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.common.CdmUtils;
|
13
|
import eu.etaxonomy.cdm.io.mexico.SimpleExcelTaxonImport;
|
14
|
import eu.etaxonomy.cdm.io.mexico.SimpleExcelTaxonImportState;
|
15
|
import eu.etaxonomy.cdm.model.common.*;
|
16
|
import eu.etaxonomy.cdm.model.name.*;
|
17
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
18
|
import eu.etaxonomy.cdm.model.taxon.*;
|
19
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
20
|
import org.apache.commons.lang.StringEscapeUtils;
|
21
|
import org.apache.commons.lang.StringUtils;
|
22
|
import org.apache.log4j.Level;
|
23
|
import org.apache.log4j.Logger;
|
24
|
import org.springframework.stereotype.Component;
|
25
|
|
26
|
import java.util.*;
|
27
|
import java.util.regex.Matcher;
|
28
|
import java.util.regex.Pattern;
|
29
|
|
30
|
/**
|
31
|
* @author a.mueller
|
32
|
* @created 05.01.2016
|
33
|
*/
|
34
|
|
35
|
@Component("iAPTExcelImport")
|
36
|
public class IAPTExcelImport<CONFIG extends IAPTImportConfigurator> extends SimpleExcelTaxonImport<CONFIG> {
|
37
|
private static final long serialVersionUID = -747486709409732371L;
|
38
|
private static final Logger logger = Logger.getLogger(IAPTExcelImport.class);
|
39
|
public static final String ANNOTATION_MARKER_STRING = "[*]";
|
40
|
|
41
|
|
42
|
private static UUID ROOT_UUID = UUID.fromString("4137fd2a-20f6-4e70-80b9-f296daf51d82");
|
43
|
|
44
|
private static NonViralNameParserImpl nameParser = NonViralNameParserImpl.NewInstance();
|
45
|
|
46
|
private final static String REGISTRATIONNO_PK= "RegistrationNo_Pk";
|
47
|
private final static String HIGHERTAXON= "HigherTaxon";
|
48
|
private final static String FULLNAME= "FullName";
|
49
|
private final static String AUTHORSSPELLING= "AuthorsSpelling";
|
50
|
private final static String LITSTRING= "LitString";
|
51
|
private final static String REGISTRATION= "Registration";
|
52
|
private final static String TYPE= "Type";
|
53
|
private final static String CAVEATS= "Caveats";
|
54
|
private final static String FULLBASIONYM= "FullBasionym";
|
55
|
private final static String FULLSYNSUBST= "FullSynSubst";
|
56
|
private final static String NOTESTXT= "NotesTxt";
|
57
|
private final static String REGDATE= "RegDate";
|
58
|
private final static String NAMESTRING= "NameString";
|
59
|
private final static String BASIONYMSTRING= "BasionymString";
|
60
|
private final static String SYNSUBSTSTR= "SynSubstStr";
|
61
|
private final static String AUTHORSTRING= "AuthorString";
|
62
|
|
63
|
private static List<String> expectedKeys= Arrays.asList(new String[]{
|
64
|
REGISTRATIONNO_PK, HIGHERTAXON, FULLNAME, AUTHORSSPELLING, LITSTRING, REGISTRATION, TYPE, CAVEATS, FULLBASIONYM, FULLSYNSUBST, NOTESTXT, REGDATE, NAMESTRING, BASIONYMSTRING, SYNSUBSTSTR, AUTHORSTRING});
|
65
|
|
66
|
private static final Pattern nomRefTokenizeP = Pattern.compile("^(.*):\\s([^\\.:]+)\\.(.*)$");
|
67
|
private static final Pattern nomRefPubYearExtractP = Pattern.compile("(.*?)(1[7,8,9][0-9]{2}).*$|^.*?[0-9]{1,2}([\\./])[0-1]?[0-9]\\3([0-9]{2})\\.$"); // 1700 - 1999
|
68
|
|
69
|
private Taxon makeTaxon(HashMap<String, String> record, SimpleExcelTaxonImportState<CONFIG> state,
|
70
|
TaxonNode higherTaxonNode, boolean isSynonym) {
|
71
|
|
72
|
String line = state.getCurrentLine() + ": ";
|
73
|
|
74
|
String titleCacheStr = getValue(record, FULLNAME, true);
|
75
|
String nameStr = getValue(record, NAMESTRING, true);
|
76
|
String authorStr = getValue(record, AUTHORSTRING, true);
|
77
|
String nomRefStr = getValue(record, LITSTRING, true);
|
78
|
|
79
|
String nomRefTitle = null;
|
80
|
String nomRefDetail = null;
|
81
|
String nomRefPupDate = null;
|
82
|
String nomRefPupYear = null;
|
83
|
|
84
|
// preprocess nomRef: separate citation, reference detail, publishing date
|
85
|
if(!StringUtils.isEmpty(nomRefStr)){
|
86
|
nomRefStr = nomRefStr.trim();
|
87
|
Matcher m = nomRefTokenizeP.matcher(nomRefStr);
|
88
|
if(m.matches()){
|
89
|
nomRefTitle = m.group(1);
|
90
|
nomRefDetail = m.group(2);
|
91
|
nomRefPupDate = m.group(3);
|
92
|
|
93
|
// nomRefDetail.replaceAll("[\\:\\.\\s]", ""); // TODO integrate into nomRefTokenizeP
|
94
|
Matcher m2 = nomRefPubYearExtractP.matcher(nomRefPupDate);
|
95
|
if(m2.matches()){
|
96
|
nomRefPupYear = m2.group(2);
|
97
|
if(nomRefPupYear.length() == 2 ){
|
98
|
// it is an abbreviated year from the 19** years
|
99
|
nomRefPupYear = "19" + nomRefPupYear;
|
100
|
}
|
101
|
nomRefTitle = nomRefTitle + ": " + nomRefDetail + ". " + nomRefPupYear + ".";
|
102
|
} else {
|
103
|
logger.warn("Pub year not found in " + nomRefStr );
|
104
|
}
|
105
|
|
106
|
} else {
|
107
|
nomRefTitle = nomRefStr;
|
108
|
}
|
109
|
}
|
110
|
|
111
|
|
112
|
BotanicalName taxonName;
|
113
|
Map<String, AnnotationType> nameAnnotations = new HashMap<>();
|
114
|
|
115
|
if(titleCacheStr.endsWith(ANNOTATION_MARKER_STRING) && authorStr.endsWith(ANNOTATION_MARKER_STRING)){
|
116
|
nameAnnotations.put("Author abbreviation not checked.", AnnotationType.EDITORIAL());
|
117
|
titleCacheStr = titleCacheStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
118
|
authorStr = authorStr.replace(ANNOTATION_MARKER_STRING, "").trim();
|
119
|
}
|
120
|
|
121
|
if(!StringUtils.isEmpty(nomRefTitle)){
|
122
|
String referenceSeparator = nomRefTitle.startsWith("in ") ? " " : ", ";
|
123
|
String taxonFullNameStr = titleCacheStr + referenceSeparator + nomRefTitle;
|
124
|
logger.debug(":::::" + taxonFullNameStr);
|
125
|
taxonName = (BotanicalName) nameParser.parseReferencedName(taxonFullNameStr, NomenclaturalCode.ICNAFP, null);
|
126
|
} else {
|
127
|
taxonName = (BotanicalName) nameParser.parseFullName(titleCacheStr, NomenclaturalCode.ICNAFP, null);
|
128
|
}
|
129
|
|
130
|
if (taxonName.isProtectedTitleCache()) {
|
131
|
logger.warn(line + "Name could not be parsed: " + titleCacheStr);
|
132
|
} else {
|
133
|
|
134
|
boolean doRestoreTitleCacheStr = false;
|
135
|
// Check titleCache
|
136
|
String generatedTitleCache = taxonName.getTitleCache();
|
137
|
if (!generatedTitleCache.trim().equals(titleCacheStr)) {
|
138
|
logger.warn(line + "The generated titleCache differs from the imported string : " + generatedTitleCache + " <> " + titleCacheStr + " will restore original titleCacheStr");
|
139
|
doRestoreTitleCacheStr = true;
|
140
|
}
|
141
|
// Check Name
|
142
|
if (!taxonName.getNameCache().trim().equals(nameStr)) {
|
143
|
logger.warn(line + "parsed nameCache differs from " + NAMESTRING + " : " + taxonName.getNameCache() + " <> " + nameStr);
|
144
|
}
|
145
|
|
146
|
// Author
|
147
|
//nameParser.handleAuthors(taxonName, titleCacheStr, authorStr);
|
148
|
//if (!titleCacheStr.equals(taxonName.getTitleCache())) {
|
149
|
// logger.warn(line + "titleCache has changed after setting authors, will restore original titleCacheStr");
|
150
|
// doRestoreTitleCacheStr = true;
|
151
|
//}
|
152
|
|
153
|
if(doRestoreTitleCacheStr){
|
154
|
taxonName.setTitleCache(titleCacheStr, true);
|
155
|
}
|
156
|
|
157
|
// deduplicate
|
158
|
replaceAuthorNamesAndNomRef(state, taxonName);
|
159
|
|
160
|
// Annotations
|
161
|
if(!nameAnnotations.isEmpty()){
|
162
|
for(String text : nameAnnotations.keySet()){
|
163
|
taxonName.addAnnotation(Annotation.NewInstance(text, nameAnnotations.get(text), Language.DEFAULT()));
|
164
|
}
|
165
|
getNameService().save(taxonName);
|
166
|
}
|
167
|
}
|
168
|
|
169
|
Reference sec = state.getConfig().getSecReference();
|
170
|
Taxon taxon = Taxon.NewInstance(taxonName, sec);
|
171
|
getTaxonService().save(taxon);
|
172
|
if(higherTaxonNode != null){
|
173
|
higherTaxonNode.addChildTaxon(taxon, null, null);
|
174
|
getTaxonNodeService().save(higherTaxonNode);
|
175
|
}
|
176
|
|
177
|
return taxon;
|
178
|
|
179
|
}
|
180
|
|
181
|
/**
|
182
|
* @param state
|
183
|
* @return
|
184
|
*/
|
185
|
private TaxonNode getClassification(IAPTImportState state) {
|
186
|
|
187
|
Classification classification = state.getClassification();
|
188
|
if (classification == null){
|
189
|
IAPTImportConfigurator config = state.getConfig();
|
190
|
classification = Classification.NewInstance(state.getConfig().getClassificationName());
|
191
|
classification.setUuid(config.getClassificationUuid());
|
192
|
classification.setReference(config.getSecReference());
|
193
|
classification = getClassificationService().find(state.getConfig().getClassificationUuid());
|
194
|
}
|
195
|
TaxonNode rootNode = state.getRootNode();
|
196
|
if (rootNode == null){
|
197
|
rootNode = getTaxonNodeService().find(ROOT_UUID);
|
198
|
}
|
199
|
if (rootNode == null){
|
200
|
Reference sec = state.getSecReference();
|
201
|
if (classification == null){
|
202
|
String classificationName = state.getConfig().getClassificationName();
|
203
|
//TODO
|
204
|
Language language = Language.DEFAULT();
|
205
|
classification = Classification.NewInstance(classificationName, sec, language);
|
206
|
state.setClassification(classification);
|
207
|
classification.setUuid(state.getConfig().getClassificationUuid());
|
208
|
classification.getRootNode().setUuid(ROOT_UUID);
|
209
|
}
|
210
|
|
211
|
getClassificationService().save(classification);
|
212
|
rootNode = classification.getRootNode();
|
213
|
}
|
214
|
return rootNode;
|
215
|
}
|
216
|
|
217
|
|
218
|
/**
|
219
|
* @param record
|
220
|
* @param originalKey
|
221
|
* @param doUnescapeHtmlEntities
|
222
|
* @return
|
223
|
*/
|
224
|
private String getValue(HashMap<String, String> record, String originalKey, boolean doUnescapeHtmlEntities) {
|
225
|
String value = record.get(originalKey);
|
226
|
if (! StringUtils.isBlank(value)) {
|
227
|
if (logger.isDebugEnabled()) {
|
228
|
logger.debug(originalKey + ": " + value);
|
229
|
}
|
230
|
value = CdmUtils.removeDuplicateWhitespace(value.trim()).toString();
|
231
|
if(doUnescapeHtmlEntities){
|
232
|
value = StringEscapeUtils.unescapeHtml(value);
|
233
|
}
|
234
|
return value.trim();
|
235
|
}else{
|
236
|
return null;
|
237
|
}
|
238
|
}
|
239
|
|
240
|
|
241
|
|
242
|
/**
|
243
|
* Stores taxa records in DB
|
244
|
*/
|
245
|
@Override
|
246
|
protected void firstPass(SimpleExcelTaxonImportState<CONFIG> state) {
|
247
|
|
248
|
boolean isSynonymOnly = false;
|
249
|
|
250
|
String line = state.getCurrentLine() + ": ";
|
251
|
logger.setLevel(Level.DEBUG);
|
252
|
HashMap<String, String> record = state.getOriginalRecord();
|
253
|
logger.debug(record.toString());
|
254
|
|
255
|
Set<String> keys = record.keySet();
|
256
|
for (String key: keys) {
|
257
|
if (! expectedKeys.contains(key)){
|
258
|
logger.warn(line + "Unexpected Key: " + key);
|
259
|
}
|
260
|
}
|
261
|
|
262
|
String reg_id = record.get(REGISTRATIONNO_PK);
|
263
|
//higherTaxon
|
264
|
TaxonNode higherTaxon = getHigherTaxon(record, (IAPTImportState)state);
|
265
|
|
266
|
//Taxon
|
267
|
Taxon taxon = makeTaxon(record, state, higherTaxon, isSynonymOnly);
|
268
|
if (taxon == null && ! isSynonymOnly){
|
269
|
logger.warn(line + "taxon could not be created and is null");
|
270
|
return;
|
271
|
}
|
272
|
((IAPTImportState)state).setCurrentTaxon(taxon);
|
273
|
|
274
|
//(Notas)
|
275
|
//makeNotes(record, state);
|
276
|
|
277
|
//Syn.
|
278
|
//makeSynonyms(record, state, !isSynonymOnly);
|
279
|
|
280
|
|
281
|
return;
|
282
|
}
|
283
|
|
284
|
private TaxonNode getHigherTaxon(HashMap<String, String> record, IAPTImportState state) {
|
285
|
String higherTaxaString = record.get(HIGHERTAXON);
|
286
|
// higherTaxaString is like
|
287
|
// - DICOTYLEDONES: LEGUMINOSAE: MIMOSOIDEAE
|
288
|
// - FOSSIL DICOTYLEDONES: PROTEACEAE
|
289
|
// - [fungi]
|
290
|
// - [no group assigned]
|
291
|
if(higherTaxaString.equals("[no group assigned]")){
|
292
|
return null;
|
293
|
}
|
294
|
String[] higherTaxaNames = higherTaxaString.toLowerCase().replaceAll("[\\[\\]]", "").split(":");
|
295
|
TaxonNode higherTaxonNode = null;
|
296
|
|
297
|
ITaxonTreeNode rootNode = getClassification(state);
|
298
|
for (String htn : higherTaxaNames) {
|
299
|
htn = StringUtils.capitalize(htn.trim());
|
300
|
Taxon higherTaxon = state.getHigherTaxon(htn);
|
301
|
if (higherTaxon != null){
|
302
|
higherTaxonNode = higherTaxon.getTaxonNodes().iterator().next();
|
303
|
}else{
|
304
|
BotanicalName name = makeHigherTaxonName(state, htn);
|
305
|
Reference sec = state.getSecReference();
|
306
|
higherTaxon = Taxon.NewInstance(name, sec);
|
307
|
getTaxonService().save(higherTaxon);
|
308
|
higherTaxonNode = rootNode.addChildTaxon(higherTaxon, sec, null);
|
309
|
state.putHigherTaxon(htn, higherTaxon);
|
310
|
getClassificationService().saveTreeNode(higherTaxonNode);
|
311
|
}
|
312
|
rootNode = higherTaxonNode;
|
313
|
}
|
314
|
return higherTaxonNode;
|
315
|
}
|
316
|
|
317
|
private BotanicalName makeHigherTaxonName(IAPTImportState state, String name) {
|
318
|
|
319
|
Rank rank = guessRank(name);
|
320
|
|
321
|
BotanicalName taxonName = BotanicalName.NewInstance(rank);
|
322
|
taxonName.addSource(makeOriginalSource(state));
|
323
|
taxonName.setGenusOrUninomial(StringUtils.capitalize(name));
|
324
|
return taxonName;
|
325
|
}
|
326
|
|
327
|
private Rank guessRank(String name) {
|
328
|
|
329
|
// normalize
|
330
|
name = name.replaceAll("\\(.*\\)", "").trim();
|
331
|
|
332
|
if(name.matches("^Plantae$|^Fungi$|^Musci$")){
|
333
|
return Rank.KINGDOM();
|
334
|
} else if(name.matches(".*incertae sedis$|^Fossil no group assigned$")){
|
335
|
return Rank.FAMILY();
|
336
|
} else if(name.matches(".*phyta$|.*mycota$")){
|
337
|
return Rank.SECTION_BOTANY();
|
338
|
} else if(name.matches(".*phytina$|.*mycotina$")){
|
339
|
return Rank.SUBSECTION_BOTANY();
|
340
|
} else if(name.matches(".*opsida$|.*phyceae$|.*mycetes$|.*ones$")){
|
341
|
return Rank.CLASS();
|
342
|
} else if(name.matches(".*idae$|.*phycidae$|.*mycetidae$")){
|
343
|
return Rank.SUBCLASS();
|
344
|
} else if(name.matches(".*ales$")){
|
345
|
return Rank.ORDER();
|
346
|
} else if(name.matches(".*ineae$")){
|
347
|
return Rank.SUBORDER();
|
348
|
} else if(name.matches(".*oideae$")){
|
349
|
return Rank.SUBFAMILY();
|
350
|
} else if(name.matches(".*eae$")){
|
351
|
return Rank.TRIBE();
|
352
|
} else if(name.matches(".*inae$")){
|
353
|
return Rank.SUBTRIBE();
|
354
|
} else if(name.matches(".*ae$")){
|
355
|
return Rank.FAMILY();
|
356
|
}
|
357
|
return Rank.UNKNOWN_RANK();
|
358
|
}
|
359
|
|
360
|
|
361
|
/**
|
362
|
* @param state
|
363
|
* @return
|
364
|
*/
|
365
|
private IdentifiableSource makeOriginalSource(IAPTImportState state) {
|
366
|
return IdentifiableSource.NewDataImportInstance("line: " + state.getCurrentLine(), null, state.getConfig().getSourceReference());
|
367
|
}
|
368
|
|
369
|
|
370
|
private Reference makeReference(IAPTImportState state, UUID uuidRef) {
|
371
|
Reference ref = state.getReference(uuidRef);
|
372
|
if (ref == null){
|
373
|
ref = getReferenceService().find(uuidRef);
|
374
|
state.putReference(uuidRef, ref);
|
375
|
}
|
376
|
return ref;
|
377
|
}
|
378
|
|
379
|
|
380
|
|
381
|
}
|