellingTokens.length){
|
254
|
nameStrTokens[i] = authorSpellingTokens[i];
|
255
|
}
|
256
|
}
|
257
|
ArrayUtils.reverse(nameStrTokens);
|
258
|
|
259
|
String misspelledNameStr = StringUtils.join (nameStrTokens, ' ');
|
260
|
// build the fullnameString of the misspelled name
|
261
|
misspelledNameStr = taxonName.getTitleCache().replace(nameStr, misspelledNameStr);
|
262
|
|
263
|
TaxonNameBase misspelledName = (BotanicalName) nameParser.parseReferencedName(misspelledNameStr, NomenclaturalCode.ICNAFP, null);
|
264
|
misspelledName.addRelationshipToName(taxonName, NameRelationshipType.MISSPELLING(), null);
|
265
|
getNameService().save(misspelledName);
|
266
|
}
|
267
|
|
268
|
// Replaced Synonyms
|
269
|
if(!StringUtils.isEmpty(fullSynSubstStr)){
|
270
|
fullSynSubstStr = fullSynSubstStr.replace("Syn. subst.: ", "");
|
271
|
BotanicalName replacedSynonymName = makeBotanicalName(state, fullSynSubstStr, synSubstStr, null, null);
|
272
|
replacedSynonymName.addReplacedSynonym(taxonName, null, null, null);
|
273
|
getNameService().save(replacedSynonymName);
|
274
|
}
|
275
|
|
276
|
Reference sec = state.getConfig().getSecReference();
|
277
|
Taxon taxon = Taxon.NewInstance(taxonName, sec);
|
278
|
|
279
|
// Markers
|
280
|
if(isFossil){
|
281
|
taxon.addMarker(Marker.NewInstance(markerTypeFossil(), true));
|
282
|
}
|
283
|
|
284
|
// Types
|
285
|
if(!StringUtils.isEmpty(typeStr)){
|
286
|
Matcher m = typeSplitPattern.matcher(typeStr);
|
287
|
|
288
|
if(m.matches()){
|
289
|
String typeString = m.group(TypesName.type.name());
|
290
|
boolean isFieldUnit = typeStr.matches(".*([°']|\\d+\\s?m\\s|\\d+\\s?km\\s).*"); // check for location or unit m, km
|
291
|
|
292
|
if(isFieldUnit) {
|
293
|
// type as fieldUnit
|
294
|
FieldUnit fu = FieldUnit.NewInstance();
|
295
|
fu.setTitleCache(typeString, true);
|
296
|
getOccurrenceService().save(fu);
|
297
|
|
298
|
// all others ..
|
299
|
addSpecimenTypes(taxonName, fu, m.group(TypesName.holotype.name()), TypesName.holotype, false);
|
300
|
addSpecimenTypes(taxonName, fu, m.group(TypesName.isotype.name()), TypesName.isotype, true);
|
301
|
} else {
|
302
|
TaxonNameBase typeName = nameParser.parseFullName(typeString);
|
303
|
taxonName.addNameTypeDesignation(typeName, null, null, null, NameTypeDesignationStatus.AUTOMATIC(), true, true, true, true);
|
304
|
}
|
305
|
}
|
306
|
getNameService().save(taxonName);
|
307
|
|
308
|
}
|
309
|
|
310
|
getTaxonService().save(taxon);
|
311
|
if(higherTaxonNode != null){
|
312
|
higherTaxonNode.addChildTaxon(taxon, null, null);
|
313
|
getTaxonNodeService().save(higherTaxonNode);
|
314
|
}
|
315
|
|
316
|
return taxon;
|
317
|
|
318
|
}
|
319
|
|
320
|
private String monthFromName(String monthName, String regNumber) {
|
321
|
|
322
|
Integer month = monthFromNameMap.get(monthName.toLowerCase());
|
323
|
if(month == null){
|
324
|
logger.warn("Unknown month [" + regNumber + "]: " + monthName + " (" + monthName.toLowerCase() + ")");
|
325
|
return null;
|
326
|
} else {
|
327
|
return month.toString();
|
328
|
}
|
329
|
}
|
330
|
|
331
|
|
332
|
private void addSpecimenTypes(BotanicalName taxonName, FieldUnit fieldUnit, String typeStr, TypesName typeName, boolean multiple){
|
333
|
if(StringUtils.isEmpty(typeStr)){
|
334
|
return;
|
335
|
}
|
336
|
typeStr = typeStr.trim().replaceAll("\\.$", "");
|
337
|
|
338
|
List<String> typeData = new ArrayList<>();
|
339
|
if(multiple){
|
340
|
String[] tokens = typeStr.split("\\s?,\\s?");
|
341
|
for (String t : tokens) {
|
342
|
if(!t.isEmpty()){
|
343
|
typeData.add(t.trim());
|
344
|
}
|
345
|
}
|
346
|
} else {
|
347
|
typeData.add(typeStr.trim());
|
348
|
}
|
349
|
|
350
|
for(String type : typeData){
|
351
|
DerivedUnitFacade facade = DerivedUnitFacade.NewInstance(SpecimenOrObservationType.OtherSpecimen, fieldUnit);
|
352
|
facade.setTitleCache(type, true);
|
353
|
DerivedUnit specimen = facade.innerDerivedUnit();
|
354
|
taxonName.addSpecimenTypeDesignation(specimen, typeName.status(), null, null, null, false, true);
|
355
|
}
|
356
|
}
|
357
|
|
358
|
private BotanicalName makeBotanicalName(SimpleExcelTaxonImportState<CONFIG> state, String titleCacheStr, String nameStr,
|
359
|
String authorStr, String nomRefTitle) {
|
360
|
|
361
|
BotanicalName taxonName;// cache field for the taxonName.titleCache
|
362
|
String taxonNameTitleCache = null;
|
363
|
Map<String, AnnotationType> nameAnnotations = new HashMap<>();
|
364
|
|
365
|
String line = state.getCurrentLine() + ": ";
|
366
|
|
367
|
// TitleCache preprocessing
|
368
|
if(titleCacheStr.endsWith(ANNOTATION_MARKER_STRING) || (authorStr != null && authorStr.endsWith(ANNOTATION_MARKER_STRING))){
|
369
|
nameAnnotations.put("Author abbreviation not checked.", AnnotationType.EDITORIAL());
|
370
|
titleCacheStr = titleCacheStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
371
|
authorStr = authorStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
372
|
}
|
373
|
|
374
|
// parse the full taxon name
|
375
|
if(!StringUtils.isEmpty(nomRefTitle)){
|
376
|
String referenceSeparator = nomRefTitle.startsWith("in ") ? " " : ", ";
|
377
|
String taxonFullNameStr = titleCacheStr + referenceSeparator + nomRefTitle;
|
378
|
logger.debug(":::::" + taxonFullNameStr);
|
379
|
taxonName = (BotanicalName) nameParser.parseReferencedName(taxonFullNameStr, NomenclaturalCode.ICNAFP, null);
|
380
|
} else {
|
381
|
taxonName = (BotanicalName) nameParser.parseFullName(titleCacheStr, NomenclaturalCode.ICNAFP, null);
|
382
|
}
|
383
|
|
384
|
taxonNameTitleCache = taxonName.getTitleCache().trim();
|
385
|
if (taxonName.isProtectedTitleCache()) {
|
386
|
logger.warn(line + "Name could not be parsed: " + titleCacheStr);
|
387
|
} else {
|
388
|
|
389
|
boolean doRestoreTitleCacheStr = false;
|
390
|
|
391
|
// Check if titleCache and nameCache are plausible
|
392
|
String titleCacheCompareStr = titleCacheStr;
|
393
|
String nameCache = taxonName.getNameCache();
|
394
|
String nameCompareStr = nameStr;
|
395
|
if(taxonName.isBinomHybrid()){
|
396
|
titleCacheCompareStr = titleCacheCompareStr.replace(" x ", " ×");
|
397
|
nameCompareStr = nameCompareStr.replace(" x ", " ×");
|
398
|
}
|
399
|
if(taxonName.isMonomHybrid()){
|
400
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll("^X ", "× ");
|
401
|
nameCompareStr = nameCompareStr.replace("^X ", "× ");
|
402
|
}
|
403
|
if(authorStr != null && authorStr.contains(" et ")){
|
404
|
titleCacheCompareStr = titleCacheCompareStr.replaceAll(" et ", " & ");
|
405
|
}
|
406
|
if (!taxonNameTitleCache.equals(titleCacheCompareStr)) {
|
407
|
logger.warn(line + "The generated titleCache differs from the imported string : " + taxonNameTitleCache + " <> " + titleCacheStr + " will restore original titleCacheStr");
|
408
|
doRestoreTitleCacheStr = true;
|
409
|
}
|
410
|
if (!nameCache.trim().equals(nameCompareStr)) {
|
411
|
logger.warn(line + "The parsed nameCache differs from " + NAMESTRING + " : " + nameCache + " <> " + nameCompareStr);
|
412
|
}
|
413
|
|
414
|
// Author
|
415
|
//nameParser.handleAuthors(taxonName, titleCacheStr, authorStr);
|
416
|
//if (!titleCacheStr.equals(taxonName.getTitleCache())) {
|
417
|
// logger.warn(line + "titleCache has changed after setting authors, will restore original titleCacheStr");
|
418
|
// doRestoreTitleCacheStr = true;
|
419
|
//}
|
420
|
|
421
|
if(doRestoreTitleCacheStr){
|
422
|
taxonName.setTitleCache(titleCacheStr, true);
|
423
|
}
|
424
|
|
425
|
// deduplicate
|
426
|
replaceAuthorNamesAndNomRef(state, taxonName);
|
427
|
}
|
428
|
|
429
|
// Annotations
|
430
|
if(!nameAnnotations.isEmpty()){
|
431
|
for(String text : nameAnnotations.keySet()){
|
432
|
taxonName.addAnnotation(Annotation.NewInstance(text, nameAnnotations.get(text), Language.DEFAULT()));
|
433
|
}
|
434
|
getNameService().save(taxonName);
|
435
|
}
|
436
|
return taxonName;
|
437
|
}
|
438
|
|
439
|
/**
|
440
|
* @param state
|
441
|
* @return
|
442
|
*/
|
443
|
private TaxonNode getClassificationRootNode(IAPTImportState state) {
|
444
|
|
445
|
// Classification classification = state.getClassification();
|
446
|
// if (classification == null){
|
447
|
// IAPTImportConfigurator config = state.getConfig();
|
448
|
// classification = Classification.NewInstance(state.getConfig().getClassificationName());
|
449
|
// classification.setUuid(config.getClassificationUuid());
|
450
|
// classification.setReference(config.getSecReference());
|
451
|
// classification = getClassificationService().find(state.getConfig().getClassificationUuid());
|
452
|
// }
|
453
|
TaxonNode rootNode = state.getRootNode();
|
454
|
if (rootNode == null){
|
455
|
rootNode = getTaxonNodeService().find(ROOT_UUID);
|
456
|
}
|
457
|
if (rootNode == null){
|
458
|
Classification classification = state.getClassification();
|
459
|
if (classification == null){
|
460
|
Reference sec = state.getSecReference();
|
461
|
String classificationName = state.getConfig().getClassificationName();
|
462
|
Language language = Language.DEFAULT();
|
463
|
classification = Classification.NewInstance(classificationName, sec, language);
|
464
|
state.setClassification(classification);
|
465
|
classification.setUuid(state.getConfig().getClassificationUuid());
|
466
|
classification.getRootNode().setUuid(ROOT_UUID);
|
467
|
getClassificationService().save(classification);
|
468
|
}
|
469
|
rootNode = classification.getRootNode();
|
470
|
state.setRootNode(rootNode);
|
471
|
}
|
472
|
return rootNode;
|
473
|
}
|
474
|
|
475
|
|
476
|
/**
|
477
|
* @param record
|
478
|
* @param originalKey
|
479
|
* @param doUnescapeHtmlEntities
|
480
|
* @return
|
481
|
*/
|
482
|
private String getValue(HashMap<String, String> record, String originalKey, boolean doUnescapeHtmlEntities) {
|
483
|
String value = record.get(originalKey);
|
484
|
|
485
|
value = fixCharacters(value);
|
486
|
|
487
|
if (! StringUtils.isBlank(value)) {
|
488
|
if (logger.isDebugEnabled()) {
|
489
|
logger.debug(originalKey + ": " + value);
|
490
|
}
|
491
|
value = CdmUtils.removeDuplicateWhitespace(value.trim()).toString();
|
492
|
if(doUnescapeHtmlEntities){
|
493
|
value = StringEscapeUtils.unescapeHtml(value);
|
494
|
}
|
495
|
return value.trim();
|
496
|
}else{
|
497
|
return null;
|
498
|
}
|
499
|
}
|
500
|
|
501
|
/**
|
502
|
* Fixes broken characters.
|
503
|
* For details see
|
504
|
* http://dev.e-taxonomy.eu/redmine/issues/6035
|
505
|
*
|
506
|
* @param value
|
507
|
* @return
|
508
|
*/
|
509
|
private String fixCharacters(String value) {
|
510
|
|
511
|
value = StringUtils.replace(value, "s$K", "š");
|
512
|
value = StringUtils.replace(value, "n$K", "ň");
|
513
|
value = StringUtils.replace(value, "e$K", "ě");
|
514
|
value = StringUtils.replace(value, "r$K", "ř");
|
515
|
value = StringUtils.replace(value, "c$K", "č");
|
516
|
value = StringUtils.replace(value, "z$K", "ž");
|
517
|
value = StringUtils.replace(value, "S>U$K", "Š");
|
518
|
value = StringUtils.replace(value, "C>U$K", "Č");
|
519
|
value = StringUtils.replace(value, "R>U$K", "Ř");
|
520
|
value = StringUtils.replace(value, "Z>U$K", "Ž");
|
521
|
value = StringUtils.replace(value, "g$K", "ǧ");
|
522
|
value = StringUtils.replace(value, "s$A", "ś");
|
523
|
value = StringUtils.replace(value, "n$A", "ń");
|
524
|
value = StringUtils.replace(value, "c$A", "ć");
|
525
|
value = StringUtils.replace(value, "e$E", "ę");
|
526
|
value = StringUtils.replace(value, "o$H", "õ");
|
527
|
value = StringUtils.replace(value, "s$C", "ş");
|
528
|
value = StringUtils.replace(value, "t$C", "ț");
|
529
|
value = StringUtils.replace(value, "S>U$C", "Ş");
|
530
|
value = StringUtils.replace(value, "a$O", "å");
|
531
|
value = StringUtils.replace(value, "A>U$O", "Å");
|
532
|
value = StringUtils.replace(value, "u$O", "ů");
|
533
|
value = StringUtils.replace(value, "g$B", "ğ");
|
534
|
value = StringUtils.replace(value, "g$B", "ĕ");
|
535
|
value = StringUtils.replace(value, "a$B", "ă");
|
536
|
value = StringUtils.replace(value, "l$/", "ł");
|
537
|
value = StringUtils.replace(value, ">i", "ı");
|
538
|
value = StringUtils.replace(value, "i$U", "ï");
|
539
|
// Special-cases
|
540
|
value = StringUtils.replace(value, "ý", "ý");
|
541
|
value = StringUtils.replace(value, ">L", "Ł"); // corrected rule
|
542
|
value = StringUtils.replace(value, "E>U$D", "З");
|
543
|
value = StringUtils.replace(value, "S>U$E", "Ş");
|
544
|
value = StringUtils.replace(value, "s$E", "ş");
|
545
|
|
546
|
value = StringUtils.replace(value, "c$k", "č");
|
547
|
value = StringUtils.replace(value, " U$K", " Š");
|
548
|
|
549
|
return value;
|
550
|
}
|
551
|
|
552
|
|
553
|
/**
|
554
|
* Stores taxa records in DB
|
555
|
*/
|
556
|
@Override
|
557
|
protected void firstPass(SimpleExcelTaxonImportState<CONFIG> state) {
|
558
|
|
559
|
String lineNumber = state.getCurrentLine() + ": ";
|
560
|
logger.setLevel(Level.DEBUG);
|
561
|
HashMap<String, String> record = state.getOriginalRecord();
|
562
|
logger.debug(lineNumber + record.toString());
|
563
|
|
564
|
Set<String> keys = record.keySet();
|
565
|
for (String key: keys) {
|
566
|
if (! expectedKeys.contains(key)){
|
567
|
logger.warn(lineNumber + "Unexpected Key: " + key);
|
568
|
}
|
569
|
}
|
570
|
|
571
|
String reg_id = record.get(REGISTRATIONNO_PK);
|
572
|
|
573
|
//higherTaxon
|
574
|
String higherTaxaString = record.get(HIGHERTAXON);
|
575
|
boolean isFossil = false;
|
576
|
if(higherTaxaString.startsWith("FOSSIL ")){
|
577
|
higherTaxaString = higherTaxaString.replace("FOSSIL ", "");
|
578
|
isFossil = true;
|
579
|
}
|
580
|
TaxonNode higherTaxon = getHigherTaxon(higherTaxaString, (IAPTImportState)state);
|
581
|
|
582
|
//Taxon
|
583
|
Taxon taxon = makeTaxon(record, state, higherTaxon, isFossil);
|
584
|
if (taxon == null){
|
585
|
logger.warn(lineNumber + "taxon could not be created and is null");
|
586
|
return;
|
587
|
}
|
588
|
((IAPTImportState)state).setCurrentTaxon(taxon);
|
589
|
|
590
|
|
591
|
return;
|
592
|
}
|
593
|
|
594
|
private TaxonNode getHigherTaxon(String higherTaxaString, IAPTImportState state) {
|
595
|
String[] higherTaxaNames = higherTaxaString.toLowerCase().replaceAll("[\\[\\]]", "").split(":");
|
596
|
TaxonNode higherTaxonNode = null;
|
597
|
|
598
|
ITaxonTreeNode rootNode = getClassificationRootNode(state);
|
599
|
for (String htn : higherTaxaNames) {
|
600
|
htn = StringUtils.capitalize(htn.trim());
|
601
|
Taxon higherTaxon = state.getHigherTaxon(htn);
|
602
|
if (higherTaxon != null){
|
603
|
higherTaxonNode = higherTaxon.getTaxonNodes().iterator().next();
|
604
|
}else{
|
605
|
BotanicalName name = makeHigherTaxonName(state, htn);
|
606
|
Reference sec = state.getSecReference();
|
607
|
higherTaxon = Taxon.NewInstance(name, sec);
|
608
|
getTaxonService().save(higherTaxon);
|
609
|
higherTaxonNode = rootNode.addChildTaxon(higherTaxon, sec, null);
|
610
|
state.putHigherTaxon(htn, higherTaxon);
|
611
|
getClassificationService().saveTreeNode(higherTaxonNode);
|
612
|
}
|
613
|
rootNode = higherTaxonNode;
|
614
|
}
|
615
|
return higherTaxonNode;
|
616
|
}
|
617
|
|
618
|
private BotanicalName makeHigherTaxonName(IAPTImportState state, String name) {
|
619
|
|
620
|
Rank rank = guessRank(name);
|
621
|
|
622
|
BotanicalName taxonName = BotanicalName.NewInstance(rank);
|
623
|
taxonName.addSource(makeOriginalSource(state));
|
624
|
taxonName.setGenusOrUninomial(StringUtils.capitalize(name));
|
625
|
return taxonName;
|
626
|
}
|
627
|
|
628
|
private Rank guessRank(String name) {
|
629
|
|
630
|
// normalize
|
631
|
name = name.replaceAll("\\(.*\\)", "").trim();
|
632
|
|
633
|
if(name.matches("^Plantae$|^Fungi$")){
|
634
|
return Rank.KINGDOM();
|
635
|
} else if(name.matches("^Incertae sedis$|^No group assigned$")){
|
636
|
return rankFamilyIncertisSedis();
|
637
|
} else if(name.matches(".*phyta$|.*mycota$")){
|
638
|
return Rank.SECTION_BOTANY();
|
639
|
} else if(name.matches(".*phytina$|.*mycotina$")){
|
640
|
return Rank.SUBSECTION_BOTANY();
|
641
|
} else if(name.matches("Gymnospermae$|.*ones$")){ // Monocotyledones, Dicotyledones
|
642
|
return rankUnrankedSupraGeneric();
|
643
|
} else if(name.matches(".*opsida$|.*phyceae$|.*mycetes$|.*ones$|^Musci$|^Hepaticae$")){
|
644
|
return Rank.CLASS();
|
645
|
} else if(name.matches(".*idae$|.*phycidae$|.*mycetidae$")){
|
646
|
return Rank.SUBCLASS();
|
647
|
} else if(name.matches(".*ales$")){
|
648
|
return Rank.ORDER();
|
649
|
} else if(name.matches(".*ineae$")){
|
650
|
return Rank.SUBORDER();
|
651
|
} else if(name.matches(".*aceae$")){
|
652
|
return Rank.FAMILY();
|
653
|
} else if(name.matches(".*oideae$")){
|
654
|
return Rank.SUBFAMILY();
|
655
|
} else
|
656
|
// if(name.matches(".*eae$")){
|
657
|
// return Rank.TRIBE();
|
658
|
// } else
|
659
|
if(name.matches(".*inae$")){
|
660
|
return Rank.SUBTRIBE();
|
661
|
} else if(name.matches(".*ae$")){
|
662
|
return Rank.FAMILY();
|
663
|
}
|
664
|
return Rank.UNKNOWN_RANK();
|
665
|
}
|
666
|
|
667
|
private Rank rankUnrankedSupraGeneric() {
|
668
|
|
669
|
if(rankUnrankedSupraGeneric == null){
|
670
|
rankUnrankedSupraGeneric = Rank.NewInstance(RankClass.Suprageneric, "Unranked supra generic", " ", " ");
|
671
|
getTermService().save(rankUnrankedSupraGeneric);
|
672
|
}
|
673
|
return rankUnrankedSupraGeneric;
|
674
|
}
|
675
|
|
676
|
private Rank rankFamilyIncertisSedis() {
|
677
|
|
678
|
if(familyIncertisSedis == null){
|
679
|
familyIncertisSedis = Rank.NewInstance(RankClass.Suprageneric, "Family incertis sedis", " ", " ");
|
680
|
getTermService().save(familyIncertisSedis);
|
681
|
}
|
682
|
return familyIncertisSedis;
|
683
|
}
|
684
|
|
685
|
private AnnotationType annotationTypeCaveats(){
|
686
|
if(annotationTypeCaveats == null){
|
687
|
annotationTypeCaveats = AnnotationType.NewInstance("Caveats", "Caveats", "");
|
688
|
getTermService().save(annotationTypeCaveats);
|
689
|
}
|
690
|
return annotationTypeCaveats;
|
691
|
}
|
692
|
|
693
|
|
694
|
/**
|
695
|
* @param state
|
696
|
* @return
|
697
|
*/
|
698
|
private IdentifiableSource makeOriginalSource(IAPTImportState state) {
|
699
|
return IdentifiableSource.NewDataImportInstance("line: " + state.getCurrentLine(), null, state.getConfig().getSourceReference());
|
700
|
}
|
701
|
|
702
|
|
703
|
private Reference makeReference(IAPTImportState state, UUID uuidRef) {
|
704
|
Reference ref = state.getReference(uuidRef);
|
705
|
if (ref == null){
|
706
|
ref = getReferenceService().find(uuidRef);
|
707
|
state.putReference(uuidRef, ref);
|
708
|
}
|
709
|
return ref;
|
710
|
}
|
711
|
|
712
|
private MarkerType markerTypeFossil(){
|
713
|
if(this.markerTypeFossil == null){
|
714
|
markerTypeFossil = MarkerType.NewInstance("isFossilTaxon", "isFossil", null);
|
715
|
getTermService().save(this.markerTypeFossil);
|
716
|
}
|
717
|
return markerTypeFossil;
|
718
|
}
|
719
|
|
720
|
|
721
|
}
|