|
1
|
/**
|
|
2
|
* Copyright (C) 2009 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.markup;
|
|
11
|
|
|
12
|
import java.util.HashMap;
|
|
13
|
import java.util.Map;
|
|
14
|
|
|
15
|
import javax.xml.stream.XMLEventReader;
|
|
16
|
import javax.xml.stream.XMLStreamException;
|
|
17
|
import javax.xml.stream.events.Attribute;
|
|
18
|
import javax.xml.stream.events.StartElement;
|
|
19
|
import javax.xml.stream.events.XMLEvent;
|
|
20
|
|
|
21
|
import org.apache.commons.lang.StringUtils;
|
|
22
|
import org.apache.log4j.Logger;
|
|
23
|
|
|
24
|
import eu.etaxonomy.cdm.model.agent.INomenclaturalAuthor;
|
|
25
|
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
|
|
26
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
|
27
|
import eu.etaxonomy.cdm.model.common.TimePeriod;
|
|
28
|
import eu.etaxonomy.cdm.model.description.Feature;
|
|
29
|
import eu.etaxonomy.cdm.model.description.TaxonDescription;
|
|
30
|
import eu.etaxonomy.cdm.model.description.TextData;
|
|
31
|
import eu.etaxonomy.cdm.model.name.HomotypicalGroup;
|
|
32
|
import eu.etaxonomy.cdm.model.name.NameTypeDesignationStatus;
|
|
33
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
|
|
34
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatusType;
|
|
35
|
import eu.etaxonomy.cdm.model.name.NonViralName;
|
|
36
|
import eu.etaxonomy.cdm.model.name.Rank;
|
|
37
|
import eu.etaxonomy.cdm.model.name.TaxonNameBase;
|
|
38
|
import eu.etaxonomy.cdm.model.reference.IArticle;
|
|
39
|
import eu.etaxonomy.cdm.model.reference.IJournal;
|
|
40
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
|
41
|
import eu.etaxonomy.cdm.model.reference.ReferenceFactory;
|
|
42
|
import eu.etaxonomy.cdm.model.reference.ReferenceType;
|
|
43
|
import eu.etaxonomy.cdm.model.taxon.SynonymRelationshipType;
|
|
44
|
import eu.etaxonomy.cdm.model.taxon.Taxon;
|
|
45
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
|
46
|
import eu.etaxonomy.cdm.strategy.parser.NameTypeParser;
|
|
47
|
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl;
|
|
48
|
|
|
49
|
/**
|
|
50
|
* @author a.mueller
|
|
51
|
* @created 30.05.2012
|
|
52
|
*
|
|
53
|
*/
|
|
54
|
public class MarkupNomenclatureImport extends MarkupImportBase {
|
|
55
|
@SuppressWarnings("unused")
|
|
56
|
private static final Logger logger = Logger.getLogger(MarkupNomenclatureImport.class);
|
|
57
|
|
|
58
|
|
|
59
|
private NonViralNameParserImpl parser = new NonViralNameParserImpl();
|
|
60
|
|
|
61
|
private MarkupKeyImport keyImport;
|
|
62
|
private MarkupSpecimenImport specimenImport;
|
|
63
|
|
|
64
|
public MarkupNomenclatureImport(MarkupDocumentImport docImport,
|
|
65
|
MarkupKeyImport keyImport, MarkupSpecimenImport specimenImport) {
|
|
66
|
super(docImport);
|
|
67
|
this.keyImport = keyImport;
|
|
68
|
this.specimenImport = specimenImport;
|
|
69
|
}
|
|
70
|
|
|
71
|
public void handleNomenclature(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent)
|
|
72
|
throws XMLStreamException {
|
|
73
|
checkNoAttributes(parentEvent);
|
|
74
|
|
|
75
|
while (reader.hasNext()) {
|
|
76
|
XMLEvent next = readNoWhitespace(reader);
|
|
77
|
if (isStartingElement(next, HOMOTYPES)) {
|
|
78
|
handleHomotypes(state, reader, next.asStartElement());
|
|
79
|
} else if (isMyEndingElement(next, parentEvent)) {
|
|
80
|
return;
|
|
81
|
} else {
|
|
82
|
fireSchemaConflictEventExpectedStartTag(HOMOTYPES, reader);
|
|
83
|
state.setUnsuccessfull();
|
|
84
|
}
|
|
85
|
}
|
|
86
|
return;
|
|
87
|
}
|
|
88
|
|
|
89
|
private void handleHomotypes(MarkupImportState state,
|
|
90
|
XMLEventReader reader, StartElement parentEvent)
|
|
91
|
throws XMLStreamException {
|
|
92
|
checkNoAttributes(parentEvent);
|
|
93
|
|
|
94
|
HomotypicalGroup homotypicalGroup = null;
|
|
95
|
|
|
96
|
boolean hasNom = false;
|
|
97
|
while (reader.hasNext()) {
|
|
98
|
XMLEvent next = readNoWhitespace(reader);
|
|
99
|
if (next.isEndElement()) {
|
|
100
|
if (isMyEndingElement(next, parentEvent)) {
|
|
101
|
checkMandatoryElement(hasNom, parentEvent, NOM);
|
|
102
|
return;
|
|
103
|
} else {
|
|
104
|
if (isEndingElement(next, NAME_TYPE)) {
|
|
105
|
state.setNameType(false);
|
|
106
|
} else if (isEndingElement(next, NOTES)) {
|
|
107
|
// NOT YET IMPLEMENTED
|
|
108
|
popUnimplemented(next.asEndElement());
|
|
109
|
} else {
|
|
110
|
handleUnexpectedEndElement(next.asEndElement());
|
|
111
|
}
|
|
112
|
}
|
|
113
|
} else if (next.isStartElement()) {
|
|
114
|
if (isStartingElement(next, NOM)) {
|
|
115
|
NonViralName<?> name = handleNom(state, reader, next, homotypicalGroup);
|
|
116
|
homotypicalGroup = name.getHomotypicalGroup();
|
|
117
|
hasNom = true;
|
|
118
|
} else if (isStartingElement(next, NAME_TYPE)) {
|
|
119
|
state.setNameType(true);
|
|
120
|
handleNameType(state, reader, next, homotypicalGroup);
|
|
121
|
} else if (isStartingElement(next, SPECIMEN_TYPE)) {
|
|
122
|
specimenImport.handleSpecimenType(state, reader, next,
|
|
123
|
homotypicalGroup);
|
|
124
|
} else if (isStartingElement(next, NOTES)) {
|
|
125
|
handleNotYetImplementedElement(next);
|
|
126
|
} else {
|
|
127
|
handleUnexpectedStartElement(next);
|
|
128
|
}
|
|
129
|
} else {
|
|
130
|
handleUnexpectedElement(next);
|
|
131
|
}
|
|
132
|
}
|
|
133
|
// TODO handle missing end element
|
|
134
|
throw new IllegalStateException("Homotypes has no closing tag");
|
|
135
|
|
|
136
|
}
|
|
137
|
|
|
138
|
private void handleNameType(MarkupImportState state, XMLEventReader reader,
|
|
139
|
XMLEvent parentEvent, HomotypicalGroup homotypicalGroup)
|
|
140
|
throws XMLStreamException {
|
|
141
|
Map<String, Attribute> attributes = getAttributes(parentEvent);
|
|
142
|
String typeStatus = getAndRemoveAttributeValue(attributes, TYPE_STATUS);
|
|
143
|
checkNoAttributes(attributes, parentEvent);
|
|
144
|
|
|
145
|
NameTypeDesignationStatus status;
|
|
146
|
try {
|
|
147
|
status = NameTypeParser.parseNameTypeStatus(typeStatus);
|
|
148
|
} catch (UnknownCdmTypeException e) {
|
|
149
|
String message = "Type status could not be recognized: %s";
|
|
150
|
message = String.format(message, typeStatus);
|
|
151
|
fireWarningEvent(message, parentEvent, 4);
|
|
152
|
status = null;
|
|
153
|
}
|
|
154
|
|
|
155
|
boolean hasNom = false;
|
|
156
|
while (reader.hasNext()) {
|
|
157
|
XMLEvent next = readNoWhitespace(reader);
|
|
158
|
if (next.isEndElement()) {
|
|
159
|
if (isMyEndingElement(next, parentEvent)) {
|
|
160
|
checkMandatoryElement(hasNom, parentEvent.asStartElement(),
|
|
161
|
NOM);
|
|
162
|
state.setNameType(false);
|
|
163
|
return;
|
|
164
|
} else {
|
|
165
|
if (isEndingElement(next, ACCEPTED_NAME)) {
|
|
166
|
// NOT YET IMPLEMENTED
|
|
167
|
popUnimplemented(next.asEndElement());
|
|
168
|
} else {
|
|
169
|
handleUnexpectedEndElement(next.asEndElement());
|
|
170
|
}
|
|
171
|
}
|
|
172
|
} else if (next.isStartElement()) {
|
|
173
|
if (isStartingElement(next, NOM)) {
|
|
174
|
// TODO should we check if the type is always a species, is
|
|
175
|
// this a rule?
|
|
176
|
NonViralName<?> speciesName = handleNom(state, reader,
|
|
177
|
next, null);
|
|
178
|
for (TaxonNameBase<?, ?> name : homotypicalGroup
|
|
179
|
.getTypifiedNames()) {
|
|
180
|
name.addNameTypeDesignation(speciesName, null, null,
|
|
181
|
null, status, false, false, false, false);
|
|
182
|
}
|
|
183
|
hasNom = true;
|
|
184
|
} else if (isStartingElement(next, ACCEPTED_NAME)) {
|
|
185
|
handleNotYetImplementedElement(next);
|
|
186
|
} else {
|
|
187
|
handleUnexpectedStartElement(next);
|
|
188
|
}
|
|
189
|
} else {
|
|
190
|
handleUnexpectedElement(next);
|
|
191
|
}
|
|
192
|
}
|
|
193
|
// TODO handle missing end element
|
|
194
|
throw new IllegalStateException("Homotypes has no closing tag");
|
|
195
|
|
|
196
|
}
|
|
197
|
|
|
198
|
/**
|
|
199
|
* Creates the name defined by a nom tag. Adds it to the given homotypical
|
|
200
|
* group (if not null).
|
|
201
|
*
|
|
202
|
* @param state
|
|
203
|
* @param reader
|
|
204
|
* @param parentEvent
|
|
205
|
* @param homotypicalGroup
|
|
206
|
* @return
|
|
207
|
* @throws XMLStreamException
|
|
208
|
*/
|
|
209
|
private NonViralName<?> handleNom(MarkupImportState state,
|
|
210
|
XMLEventReader reader, XMLEvent parentEvent,
|
|
211
|
HomotypicalGroup homotypicalGroup) throws XMLStreamException {
|
|
212
|
boolean isSynonym = false;
|
|
213
|
boolean isNameType = state.isNameType();
|
|
214
|
// attributes
|
|
215
|
String classValue = getClassOnlyAttribute(parentEvent);
|
|
216
|
NonViralName<?> name;
|
|
217
|
if (!isNameType && ACCEPTED.equalsIgnoreCase(classValue)) {
|
|
218
|
isSynonym = false;
|
|
219
|
name = createName(state, homotypicalGroup, isSynonym);
|
|
220
|
} else if (!isNameType && SYNONYM.equalsIgnoreCase(classValue)) {
|
|
221
|
isSynonym = true;
|
|
222
|
name = createName(state, homotypicalGroup, isSynonym);
|
|
223
|
} else if (isNameType && NAME_TYPE.equalsIgnoreCase(classValue)) {
|
|
224
|
// TODO do we need to define the rank here?
|
|
225
|
name = createNameByCode(state, null);
|
|
226
|
} else {
|
|
227
|
fireUnexpectedAttributeValue(parentEvent, CLASS, classValue);
|
|
228
|
name = createNameByCode(state, null);
|
|
229
|
}
|
|
230
|
|
|
231
|
Map<String, String> nameMap = new HashMap<String, String>();
|
|
232
|
String text = "";
|
|
233
|
|
|
234
|
while (reader.hasNext()) {
|
|
235
|
XMLEvent next = readNoWhitespace(reader);
|
|
236
|
if (isMyEndingElement(next, parentEvent)) {
|
|
237
|
// fill the name with all data gathered
|
|
238
|
fillName(state, nameMap, name, next);
|
|
239
|
handleNomText(state, parentEvent, text, isNameType);
|
|
240
|
return name;
|
|
241
|
} else if (isEndingElement(next, ANNOTATION)) {
|
|
242
|
// NOT YET IMPLEMENTED //TODO test
|
|
243
|
// handleSimpleAnnotation
|
|
244
|
popUnimplemented(next.asEndElement());
|
|
245
|
}else if (isStartingElement(next, FULL_NAME)) {
|
|
246
|
handleFullName(state, reader, name, next);
|
|
247
|
} else if (isStartingElement(next, NUM)) {
|
|
248
|
handleNomNum(state, reader, next);
|
|
249
|
} else if (isStartingElement(next, NAME)) {
|
|
250
|
handleName(state, reader, next, nameMap);
|
|
251
|
} else if (isStartingElement(next, CITATION)) {
|
|
252
|
handleCitation(state, reader, next, name);
|
|
253
|
} else if (next.isCharacters()) {
|
|
254
|
text += next.asCharacters().getData();
|
|
255
|
} else if (isStartingElement(next, HOMONYM)) {
|
|
256
|
handleNotYetImplementedElement(next);
|
|
257
|
} else if (isStartingElement(next, NOTES)) {
|
|
258
|
handleNotYetImplementedElement(next);
|
|
259
|
} else if (isStartingElement(next, ANNOTATION)) {
|
|
260
|
handleNotYetImplementedElement(next);
|
|
261
|
} else {
|
|
262
|
handleUnexpectedElement(next);
|
|
263
|
}
|
|
264
|
}
|
|
265
|
// TODO handle missing end element
|
|
266
|
throw new IllegalStateException("Nom has no closing tag");
|
|
267
|
}
|
|
268
|
|
|
269
|
/**
|
|
270
|
* Handles appearance of text within <nom> tags.
|
|
271
|
* Usually this is not expected except for some information that is already handled
|
|
272
|
* elsewhere, e.g. the string Nametype is holding information that is available already
|
|
273
|
* via the surrounding nametype tag. Therefore this information can be neglected.
|
|
274
|
* This method is open for upcoming cases which need to be handled.
|
|
275
|
* @param state
|
|
276
|
* @param event
|
|
277
|
* @param text
|
|
278
|
* @param isNameType
|
|
279
|
*/
|
|
280
|
private void handleNomText(MarkupImportState state, XMLEvent event, String text, boolean isNameType) {
|
|
281
|
if (isBlank(text)){
|
|
282
|
return;
|
|
283
|
}
|
|
284
|
text = text.trim();
|
|
285
|
//neglect known redundant strings
|
|
286
|
if (isNameType && text.matches("(?i)^Esp[\u00E8\u00C8]ce[·\\-\\s]type\\:$")){
|
|
287
|
return;
|
|
288
|
}//neglect meaningless punctuation
|
|
289
|
else if (isPunctuation(text)){
|
|
290
|
return;
|
|
291
|
}else{
|
|
292
|
String message = "Unhandled text in <nom> tag: \"%s\"";
|
|
293
|
fireWarningEvent(String.format(message, text), event, 4);
|
|
294
|
}
|
|
295
|
}
|
|
296
|
|
|
297
|
/**
|
|
298
|
* @param state
|
|
299
|
* @param reader
|
|
300
|
* @param next
|
|
301
|
* @throws XMLStreamException
|
|
302
|
*/
|
|
303
|
private void handleNomNum(MarkupImportState state, XMLEventReader reader,
|
|
304
|
XMLEvent next) throws XMLStreamException {
|
|
305
|
String num = getCData(state, reader, next);
|
|
306
|
num = num.replace(".", "");
|
|
307
|
num = num.replace(")", "");
|
|
308
|
if (StringUtils.isNotBlank(num)) {
|
|
309
|
if (state.getCurrentTaxonNum() != null
|
|
310
|
&& !state.getCurrentTaxonNum().equals(num)) {
|
|
311
|
String message = "Taxontitle num and homotypes/nom/num differ ( %s <-> %s ). I use the later one.";
|
|
312
|
message = String.format(message,
|
|
313
|
state.getCurrentTaxonNum(), num);
|
|
314
|
fireWarningEvent(message, next, 4);
|
|
315
|
}
|
|
316
|
state.setCurrentTaxonNum(num);
|
|
317
|
}
|
|
318
|
}
|
|
319
|
|
|
320
|
/**
|
|
321
|
* @param state
|
|
322
|
* @param reader
|
|
323
|
* @param name
|
|
324
|
* @param next
|
|
325
|
* @throws XMLStreamException
|
|
326
|
*/
|
|
327
|
private void handleFullName(MarkupImportState state, XMLEventReader reader,
|
|
328
|
NonViralName<?> name, XMLEvent next) throws XMLStreamException {
|
|
329
|
String fullNameStr;
|
|
330
|
Map<String, Attribute> attrs = getAttributes(next);
|
|
331
|
String rankStr = getAndRemoveRequiredAttributeValue(next,
|
|
332
|
attrs, "rank");
|
|
333
|
Rank rank = makeRank(state, rankStr, false);
|
|
334
|
name.setRank(rank);
|
|
335
|
if (rank == null) {
|
|
336
|
String message = "Rank was computed as null. This must not be.";
|
|
337
|
fireWarningEvent(message, next, 6);
|
|
338
|
name.setRank(Rank.UNKNOWN_RANK());
|
|
339
|
}
|
|
340
|
if (!attrs.isEmpty()) {
|
|
341
|
handleUnexpectedAttributes(next.getLocation(), attrs);
|
|
342
|
}
|
|
343
|
fullNameStr = getCData(state, reader, next);
|
|
344
|
name.setTitleCache(fullNameStr, true);
|
|
345
|
}
|
|
346
|
|
|
347
|
private void handleName(MarkupImportState state, XMLEventReader reader,
|
|
348
|
XMLEvent parentEvent, Map<String, String> nameMap)
|
|
349
|
throws XMLStreamException {
|
|
350
|
String classValue = getClassOnlyAttribute(parentEvent);
|
|
351
|
|
|
352
|
String text = "";
|
|
353
|
while (reader.hasNext()) {
|
|
354
|
XMLEvent next = readNoWhitespace(reader);
|
|
355
|
if (isMyEndingElement(next, parentEvent)) {
|
|
356
|
nameMap.put(classValue, text);
|
|
357
|
return;
|
|
358
|
} else if (isStartingElement(next, ANNOTATION)) {
|
|
359
|
handleNotYetImplementedElement(next); // TODO test
|
|
360
|
// handleSimpleAnnotation
|
|
361
|
} else if (next.isCharacters()) {
|
|
362
|
text += next.asCharacters().getData();
|
|
363
|
} else {
|
|
364
|
handleUnexpectedElement(next);
|
|
365
|
}
|
|
366
|
}
|
|
367
|
throw new IllegalStateException("name has no closing tag");
|
|
368
|
}
|
|
369
|
|
|
370
|
private void fillName(MarkupImportState state, Map<String, String> nameMap,
|
|
371
|
NonViralName<?> name, XMLEvent event) {
|
|
372
|
|
|
373
|
// Ranks: family, subfamily, tribus, genus, subgenus, section,
|
|
374
|
// subsection, species, subspecies, variety, subvariety, forma
|
|
375
|
// infrank, paraut, author, infrparaut, infraut, status, notes
|
|
376
|
|
|
377
|
String infrank = getAndRemoveMapKey(nameMap, INFRANK);
|
|
378
|
String authorStr = getAndRemoveMapKey(nameMap, AUTHOR);
|
|
379
|
String paraut = getAndRemoveMapKey(nameMap, PARAUT);
|
|
380
|
|
|
381
|
String infrParAut = getAndRemoveMapKey(nameMap, INFRPARAUT);
|
|
382
|
String infrAut = getAndRemoveMapKey(nameMap, INFRAUT);
|
|
383
|
|
|
384
|
String statusStr = getAndRemoveMapKey(nameMap, STATUS);
|
|
385
|
String notes = getAndRemoveMapKey(nameMap, NOTES);
|
|
386
|
|
|
387
|
if (!name.isProtectedTitleCache()) { // otherwise fullName
|
|
388
|
|
|
389
|
makeRankDecision(state, nameMap, name, event, infrank);
|
|
390
|
|
|
391
|
// test consistency of rank and authors
|
|
392
|
testRankAuthorConsistency(name, event, authorStr, paraut,
|
|
393
|
infrParAut, infrAut);
|
|
394
|
|
|
395
|
// authors
|
|
396
|
makeNomenclaturalAuthors(name, event, authorStr, paraut,
|
|
397
|
infrParAut, infrAut);
|
|
398
|
}
|
|
399
|
|
|
400
|
// status
|
|
401
|
// TODO handle pro parte, pro syn. etc.
|
|
402
|
if (StringUtils.isNotBlank(statusStr)) {
|
|
403
|
String proPartePattern = "(pro parte|p.p.)";
|
|
404
|
if (statusStr.matches(proPartePattern)) {
|
|
405
|
state.setProParte(true);
|
|
406
|
}
|
|
407
|
try {
|
|
408
|
// TODO handle trim earlier
|
|
409
|
statusStr = statusStr.trim();
|
|
410
|
NomenclaturalStatusType nomStatusType = NomenclaturalStatusType
|
|
411
|
.getNomenclaturalStatusTypeByAbbreviation(statusStr);
|
|
412
|
name.addStatus(NomenclaturalStatus.NewInstance(nomStatusType));
|
|
413
|
} catch (UnknownCdmTypeException e) {
|
|
414
|
String message = "Status '%s' could not be recognized";
|
|
415
|
message = String.format(message, statusStr);
|
|
416
|
fireWarningEvent(message, event, 4);
|
|
417
|
}
|
|
418
|
}
|
|
419
|
|
|
420
|
// notes
|
|
421
|
if (StringUtils.isNotBlank(notes)) {
|
|
422
|
handleNotYetImplementedAttributeValue(event, CLASS, NOTES);
|
|
423
|
}
|
|
424
|
|
|
425
|
return;
|
|
426
|
}
|
|
427
|
|
|
428
|
/**
|
|
429
|
* @param state
|
|
430
|
* @param nameMap
|
|
431
|
* @param name
|
|
432
|
* @param event
|
|
433
|
* @param infrankStr
|
|
434
|
*/
|
|
435
|
private void makeRankDecision(MarkupImportState state,
|
|
436
|
Map<String, String> nameMap, NonViralName<?> name, XMLEvent event,
|
|
437
|
String infrankStr) {
|
|
438
|
// TODO ranks
|
|
439
|
for (String key : nameMap.keySet()) {
|
|
440
|
Rank rank = makeRank(state, key, false);
|
|
441
|
if (rank == null) {
|
|
442
|
handleNotYetImplementedAttributeValue(event, CLASS, key);
|
|
443
|
} else {
|
|
444
|
if (name.getRank() == null || rank.isLower(name.getRank())) {
|
|
445
|
name.setRank(rank);
|
|
446
|
}
|
|
447
|
String value = nameMap.get(key);
|
|
448
|
if (rank.isSupraGeneric() || rank.isGenus()) {
|
|
449
|
if ((key.equalsIgnoreCase(GENUS_ABBREVIATION)
|
|
450
|
&& isNotBlank(state.getLatestGenusEpithet()) || isGenusAbbrev(
|
|
451
|
value, state.getLatestGenusEpithet()))) {
|
|
452
|
value = state.getLatestGenusEpithet();
|
|
453
|
}
|
|
454
|
name.setGenusOrUninomial(toFirstCapital(value));
|
|
455
|
} else if (rank.isInfraGeneric()) {
|
|
456
|
name.setInfraGenericEpithet(toFirstCapital(value));
|
|
457
|
} else if (rank.isSpecies()) {
|
|
458
|
if (state.getConfig().isAllowCapitalSpeciesEpithet()
|
|
459
|
&& isFirstCapitalWord(value)) { // capital letters
|
|
460
|
// are allowed for
|
|
461
|
// species epithet
|
|
462
|
// in case of person
|
|
463
|
// names (e.g.
|
|
464
|
// Manilkara
|
|
465
|
// Welwitschii Engl.
|
|
466
|
name.setSpecificEpithet(value);
|
|
467
|
} else {
|
|
468
|
name.setSpecificEpithet(value.toLowerCase());
|
|
469
|
}
|
|
470
|
} else if (rank.isInfraSpecific()) {
|
|
471
|
name.setInfraSpecificEpithet(value.toLowerCase());
|
|
472
|
} else {
|
|
473
|
String message = "Invalid rank '%s'. Can't decide which epithet to fill with '%s'";
|
|
474
|
message = String.format(message, rank.getTitleCache(),
|
|
475
|
value);
|
|
476
|
fireWarningEvent(message, event, 4);
|
|
477
|
}
|
|
478
|
}
|
|
479
|
|
|
480
|
}
|
|
481
|
// handle given infrank marker
|
|
482
|
if (StringUtils.isNotBlank(infrankStr)) {
|
|
483
|
Rank infRank = makeRank(state, infrankStr, true);
|
|
484
|
|
|
485
|
if (infRank == null) {
|
|
486
|
String message = "Infrank '%s' rank not recognized";
|
|
487
|
message = String.format(message, infrankStr);
|
|
488
|
fireWarningEvent(message, event, 4);
|
|
489
|
} else {
|
|
490
|
if (name.getRank() == null) {
|
|
491
|
name.setRank(infRank);
|
|
492
|
} else if (infRank.isLower(name.getRank())) {
|
|
493
|
String message = "InfRank '%s' is lower than existing rank ";
|
|
494
|
message = String.format(message, infrankStr);
|
|
495
|
fireWarningEvent(message, event, 2);
|
|
496
|
name.setRank(infRank);
|
|
497
|
} else if (infRank.equals(name.getRank())) {
|
|
498
|
// nothing
|
|
499
|
} else {
|
|
500
|
String message = "InfRank '%s' is higher than existing rank ";
|
|
501
|
message = String.format(message, infrankStr);
|
|
502
|
fireWarningEvent(message, event, 2);
|
|
503
|
}
|
|
504
|
}
|
|
505
|
}
|
|
506
|
}
|
|
507
|
|
|
508
|
/**
|
|
509
|
* @param name
|
|
510
|
* @param event
|
|
511
|
* @param authorStr
|
|
512
|
* @param paraut
|
|
513
|
* @param infrParAut
|
|
514
|
* @param infrAut
|
|
515
|
*/
|
|
516
|
private void makeNomenclaturalAuthors(NonViralName name, XMLEvent event,
|
|
517
|
String authorStr, String paraut, String infrParAut, String infrAut) {
|
|
518
|
if (name.getRank() != null && name.getRank().isInfraSpecific()) {
|
|
519
|
if (StringUtils.isNotBlank(infrAut)) {
|
|
520
|
INomenclaturalAuthor[] authorAndEx = authorAndEx(infrAut, event);
|
|
521
|
name.setCombinationAuthorTeam(authorAndEx[0]);
|
|
522
|
name.setExCombinationAuthorTeam(authorAndEx[1]);
|
|
523
|
}
|
|
524
|
if (StringUtils.isNotBlank(infrParAut)) {
|
|
525
|
INomenclaturalAuthor[] authorAndEx = authorAndEx(infrParAut,
|
|
526
|
event);
|
|
527
|
name.setBasionymAuthorTeam(authorAndEx[0]);
|
|
528
|
name.setExBasionymAuthorTeam(authorAndEx[1]);
|
|
529
|
}
|
|
530
|
} else {
|
|
531
|
if (name.getRank() == null) {
|
|
532
|
String message = "No rank defined. Check correct usage of authors!";
|
|
533
|
fireWarningEvent(message, event, 4);
|
|
534
|
if (isNotBlank(infrParAut) || isNotBlank(infrAut)) {
|
|
535
|
authorStr = infrAut;
|
|
536
|
paraut = infrParAut;
|
|
537
|
}
|
|
538
|
}
|
|
539
|
if (StringUtils.isNotBlank(authorStr)) {
|
|
540
|
INomenclaturalAuthor[] authorAndEx = authorAndEx(authorStr,
|
|
541
|
event);
|
|
542
|
name.setCombinationAuthorTeam(authorAndEx[0]);
|
|
543
|
name.setExCombinationAuthorTeam(authorAndEx[1]);
|
|
544
|
}
|
|
545
|
if (StringUtils.isNotBlank(paraut)) {
|
|
546
|
INomenclaturalAuthor[] authorAndEx = authorAndEx(paraut, event);
|
|
547
|
name.setBasionymAuthorTeam(authorAndEx[0]);
|
|
548
|
name.setExBasionymAuthorTeam(authorAndEx[1]);
|
|
549
|
}
|
|
550
|
}
|
|
551
|
}
|
|
552
|
|
|
553
|
private TeamOrPersonBase[] authorAndEx(String authorAndEx, XMLEvent xmlEvent) {
|
|
554
|
authorAndEx = authorAndEx.trim();
|
|
555
|
TeamOrPersonBase[] result = new TeamOrPersonBase[2];
|
|
556
|
|
|
557
|
String[] split = authorAndEx.split("\\sex\\s");
|
|
558
|
if (split.length > 2) {
|
|
559
|
String message = "There is more then 1 ' ex ' in author string. Can't separate author and ex-author";
|
|
560
|
fireWarningEvent(message, xmlEvent, 4);
|
|
561
|
result[0] = createAuthor(authorAndEx);
|
|
562
|
} else if (split.length == 2) {
|
|
563
|
result[0] = createAuthor(split[1]);
|
|
564
|
result[1] = createAuthor(split[0]);
|
|
565
|
} else {
|
|
566
|
result[0] = createAuthor(split[0]);
|
|
567
|
}
|
|
568
|
return result;
|
|
569
|
}
|
|
570
|
|
|
571
|
/**
|
|
572
|
* Returns the (empty) name with the correct homotypical group depending on
|
|
573
|
* the taxon status. Throws NPE if no currentTaxon is set in state.
|
|
574
|
*
|
|
575
|
* @param state
|
|
576
|
* @param homotypicalGroup
|
|
577
|
* @param isSynonym
|
|
578
|
* @return
|
|
579
|
*/
|
|
580
|
private NonViralName<?> createName(MarkupImportState state,
|
|
581
|
HomotypicalGroup homotypicalGroup, boolean isSynonym) {
|
|
582
|
NonViralName<?> name;
|
|
583
|
Taxon taxon = state.getCurrentTaxon();
|
|
584
|
if (isSynonym) {
|
|
585
|
Rank defaultRank = Rank.SPECIES(); // can be any
|
|
586
|
name = createNameByCode(state, defaultRank);
|
|
587
|
if (homotypicalGroup != null) {
|
|
588
|
name.setHomotypicalGroup(homotypicalGroup);
|
|
589
|
}
|
|
590
|
SynonymRelationshipType synonymType = SynonymRelationshipType
|
|
591
|
.HETEROTYPIC_SYNONYM_OF();
|
|
592
|
if (taxon.getHomotypicGroup().equals(homotypicalGroup)) {
|
|
593
|
synonymType = SynonymRelationshipType.HOMOTYPIC_SYNONYM_OF();
|
|
594
|
}
|
|
595
|
taxon.addSynonymName(name, synonymType);
|
|
596
|
} else {
|
|
597
|
name = CdmBase.deproxy(taxon.getName(), NonViralName.class);
|
|
598
|
}
|
|
599
|
return name;
|
|
600
|
}
|
|
601
|
|
|
602
|
private void handleCitation(MarkupImportState state, XMLEventReader reader,
|
|
603
|
XMLEvent parentEvent, NonViralName name) throws XMLStreamException {
|
|
604
|
String classValue = getClassOnlyAttribute(parentEvent);
|
|
605
|
|
|
606
|
state.setCitation(true);
|
|
607
|
boolean hasRefPart = false;
|
|
608
|
Map<String, String> refMap = new HashMap<String, String>();
|
|
609
|
while (reader.hasNext()) {
|
|
610
|
XMLEvent next = readNoWhitespace(reader);
|
|
611
|
if (isMyEndingElement(next, parentEvent)) {
|
|
612
|
checkMandatoryElement(hasRefPart, parentEvent.asStartElement(),
|
|
613
|
REF_PART);
|
|
614
|
Reference<?> reference = createReference(state, refMap, next);
|
|
615
|
String microReference = refMap.get(DETAILS);
|
|
616
|
doCitation(state, name, classValue, reference, microReference,
|
|
617
|
parentEvent);
|
|
618
|
state.setCitation(false);
|
|
619
|
return;
|
|
620
|
} else if (isStartingElement(next, REF_PART)) {
|
|
621
|
handleRefPart(state, reader, next, refMap);
|
|
622
|
hasRefPart = true;
|
|
623
|
} else {
|
|
624
|
handleUnexpectedElement(next);
|
|
625
|
}
|
|
626
|
}
|
|
627
|
throw new IllegalStateException("Citation has no closing tag");
|
|
628
|
|
|
629
|
}
|
|
630
|
|
|
631
|
private void handleRefPart(MarkupImportState state, XMLEventReader reader,
|
|
632
|
XMLEvent parentEvent, Map<String, String> refMap)
|
|
633
|
throws XMLStreamException {
|
|
634
|
String classValue = getClassOnlyAttribute(parentEvent);
|
|
635
|
|
|
636
|
String text = "";
|
|
637
|
while (reader.hasNext()) {
|
|
638
|
XMLEvent next = readNoWhitespace(reader);
|
|
639
|
if (isMyEndingElement(next, parentEvent)) {
|
|
640
|
refMap.put(classValue, text);
|
|
641
|
return;
|
|
642
|
} else if (next.isStartElement()) {
|
|
643
|
if (isStartingElement(next, ANNOTATION)) {
|
|
644
|
handleNotYetImplementedElement(next); // TODO test
|
|
645
|
// handleSimpleAnnotation
|
|
646
|
} else if (isStartingElement(next, ITALICS)) {
|
|
647
|
handleNotYetImplementedElement(next);
|
|
648
|
} else if (isStartingElement(next, BOLD)) {
|
|
649
|
handleNotYetImplementedElement(next);
|
|
650
|
} else {
|
|
651
|
handleUnexpectedStartElement(next.asStartElement());
|
|
652
|
}
|
|
653
|
} else if (next.isCharacters()) {
|
|
654
|
text += next.asCharacters().getData();
|
|
655
|
} else {
|
|
656
|
handleUnexpectedEndElement(next.asEndElement());
|
|
657
|
}
|
|
658
|
}
|
|
659
|
throw new IllegalStateException("RefPart has no closing tag");
|
|
660
|
|
|
661
|
}
|
|
662
|
|
|
663
|
private void doCitation(MarkupImportState state, NonViralName name,
|
|
664
|
String classValue, Reference reference, String microCitation,
|
|
665
|
XMLEvent parentEvent) {
|
|
666
|
if (PUBLICATION.equalsIgnoreCase(classValue)) {
|
|
667
|
name.setNomenclaturalReference(reference);
|
|
668
|
name.setNomenclaturalMicroReference(microCitation);
|
|
669
|
} else if (USAGE.equalsIgnoreCase(classValue)) {
|
|
670
|
Taxon taxon = state.getCurrentTaxon();
|
|
671
|
TaxonDescription td = getTaxonDescription(taxon, state.getConfig()
|
|
672
|
.getSourceReference(), false, true);
|
|
673
|
TextData citation = TextData.NewInstance(Feature.CITATION());
|
|
674
|
// TODO name used in source
|
|
675
|
citation.addSource(null, null, reference, microCitation);
|
|
676
|
td.addElement(citation);
|
|
677
|
} else if (TYPE.equalsIgnoreCase(classValue)) {
|
|
678
|
handleNotYetImplementedAttributeValue(parentEvent, CLASS,
|
|
679
|
classValue);
|
|
680
|
} else {
|
|
681
|
// TODO Not yet implemented
|
|
682
|
handleNotYetImplementedAttributeValue(parentEvent, CLASS,
|
|
683
|
classValue);
|
|
684
|
}
|
|
685
|
}
|
|
686
|
|
|
687
|
/**
|
|
688
|
* Tests if the names rank is consistent with the given author strings.
|
|
689
|
* NOTE: Tags for authors are differ depending on the rank.
|
|
690
|
*
|
|
691
|
* @param name
|
|
692
|
* @param event
|
|
693
|
* @param authorStr
|
|
694
|
* @param paraut
|
|
695
|
* @param infrParAut
|
|
696
|
* @param infrAut
|
|
697
|
*/
|
|
698
|
private void testRankAuthorConsistency(NonViralName name, XMLEvent event,
|
|
699
|
String authorStr, String paraut, String infrParAut, String infrAut) {
|
|
700
|
if (name.getRank() == null) {
|
|
701
|
return;
|
|
702
|
}
|
|
703
|
if (name.getRank().isInfraSpecific()) {
|
|
704
|
if (StringUtils.isBlank(infrParAut)
|
|
705
|
&& StringUtils.isBlank(infrAut) // was isNotBlank before
|
|
706
|
// 29.5.2012
|
|
707
|
&& (StringUtils.isNotBlank(paraut) || StringUtils
|
|
708
|
.isNotBlank(authorStr)) && !name.isAutonym()) {
|
|
709
|
String message = "Rank is infraspecicific but has only specific or higher author(s)";
|
|
710
|
fireWarningEvent(message, event, 4);
|
|
711
|
}
|
|
712
|
} else {
|
|
713
|
// is not infraspecific
|
|
714
|
if (StringUtils.isNotBlank(infrParAut)
|
|
715
|
|| StringUtils.isNotBlank(infrAut)) {
|
|
716
|
String message = "Rank is not infraspecicific but name has infra author(s)";
|
|
717
|
fireWarningEvent(message, event, 4);
|
|
718
|
}
|
|
719
|
}
|
|
720
|
}
|
|
721
|
|
|
722
|
private Reference<?> createReference(MarkupImportState state,
|
|
723
|
Map<String, String> refMap, XMLEvent parentEvent) {
|
|
724
|
// TODO
|
|
725
|
Reference<?> reference;
|
|
726
|
|
|
727
|
String type = getAndRemoveMapKey(refMap, PUBTYPE);
|
|
728
|
String authorStr = getAndRemoveMapKey(refMap, AUTHOR);
|
|
729
|
String titleStr = getAndRemoveMapKey(refMap, PUBTITLE);
|
|
730
|
String titleCache = getAndRemoveMapKey(refMap, PUBFULLNAME);
|
|
731
|
String volume = getAndRemoveMapKey(refMap, VOLUME);
|
|
732
|
String edition = getAndRemoveMapKey(refMap, EDITION);
|
|
733
|
String editors = getAndRemoveMapKey(refMap, EDITORS);
|
|
734
|
String year = getAndRemoveMapKey(refMap, YEAR);
|
|
735
|
String pubName = getAndRemoveMapKey(refMap, PUBNAME);
|
|
736
|
String pages = getAndRemoveMapKey(refMap, PAGES);
|
|
737
|
|
|
738
|
if (state.isCitation()) {
|
|
739
|
if (volume != null || "journal".equalsIgnoreCase(type)) {
|
|
740
|
IArticle article = ReferenceFactory.newArticle();
|
|
741
|
if (pubName != null) {
|
|
742
|
IJournal journal = ReferenceFactory.newJournal();
|
|
743
|
journal.setTitle(pubName);
|
|
744
|
article.setInJournal(journal);
|
|
745
|
}
|
|
746
|
reference = (Reference<?>) article;
|
|
747
|
|
|
748
|
} else {
|
|
749
|
// TODO
|
|
750
|
if (pubName != null) {
|
|
751
|
reference = ReferenceFactory.newBookSection();
|
|
752
|
} else {
|
|
753
|
reference = ReferenceFactory.newBook();
|
|
754
|
}
|
|
755
|
}
|
|
756
|
// TODO use existing author from name or before
|
|
757
|
TeamOrPersonBase<?> author = createAuthor(authorStr);
|
|
758
|
reference.setAuthorTeam(author);
|
|
759
|
|
|
760
|
reference.setTitle(titleStr);
|
|
761
|
if (StringUtils.isNotBlank(titleCache)) {
|
|
762
|
reference.setTitleCache(titleCache, true);
|
|
763
|
}
|
|
764
|
reference.setEdition(edition);
|
|
765
|
reference.setEditor(editors);
|
|
766
|
|
|
767
|
if (pubName != null) {
|
|
768
|
Reference<?> inReference;
|
|
769
|
if (reference.getType().equals(ReferenceType.Article)) {
|
|
770
|
inReference = ReferenceFactory.newJournal();
|
|
771
|
} else {
|
|
772
|
inReference = ReferenceFactory.newGeneric();
|
|
773
|
}
|
|
774
|
inReference.setTitle(pubName);
|
|
775
|
reference.setInReference(inReference);
|
|
776
|
}
|
|
777
|
|
|
778
|
} else { // no citation
|
|
779
|
if (volume != null || "journal".equalsIgnoreCase(type)) {
|
|
780
|
IArticle article = ReferenceFactory.newArticle();
|
|
781
|
if (pubName != null) {
|
|
782
|
IJournal journal = ReferenceFactory.newJournal();
|
|
783
|
journal.setTitle(pubName);
|
|
784
|
article.setInJournal(journal);
|
|
785
|
}
|
|
786
|
reference = (Reference<?>) article;
|
|
787
|
|
|
788
|
} else {
|
|
789
|
Reference<?> bookOrPartOf = ReferenceFactory.newGeneric();
|
|
790
|
reference = bookOrPartOf;
|
|
791
|
}
|
|
792
|
|
|
793
|
// TODO type
|
|
794
|
TeamOrPersonBase<?> author = createAuthor(authorStr);
|
|
795
|
reference.setAuthorTeam(author);
|
|
796
|
|
|
797
|
reference.setTitle(titleStr);
|
|
798
|
if (StringUtils.isNotBlank(titleCache)) {
|
|
799
|
reference.setTitleCache(titleCache, true);
|
|
800
|
}
|
|
801
|
reference.setEdition(edition);
|
|
802
|
reference.setEditor(editors);
|
|
803
|
|
|
804
|
if (pubName != null) {
|
|
805
|
Reference<?> inReference;
|
|
806
|
if (reference.getType().equals(ReferenceType.Article)) {
|
|
807
|
inReference = ReferenceFactory.newJournal();
|
|
808
|
} else {
|
|
809
|
inReference = ReferenceFactory.newGeneric();
|
|
810
|
}
|
|
811
|
inReference.setTitle(pubName);
|
|
812
|
reference.setInReference(inReference);
|
|
813
|
}
|
|
814
|
}
|
|
815
|
reference.setVolume(volume);
|
|
816
|
reference.setDatePublished(TimePeriod.parseString(year));
|
|
817
|
// TODO check if this is handled correctly in FM markup
|
|
818
|
reference.setPages(pages);
|
|
819
|
|
|
820
|
// TODO
|
|
821
|
String[] unhandledList = new String[] { ALTERNATEPUBTITLE, ISSUE,
|
|
822
|
NOTES, STATUS };
|
|
823
|
for (String unhandled : unhandledList) {
|
|
824
|
String value = getAndRemoveMapKey(refMap, unhandled);
|
|
825
|
if (isNotBlank(value)) {
|
|
826
|
this.handleNotYetImplementedAttributeValue(parentEvent, CLASS,
|
|
827
|
unhandled);
|
|
828
|
}
|
|
829
|
}
|
|
830
|
|
|
831
|
for (String key : refMap.keySet()) {
|
|
832
|
if (!DETAILS.equalsIgnoreCase(key)) {
|
|
833
|
this.fireUnexpectedAttributeValue(parentEvent, CLASS, key);
|
|
834
|
}
|
|
835
|
}
|
|
836
|
|
|
837
|
return reference;
|
|
838
|
}
|
|
839
|
|
|
840
|
public Reference<?> handleReference(MarkupImportState state,
|
|
841
|
XMLEventReader reader, XMLEvent parentEvent)
|
|
842
|
throws XMLStreamException {
|
|
843
|
checkNoAttributes(parentEvent);
|
|
844
|
|
|
845
|
boolean hasRefPart = false;
|
|
846
|
Map<String, String> refMap = new HashMap<String, String>();
|
|
847
|
while (reader.hasNext()) {
|
|
848
|
XMLEvent next = readNoWhitespace(reader);
|
|
849
|
if (isMyEndingElement(next, parentEvent)) {
|
|
850
|
checkMandatoryElement(hasRefPart, parentEvent.asStartElement(),
|
|
851
|
REF_PART);
|
|
852
|
Reference<?> reference = createReference(state, refMap, next);
|
|
853
|
return reference;
|
|
854
|
} else if (isStartingElement(next, REF_PART)) {
|
|
855
|
handleRefPart(state, reader, next, refMap);
|
|
856
|
hasRefPart = true;
|
|
857
|
} else {
|
|
858
|
handleUnexpectedElement(next);
|
|
859
|
}
|
|
860
|
}
|
|
861
|
// TODO handle missing end element
|
|
862
|
throw new IllegalStateException("<Reference> has no closing tag");
|
|
863
|
}
|
|
864
|
|
|
865
|
}
|