|
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
|
package eu.etaxonomy.cdm.io.markup;
|
|
10
|
|
|
11
|
import java.util.ArrayList;
|
|
12
|
import java.util.HashSet;
|
|
13
|
import java.util.List;
|
|
14
|
import java.util.Map;
|
|
15
|
import java.util.Set;
|
|
16
|
import java.util.UUID;
|
|
17
|
|
|
18
|
import javax.xml.stream.XMLEventReader;
|
|
19
|
import javax.xml.stream.XMLStreamException;
|
|
20
|
import javax.xml.stream.events.Attribute;
|
|
21
|
import javax.xml.stream.events.XMLEvent;
|
|
22
|
|
|
23
|
import org.apache.commons.lang.StringUtils;
|
|
24
|
import org.apache.logging.log4j.LogManager;
|
|
25
|
import org.apache.logging.log4j.Logger;
|
|
26
|
|
|
27
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
|
28
|
import eu.etaxonomy.cdm.io.common.mapping.UndefinedTransformerMethodException;
|
|
29
|
import eu.etaxonomy.cdm.model.common.AnnotatableEntity;
|
|
30
|
import eu.etaxonomy.cdm.model.common.Annotation;
|
|
31
|
import eu.etaxonomy.cdm.model.common.AnnotationType;
|
|
32
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
|
33
|
import eu.etaxonomy.cdm.model.common.IntextReference;
|
|
34
|
import eu.etaxonomy.cdm.model.common.Language;
|
|
35
|
import eu.etaxonomy.cdm.model.common.LanguageString;
|
|
36
|
import eu.etaxonomy.cdm.model.common.MarkerType;
|
|
37
|
import eu.etaxonomy.cdm.model.description.CommonTaxonName;
|
|
38
|
import eu.etaxonomy.cdm.model.description.DescriptionElementBase;
|
|
39
|
import eu.etaxonomy.cdm.model.description.Feature;
|
|
40
|
import eu.etaxonomy.cdm.model.description.TaxonDescription;
|
|
41
|
import eu.etaxonomy.cdm.model.description.TextData;
|
|
42
|
import eu.etaxonomy.cdm.model.location.Country;
|
|
43
|
import eu.etaxonomy.cdm.model.location.NamedArea;
|
|
44
|
import eu.etaxonomy.cdm.model.media.Media;
|
|
45
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
|
46
|
import eu.etaxonomy.cdm.model.taxon.Taxon;
|
|
47
|
import eu.etaxonomy.cdm.model.term.TermVocabulary;
|
|
48
|
|
|
49
|
/**
|
|
50
|
* @author a.mueller
|
|
51
|
* @since 30.05.2012
|
|
52
|
*/
|
|
53
|
public class MarkupFeatureImport extends MarkupImportBase {
|
|
54
|
|
|
55
|
@SuppressWarnings("unused")
|
|
56
|
private static final Logger logger = LogManager.getLogger(MarkupFeatureImport.class);
|
|
57
|
|
|
58
|
protected static final String MODS_TITLEINFO = "titleInfo";
|
|
59
|
|
|
60
|
private final MarkupSpecimenImport specimenImport;
|
|
61
|
private final MarkupNomenclatureImport nomenclatureImport;
|
|
62
|
private final MarkupKeyImport keyImport;
|
|
63
|
|
|
64
|
public MarkupFeatureImport(MarkupDocumentImport docImport, MarkupSpecimenImport specimenImport,
|
|
65
|
MarkupNomenclatureImport nomenclatureImport, MarkupKeyImport keyImport) {
|
|
66
|
super(docImport);
|
|
67
|
this.specimenImport = specimenImport;
|
|
68
|
this.nomenclatureImport = nomenclatureImport;
|
|
69
|
this.keyImport = keyImport;
|
|
70
|
this.featureImport = this;
|
|
71
|
}
|
|
72
|
|
|
73
|
public void handleFeature(MarkupImportState state, XMLEventReader readerOrig, XMLEvent parentEvent) throws XMLStreamException {
|
|
74
|
Map<String, Attribute> attrs = getAttributes(parentEvent);
|
|
75
|
Boolean isFreetext = getAndRemoveBooleanAttributeValue(parentEvent, attrs, IS_FREETEXT, false);
|
|
76
|
String classValue =getAndRemoveRequiredAttributeValue(parentEvent, attrs, CLASS);
|
|
77
|
checkNoAttributes(attrs, parentEvent);
|
|
78
|
|
|
79
|
Reference sourceReference = state.getConfig().getSourceReference();
|
|
80
|
Feature feature = makeFeature(classValue, state, parentEvent, null);
|
|
81
|
Taxon taxon = state.getCurrentTaxon();
|
|
82
|
TaxonDescription taxonDescription = getDefaultTaxonDescription(taxon, NO_IMAGE_GALLERY, CREATE_NEW, sourceReference);
|
|
83
|
if (!taxonDescription.isDefault()){
|
|
84
|
taxonDescription.setDefault(true);
|
|
85
|
}
|
|
86
|
// TextData figureHolderTextData = null; //for use with one TextData for
|
|
87
|
// all figure only
|
|
88
|
|
|
89
|
|
|
90
|
TaxonDescription structuredDescription = null;
|
|
91
|
|
|
92
|
boolean isDescription = feature.equals(Feature.DESCRIPTION());
|
|
93
|
|
|
94
|
XMLEventReader reader;
|
|
95
|
if (isDescription){
|
|
96
|
LookAheadEventReader lookAhead = new LookAheadEventReader(parentEvent.asStartElement(), readerOrig);
|
|
97
|
String descriptionText = makeFullDescriptionText(lookAhead.getCachedEvents(true));
|
|
98
|
TextData descriptionTextData = TextData.NewInstance(Feature.DESCRIPTION(), descriptionText, getDefaultLanguage(state),null);
|
|
99
|
descriptionTextData.addPrimaryTaxonomicSource(sourceReference);
|
|
100
|
taxonDescription.addElement(descriptionTextData);
|
|
101
|
reader = lookAhead;
|
|
102
|
}else{
|
|
103
|
reader = readerOrig;
|
|
104
|
}
|
|
105
|
|
|
106
|
DescriptionElementBase lastDescriptionElement = null;
|
|
107
|
|
|
108
|
CharOrder charOrder= new CharOrder();
|
|
109
|
while (reader.hasNext()) {
|
|
110
|
XMLEvent next = readNoWhitespace(reader);
|
|
111
|
if (isMyEndingElement(next, parentEvent)) {
|
|
112
|
state.putFeatureToGeneralSorterList(feature);
|
|
113
|
return;
|
|
114
|
} else if (isEndingElement(next, DISTRIBUTION_LIST) || isEndingElement(next, HABITAT_LIST)) {
|
|
115
|
// only handle list elements
|
|
116
|
} else if (isStartingElement(next, HEADING)) {
|
|
117
|
makeFeatureHeading(state, reader, classValue, feature, next);
|
|
118
|
} else if (isStartingElement(next, WRITER)) {
|
|
119
|
makeFeatureWriter(state, reader, feature, taxon, next);
|
|
120
|
// } else if (isStartingElement(next, DISTRIBUTION_LOCALITY)) {
|
|
121
|
// if (!feature.equals(Feature.DISTRIBUTION())) {
|
|
122
|
// String message = "Distribution locality only allowed for feature of type 'distribution'";
|
|
123
|
// fireWarningEvent(message, next, 4);
|
|
124
|
// }
|
|
125
|
// handleDistributionLocality(state, reader, next);
|
|
126
|
} else if (isStartingElement(next, DISTRIBUTION_LIST) || isStartingElement(next, HABITAT_LIST)) {
|
|
127
|
// only handle single list elements
|
|
128
|
} else if (isStartingElement(next, HABITAT)) {
|
|
129
|
if (!(feature.equals(Feature.HABITAT())
|
|
130
|
|| feature.equals(Feature.HABITAT_ECOLOGY())
|
|
131
|
|| feature.equals(Feature.ECOLOGY()))) {
|
|
132
|
String message = "Habitat only allowed for feature of type 'habitat','habitat ecology' or 'ecology'";
|
|
133
|
fireWarningEvent(message, next, 4);
|
|
134
|
}
|
|
135
|
String habitatString = handleHabitat(state, reader, next);
|
|
136
|
fireWarningEvent("Return value from habitat tag not yet handled: " + habitatString, next, 4);
|
|
137
|
} else if (isStartingElement(next, CHAR)) {
|
|
138
|
if (structuredDescription == null){
|
|
139
|
MarkerType descriptionMarker;
|
|
140
|
try {
|
|
141
|
descriptionMarker = getMarkerType(state, state.getTransformer().getMarkerTypeUuid("structured description"),
|
|
142
|
"Structured Descriptions", "Marker to mark descriptions used for more structured descriptions", null, null);
|
|
143
|
} catch (UndefinedTransformerMethodException e) {
|
|
144
|
throw new RuntimeException(e);
|
|
145
|
}
|
|
146
|
String title = "Structured descriptive data for " + taxon.getName().getTitleCache();
|
|
147
|
structuredDescription = getMarkedTaxonDescription(taxon, descriptionMarker, NO_IMAGE_GALLERY, CREATE_NEW, state.getConfig().getSourceReference(), title);
|
|
148
|
}
|
|
149
|
List<TextData> textDataList = handleChar(state, reader, next, null, charOrder);
|
|
150
|
charOrder = charOrder.next();
|
|
151
|
for (TextData textData : textDataList){
|
|
152
|
structuredDescription.addElement(textData);
|
|
153
|
}
|
|
154
|
} else if (isStartingElement(next, STRING)) {
|
|
155
|
lastDescriptionElement = makeFeatureString(state, reader, feature,
|
|
156
|
taxonDescription, lastDescriptionElement, next, isFreetext);
|
|
157
|
} else if (isStartingElement(next, FIGURE_REF)) {
|
|
158
|
lastDescriptionElement = makeFeatureFigureRef(state, reader,
|
|
159
|
taxonDescription, isDescription, lastDescriptionElement, sourceReference, next);
|
|
160
|
} else if (isStartingElement(next, REFERENCES)) {
|
|
161
|
fireWarningEvent("Check correct handling of feature references", next, 4);
|
|
162
|
List<Reference> refs = handleReferences(state, reader, next);
|
|
163
|
if (!refs.isEmpty()) {
|
|
164
|
// TODO
|
|
165
|
Reference descriptionRef = state.getConfig().getSourceReference();
|
|
166
|
TaxonDescription description = getDefaultTaxonDescription(taxon, false, true, descriptionRef);
|
|
167
|
TextData featurePlaceholder = docImport.getFeaturePlaceholder(state, description, feature, true);
|
|
168
|
for (Reference citation : refs) {
|
|
169
|
featurePlaceholder.addPrimaryTaxonomicSource(citation);
|
|
170
|
}
|
|
171
|
} else {
|
|
172
|
String message = "No reference found in references";
|
|
173
|
fireWarningEvent(message, next, 6);
|
|
174
|
}
|
|
175
|
} else if (isStartingElement(next, NUM)) {
|
|
176
|
//TODO
|
|
177
|
handleNotYetImplementedElement(next);
|
|
178
|
} else if (isStartingElement(next, KEY)) {
|
|
179
|
keyImport.handleKey(state, reader, next);
|
|
180
|
} else {
|
|
181
|
handleUnexpectedElement(next);
|
|
182
|
}
|
|
183
|
}
|
|
184
|
throw new IllegalStateException("<Feature> has no closing tag");
|
|
185
|
}
|
|
186
|
|
|
187
|
|
|
188
|
/**
|
|
189
|
* Creates a full description text from the mark
|
|
190
|
*/
|
|
191
|
private String makeFullDescriptionText(List<XMLEvent> events) {
|
|
192
|
String result = "";
|
|
193
|
for (XMLEvent event : events){
|
|
194
|
String text = normalize(event.asCharacters().getData());
|
|
195
|
result = CdmUtils.concat(" ", result, text);
|
|
196
|
}
|
|
197
|
return result;
|
|
198
|
}
|
|
199
|
|
|
200
|
public DescriptionElementBase makeFeatureFigureRef(MarkupImportState state, XMLEventReader reader,TaxonDescription taxonDescription,
|
|
201
|
boolean isDescription, DescriptionElementBase lastDescriptionElement, Reference sourceReference, XMLEvent next) throws XMLStreamException {
|
|
202
|
FigureDataHolder figureHolder = handleFigureRef(state, reader, next);
|
|
203
|
Feature figureFeature = getFeature(state, MarkupTransformer.uuidFigures, "Figures", "Figures", "Fig.",null);
|
|
204
|
if (isDescription) {
|
|
205
|
TextData figureHolderTextData = null;
|
|
206
|
// if (figureHolderTextData == null){
|
|
207
|
figureHolderTextData = TextData.NewInstance(figureFeature);
|
|
208
|
figureHolderTextData.addPrimaryTaxonomicSource(sourceReference);
|
|
209
|
|
|
210
|
if (StringUtils.isNotBlank(figureHolder.num)) {
|
|
211
|
String annotationText = "<num>" + figureHolder.num.trim() + "</num>";
|
|
212
|
Annotation annotation = Annotation.NewInstance(annotationText, AnnotationType.TECHNICAL(), getDefaultLanguage(state));
|
|
213
|
figureHolderTextData.addAnnotation(annotation);
|
|
214
|
}
|
|
215
|
if (StringUtils.isNotBlank(figureHolder.figurePart)) {
|
|
216
|
String annotationText = "<figurePart>"+ figureHolder.figurePart.trim() + "</figurePart>";
|
|
217
|
Annotation annotation = Annotation.NewInstance(annotationText,AnnotationType.EDITORIAL(), getDefaultLanguage(state));
|
|
218
|
figureHolderTextData.addAnnotation(annotation);
|
|
219
|
}
|
|
220
|
// if (StringUtils.isNotBlank(figureText)){
|
|
221
|
// figureHolderTextData.putText(language, figureText);
|
|
222
|
// }
|
|
223
|
taxonDescription.addElement(figureHolderTextData);
|
|
224
|
// }
|
|
225
|
registerFigureDemand(state, next, figureHolderTextData, figureHolder.ref);
|
|
226
|
} else {
|
|
227
|
if (lastDescriptionElement == null) {
|
|
228
|
String message = "No description element created yet that can be referred by figure. Create new TextData instead";
|
|
229
|
fireWarningEvent(message, next, 4);
|
|
230
|
lastDescriptionElement = TextData.NewInstance(figureFeature);
|
|
231
|
lastDescriptionElement.addPrimaryTaxonomicSource(sourceReference);
|
|
232
|
taxonDescription.addElement(lastDescriptionElement);
|
|
233
|
}
|
|
234
|
registerFigureDemand(state, next, lastDescriptionElement, figureHolder.ref);
|
|
235
|
}
|
|
236
|
return lastDescriptionElement;
|
|
237
|
}
|
|
238
|
|
|
239
|
private DescriptionElementBase makeFeatureString(MarkupImportState state,XMLEventReader reader, Feature feature,
|
|
240
|
TaxonDescription taxonDescription, DescriptionElementBase lastDescriptionElement, XMLEvent next, Boolean isFreetext) throws XMLStreamException {
|
|
241
|
|
|
242
|
//for specimen only
|
|
243
|
if (feature.equals(Feature.SPECIMEN()) || feature.equals(Feature.MATERIALS_EXAMINED())
|
|
244
|
|| feature.getUuid().equals(MarkupTransformer.uuidWoodSpecimens)){
|
|
245
|
|
|
246
|
List<DescriptionElementBase> specimens = specimenImport.handleMaterialsExamined(state, reader, next, feature, taxonDescription);
|
|
247
|
for (DescriptionElementBase specimen : specimens){
|
|
248
|
if (specimen.getInDescription() == null){
|
|
249
|
taxonDescription.addElement(specimen);
|
|
250
|
}
|
|
251
|
lastDescriptionElement = specimen;
|
|
252
|
}
|
|
253
|
state.setCurrentCollector(null);
|
|
254
|
|
|
255
|
return lastDescriptionElement;
|
|
256
|
}else if (feature.equals(Feature.COMMON_NAME()) && (isFreetext == null || !isFreetext)){
|
|
257
|
List<DescriptionElementBase> commonNames = makeCommonNameString(state, reader, next);
|
|
258
|
//NOTE: we do also have the old version makeVernacular, which was called from "others" below
|
|
259
|
for (DescriptionElementBase commonName : commonNames){
|
|
260
|
taxonDescription.addElement(commonName);
|
|
261
|
lastDescriptionElement = commonName;
|
|
262
|
}
|
|
263
|
return lastDescriptionElement;
|
|
264
|
}
|
|
265
|
else{
|
|
266
|
|
|
267
|
//others
|
|
268
|
Map<String, SubheadingResult> subheadingMap = handleString(state, reader, next, feature);
|
|
269
|
for (String subheading : subheadingMap.keySet()) {
|
|
270
|
Feature subheadingFeature = feature;
|
|
271
|
if (StringUtils.isNotBlank(subheading) && subheadingMap.size() > 1) {
|
|
272
|
subheadingFeature = makeFeature(subheading, state, next, null);
|
|
273
|
}
|
|
274
|
if (feature.equals(Feature.COMMON_NAME()) && (isFreetext == null || !isFreetext)){
|
|
275
|
//NOTE: see above
|
|
276
|
// List<DescriptionElementBase> commonNames = makeVernacular(state, subheading, subheadingMap.get(subheading));
|
|
277
|
// for (DescriptionElementBase commonName : commonNames){
|
|
278
|
// taxonDescription.addElement(commonName);
|
|
279
|
// lastDescriptionElement = commonName;
|
|
280
|
// }
|
|
281
|
}else {
|
|
282
|
TextData textData = TextData.NewInstance(subheadingFeature);
|
|
283
|
SubheadingResult subHeadingResult = subheadingMap.get(subheading);
|
|
284
|
LanguageString languageString = textData.putText(getDefaultLanguage(state), subHeadingResult.text);
|
|
285
|
if (isNotEmptyCollection(subHeadingResult.references.getReferences())){
|
|
286
|
for (LabeledReference reference : subHeadingResult.references.getReferences()){
|
|
287
|
textData.addPrimaryTaxonomicSource(reference.ref, reference.detail);
|
|
288
|
}
|
|
289
|
textData.addImportSource(null, null, state.getConfig().getSourceReference(), null);
|
|
290
|
}else{
|
|
291
|
textData.addPrimaryTaxonomicSource(state.getConfig().getSourceReference());
|
|
292
|
}
|
|
293
|
//intext references
|
|
294
|
for (IntextReference intext : subHeadingResult.inlineReferences){
|
|
295
|
languageString.addIntextReference(intext);
|
|
296
|
}
|
|
297
|
taxonDescription.addElement(textData);
|
|
298
|
lastDescriptionElement = textData;
|
|
299
|
// TODO how to handle figures when these data are split in
|
|
300
|
// subheadings
|
|
301
|
}
|
|
302
|
}
|
|
303
|
return lastDescriptionElement;
|
|
304
|
}
|
|
305
|
}
|
|
306
|
|
|
307
|
private Feature makeFeature(String classValue, MarkupImportState state, XMLEvent parentEvent, Feature parentFeature) {
|
|
308
|
UUID uuid;
|
|
309
|
try {
|
|
310
|
String featureText = StringUtils.capitalize(classValue);
|
|
311
|
if (parentFeature != null){
|
|
312
|
featureText = "<%s>" + featureText;
|
|
313
|
featureText = String.format(featureText, parentFeature.getTitleCache());
|
|
314
|
classValue = "<%s>" + classValue;
|
|
315
|
classValue = String.format(classValue, parentFeature.getTitleCache());
|
|
316
|
}
|
|
317
|
|
|
318
|
//get existing feature
|
|
319
|
if (classValue.endsWith(".")){
|
|
320
|
classValue = classValue.substring(0, classValue.length() - 1);
|
|
321
|
}
|
|
322
|
Feature feature = state.getTransformer().getFeatureByKey(classValue);
|
|
323
|
if (feature != null) {
|
|
324
|
return feature;
|
|
325
|
}
|
|
326
|
uuid = state.getTransformer().getFeatureUuid(classValue);
|
|
327
|
|
|
328
|
if (uuid == null){
|
|
329
|
uuid = state.getUnknownFeatureUuid(classValue);
|
|
330
|
}
|
|
331
|
|
|
332
|
if (uuid == null) {
|
|
333
|
// TODO
|
|
334
|
String message = "Uuid is not defined for '%s'";
|
|
335
|
message = String.format(message, classValue);
|
|
336
|
if (! message.contains("<")){
|
|
337
|
//log only top level features
|
|
338
|
fireWarningEvent(message, parentEvent, 8);
|
|
339
|
}
|
|
340
|
uuid = UUID.randomUUID();
|
|
341
|
state.putUnknownFeatureUuid(classValue, uuid);
|
|
342
|
}
|
|
343
|
|
|
344
|
// TODO eFlora vocabulary
|
|
345
|
TermVocabulary<Feature> voc = null;
|
|
346
|
feature = getFeature(state, uuid, featureText, featureText, classValue, voc);
|
|
347
|
if (parentFeature != null){
|
|
348
|
parentFeature.addIncludes(feature);
|
|
349
|
save(parentFeature, state);
|
|
350
|
}
|
|
351
|
save(feature, state);
|
|
352
|
|
|
353
|
if (feature == null) {
|
|
354
|
throw new NullPointerException(classValue + " not recognized as a feature");
|
|
355
|
}
|
|
356
|
// state.putFeatureToCurrentList(feature);
|
|
357
|
return feature;
|
|
358
|
} catch (Exception e) {
|
|
359
|
String message = "Could not create feature for %s: %s";
|
|
360
|
message = String.format(message, classValue, e.getMessage());
|
|
361
|
fireWarningEvent(message, parentEvent, 4);
|
|
362
|
state.putUnknownFeatureUuid(classValue, null);
|
|
363
|
// e.printStackTrace();
|
|
364
|
return Feature.UNKNOWN();
|
|
365
|
}
|
|
366
|
}
|
|
367
|
|
|
368
|
public class CharOrder{
|
|
369
|
static final int strlength = 3;
|
|
370
|
private int order = 1;
|
|
371
|
private CharOrder parent;
|
|
372
|
private final List<CharOrder> children = new ArrayList<CharOrder>();
|
|
373
|
|
|
374
|
public CharOrder nextChild(){
|
|
375
|
CharOrder result = new CharOrder();
|
|
376
|
if (! children.isEmpty()) {
|
|
377
|
result.order = children.get(children.size() - 1).order + 1;
|
|
378
|
}
|
|
379
|
result.parent = this;
|
|
380
|
children.add(result);
|
|
381
|
return result;
|
|
382
|
}
|
|
383
|
|
|
384
|
public CharOrder next(){
|
|
385
|
CharOrder result = new CharOrder();
|
|
386
|
result.order = order + 1;
|
|
387
|
result.parent = parent;
|
|
388
|
if (parent != null){
|
|
389
|
parent.children.add(result);
|
|
390
|
}
|
|
391
|
return result;
|
|
392
|
}
|
|
393
|
|
|
394
|
public String orderString(){
|
|
395
|
String parentString = parent == null ? "" : parent.orderString();
|
|
396
|
String result = CdmUtils.concat("-", parentString, StringUtils.leftPad(String.valueOf(order), strlength, '0'));
|
|
397
|
return result;
|
|
398
|
}
|
|
399
|
|
|
400
|
@Override
|
|
401
|
public String toString(){
|
|
402
|
return orderString();
|
|
403
|
}
|
|
404
|
}
|
|
405
|
|
|
406
|
|
|
407
|
/**
|
|
408
|
* Handle the char or subchar element. As
|
|
409
|
* @param state the import state
|
|
410
|
* @param reader
|
|
411
|
* @param parentEvent
|
|
412
|
* @param parentFeature in case of subchars we need to attache the newly created feature to a parent feature, should be <code>null</code>
|
|
413
|
* for top level chars.
|
|
414
|
* @return List of TextData. Not a single one as the recursive TextData will also be returned
|
|
415
|
* @throws XMLStreamException
|
|
416
|
*/
|
|
417
|
private List<TextData> handleChar(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent, Feature parentFeature, CharOrder myCharOrder) throws XMLStreamException {
|
|
418
|
List<TextData> result = new ArrayList<>();
|
|
419
|
String classValue = getClassOnlyAttribute(parentEvent);
|
|
420
|
Feature feature = makeFeature(classValue, state, parentEvent, parentFeature);
|
|
421
|
if(parentFeature == null){
|
|
422
|
state.putFeatureToCharSorterList(feature);
|
|
423
|
}else{
|
|
424
|
FeatureSorterInfo parentInfo = state.getLatestCharFeatureSorterInfo();
|
|
425
|
// if (! parentInfo.getUuid().equals(parentFeature.getUuid())){
|
|
426
|
// String message = "The parent char feature is not the same as the latest feature. This is the case for char hierarchies with > 2 levels, which is not yet handled by the import";
|
|
427
|
// fireWarningEvent(message, parentEvent, 6);
|
|
428
|
// }else{
|
|
429
|
state.getLatestCharFeatureSorterInfo().addSubFeature(new FeatureSorterInfo(feature));
|
|
430
|
// }
|
|
431
|
}
|
|
432
|
|
|
433
|
TextData textData = TextData.NewInstance(feature);
|
|
434
|
textData.addPrimaryTaxonomicSource(state.getConfig().getSourceReference());
|
|
435
|
result.add(textData);
|
|
436
|
|
|
437
|
AnnotationType annType = getAnnotationType(state, MarkupTransformer.uuidOriginalOrder, "Original order", "Order in original treatment", null, AnnotationType.TECHNICAL().getVocabulary());
|
|
438
|
textData.addAnnotation(Annotation.NewInstance(myCharOrder.orderString(), annType, Language.ENGLISH()));
|
|
439
|
|
|
440
|
boolean isTextMode = true;
|
|
441
|
String text = "";
|
|
442
|
while (reader.hasNext()) {
|
|
443
|
XMLEvent next = readNoWhitespace(reader);
|
|
444
|
if (isMyEndingElement(next, parentEvent)) {
|
|
445
|
text = text.trim();
|
|
446
|
textData.putText(getDefaultLanguage(state), text);
|
|
447
|
return result;
|
|
448
|
} else if (isStartingElement(next, FIGURE_REF)) {
|
|
449
|
//TODO
|
|
450
|
handleNotYetImplementedElement(next);
|
|
451
|
} else if (isStartingElement(next, FOOTNOTE_REF)) {
|
|
452
|
//TODO
|
|
453
|
handleNotYetImplementedElement(next);
|
|
454
|
} else if (isStartingElement(next, BR)) {
|
|
455
|
text += "<br/>";
|
|
456
|
isTextMode = false;
|
|
457
|
} else if (isEndingElement(next, BR)) {
|
|
458
|
isTextMode = true;
|
|
459
|
} else if (isHtml(next)) {
|
|
460
|
text += getXmlTag(next);
|
|
461
|
} else if (next.isStartElement()) {
|
|
462
|
if (isStartingElement(next, ANNOTATION)) {
|
|
463
|
handleNotYetImplementedElement(next); //TODO test handleSimpleAnnotation
|
|
464
|
} else if (isStartingElement(next, ITALICS)) {
|
|
465
|
handleNotYetImplementedElement(next);
|
|
466
|
} else if (isStartingElement(next, BOLD)) {
|
|
467
|
handleNotYetImplementedElement(next);
|
|
468
|
} else if (isStartingElement(next, FIGURE)) {
|
|
469
|
handleFigure(state, reader, next, specimenImport, nomenclatureImport);
|
|
470
|
} else if (isStartingElement(next, SUB_CHAR)) {
|
|
471
|
List<TextData> subTextData = handleChar(state, reader, next, feature, myCharOrder.nextChild());
|
|
472
|
result.addAll(subTextData);
|
|
473
|
} else if (isStartingElement(next, FOOTNOTE)) {
|
|
474
|
FootnoteDataHolder footnote = handleFootnote(state, reader, next, specimenImport, nomenclatureImport);
|
|
475
|
if (footnote.isRef()) {
|
|
476
|
String message = "Ref footnote not implemented here";
|
|
477
|
fireWarningEvent(message, next, 4);
|
|
478
|
} else {
|
|
479
|
registerGivenFootnote(state, footnote);
|
|
480
|
}
|
|
481
|
} else {
|
|
482
|
handleUnexpectedStartElement(next.asStartElement());
|
|
483
|
}
|
|
484
|
} else if (next.isCharacters()) {
|
|
485
|
if (!isTextMode) {
|
|
486
|
String message = "String is not in text mode";
|
|
487
|
fireWarningEvent(message, next, 6);
|
|
488
|
} else {
|
|
489
|
text += next.asCharacters().getData();
|
|
490
|
}
|
|
491
|
} else {
|
|
492
|
handleUnexpectedEndElement(next.asEndElement());
|
|
493
|
}
|
|
494
|
}
|
|
495
|
throw new IllegalStateException("RefPart has no closing tag");
|
|
496
|
}
|
|
497
|
|
|
498
|
private void makeFeatureHeading(MarkupImportState state, XMLEventReader reader, String classValue, Feature feature, XMLEvent next) throws XMLStreamException {
|
|
499
|
String heading = handleHeading(state, reader, next);
|
|
500
|
if (StringUtils.isNotBlank(heading)) {
|
|
501
|
if (!heading.equalsIgnoreCase(classValue)) {
|
|
502
|
try {
|
|
503
|
if (!feature.equals(state.getTransformer().getFeatureByKey(heading))) {
|
|
504
|
UUID headerFeatureUuid = state.getTransformer().getFeatureUuid(heading);
|
|
505
|
if (!feature.getUuid().equals(headerFeatureUuid)) {
|
|
506
|
String message = "Feature heading '%s' differs from feature class '%s' and can not be transformed to feature";
|
|
507
|
message = String.format(message, heading, classValue);
|
|
508
|
fireWarningEvent(message, next, 1);
|
|
509
|
}
|
|
510
|
}
|
|
511
|
} catch (UndefinedTransformerMethodException e) {
|
|
512
|
throw new RuntimeException(e);
|
|
513
|
}
|
|
514
|
} else {
|
|
515
|
// do nothing
|
|
516
|
}
|
|
517
|
}
|
|
518
|
}
|
|
519
|
|
|
520
|
private void makeFeatureWriter(MarkupImportState state,XMLEventReader reader, Feature feature, Taxon taxon, XMLEvent next) throws XMLStreamException {
|
|
521
|
WriterDataHolder writer = handleWriter(state, reader, next);
|
|
522
|
if (isNotBlank(writer.writer)) {
|
|
523
|
// TODO
|
|
524
|
Reference ref = state.getConfig().getSourceReference();
|
|
525
|
TaxonDescription description = getDefaultTaxonDescription(taxon, false, true, ref);
|
|
526
|
TextData featurePlaceholder = docImport.getFeaturePlaceholder(state,
|
|
527
|
description, feature, true);
|
|
528
|
featurePlaceholder.addAnnotation(writer.annotation);
|
|
529
|
registerFootnotes(state, featurePlaceholder, writer.footnotes);
|
|
530
|
} else {
|
|
531
|
String message = "Writer element is empty";
|
|
532
|
fireWarningEvent(message, next, 4);
|
|
533
|
}
|
|
534
|
}
|
|
535
|
|
|
536
|
|
|
537
|
protected String handleHabitat(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
538
|
checkNoAttributes(parentEvent);
|
|
539
|
Taxon taxon = state.getCurrentTaxon();
|
|
540
|
// TODO which ref to take?
|
|
541
|
Reference sourceReference = state.getConfig().getSourceReference();
|
|
542
|
|
|
543
|
|
|
544
|
boolean isTextMode = true;
|
|
545
|
String text = "";
|
|
546
|
while (reader.hasNext()) {
|
|
547
|
XMLEvent next = readNoWhitespace(reader);
|
|
548
|
if (isMyEndingElement(next, parentEvent)) {
|
|
549
|
Feature feature = getFeature(
|
|
550
|
state,
|
|
551
|
MarkupTransformer.uuidExtractedHabitat,
|
|
552
|
"Extracted Habitat",
|
|
553
|
"An structured habitat that was extracted from a habitat text",
|
|
554
|
"extr. habit.", null);
|
|
555
|
TextData habitat = TextData.NewInstance(feature);
|
|
556
|
habitat.addPrimaryTaxonomicSource(sourceReference);
|
|
557
|
habitat.putText(getDefaultLanguage(state), text);
|
|
558
|
TaxonDescription description = getExtractedMarkupMarkedDescription(state, taxon, sourceReference);
|
|
559
|
|
|
560
|
description.addElement(habitat);
|
|
561
|
|
|
562
|
return text;
|
|
563
|
} else if (isStartingElement(next, ALTITUDE)) {
|
|
564
|
// OLD: text = text.trim() + getTaggedCData(state, reader, next);
|
|
565
|
text += handleAltitude(state, reader, next);
|
|
566
|
} else if (isStartingElement(next, LIFE_CYCLE_PERIODS)) {
|
|
567
|
handleNotYetImplementedElement(next);
|
|
568
|
} else if (next.isCharacters()) {
|
|
569
|
if (! isTextMode) {
|
|
570
|
String message = "String is not in text mode";
|
|
571
|
fireWarningEvent(message, next, 6);
|
|
572
|
} else {
|
|
573
|
text += next.asCharacters().getData();
|
|
574
|
}
|
|
575
|
} else if (isStartingElement(next, BR)) {
|
|
576
|
text += "<br/>";
|
|
577
|
isTextMode = false;
|
|
578
|
} else if (isEndingElement(next, BR)) {
|
|
579
|
isTextMode = true;
|
|
580
|
} else if (isStartingElement(next, REFERENCES)) {
|
|
581
|
handleNotYetImplementedElement(next);
|
|
582
|
} else if (isStartingElement(next, FIGURE_REF)) {
|
|
583
|
handleNotYetImplementedElement(next);
|
|
584
|
} else {
|
|
585
|
String type = next.toString();
|
|
586
|
String location = String.valueOf(next.getLocation().getLineNumber());
|
|
587
|
System.out.println("MarkupFeature.handleHabitat: Unexpected element in habitat: " + type + ": " + location);
|
|
588
|
handleUnexpectedElement(next);
|
|
589
|
}
|
|
590
|
}
|
|
591
|
throw new IllegalStateException("<Habitat> has no closing tag");
|
|
592
|
}
|
|
593
|
|
|
594
|
/**
|
|
595
|
* Creates "Extracted factual data" with feature altitude and returns the original text as string
|
|
596
|
* to be used in parent element.
|
|
597
|
* @see #handleHabitat(MarkupImportState, XMLEventReader, XMLEvent)
|
|
598
|
*/
|
|
599
|
private String handleAltitude(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
600
|
checkNoAttributes(parentEvent);
|
|
601
|
Taxon taxon = state.getCurrentTaxon();
|
|
602
|
// TODO which ref to take?
|
|
603
|
Reference sourceReference = state.getConfig().getSourceReference();
|
|
604
|
|
|
605
|
boolean isTextMode = true;
|
|
606
|
String text = "";
|
|
607
|
while (reader.hasNext()) {
|
|
608
|
XMLEvent next = readNoWhitespace(reader);
|
|
609
|
if (isMyEndingElement(next, parentEvent)) {
|
|
610
|
Feature feature = getFeature(
|
|
611
|
state,
|
|
612
|
MarkupTransformer.uuidExtractedAltitude,
|
|
613
|
"Extracted Altitude",
|
|
614
|
"An altitude that was extracted from a habitat text",
|
|
615
|
"extr. alt.", null);
|
|
616
|
//TODO try to make quantitative data
|
|
617
|
TextData altitude = TextData.NewInstance(feature);
|
|
618
|
altitude.putText(getDefaultLanguage(state), text);
|
|
619
|
altitude.addPrimaryTaxonomicSource(sourceReference);
|
|
620
|
TaxonDescription description = getExtractedMarkupMarkedDescription(state, taxon, sourceReference);
|
|
621
|
|
|
622
|
description.addElement(altitude);
|
|
623
|
|
|
624
|
return text;
|
|
625
|
} else if (next.isCharacters()) {
|
|
626
|
if (! isTextMode) {
|
|
627
|
String message = "String is not in text mode";
|
|
628
|
fireWarningEvent(message, next, 6);
|
|
629
|
} else {
|
|
630
|
text += next.asCharacters().getData();
|
|
631
|
}
|
|
632
|
} else if (isStartingElement(next, BR)) {
|
|
633
|
text += "<br/>";
|
|
634
|
isTextMode = false;
|
|
635
|
} else if (isEndingElement(next, BR)) {
|
|
636
|
isTextMode = true;
|
|
637
|
} else {
|
|
638
|
String type = next.toString();
|
|
639
|
String location = String.valueOf(next.getLocation().getLineNumber());
|
|
640
|
System.out.println("MarkupFeatureImport.handleAltitude: Unexpected element in habitat: " + type + ": " + location);
|
|
641
|
handleUnexpectedElement(next);
|
|
642
|
}
|
|
643
|
}
|
|
644
|
throw new IllegalStateException("<Habitat> has no closing tag");
|
|
645
|
}
|
|
646
|
|
|
647
|
private FigureDataHolder handleFigureRef(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent)
|
|
648
|
throws XMLStreamException {
|
|
649
|
FigureDataHolder result = new FigureDataHolder();
|
|
650
|
Map<String, Attribute> attributes = getAttributes(parentEvent);
|
|
651
|
result.ref = getAndRemoveAttributeValue(attributes, REF);
|
|
652
|
checkNoAttributes(attributes, parentEvent);
|
|
653
|
|
|
654
|
// text is not handled, needed only for debugging purposes
|
|
655
|
String text = "";
|
|
656
|
while (reader.hasNext()) {
|
|
657
|
XMLEvent next = readNoWhitespace(reader);
|
|
658
|
if (isMyEndingElement(next, parentEvent)) {
|
|
659
|
return result;
|
|
660
|
} else if (isStartingElement(next, NUM)) {
|
|
661
|
String num = getCData(state, reader, next);
|
|
662
|
result.num = num; // num is not handled during import
|
|
663
|
} else if (isStartingElement(next, FIGURE_PART)) {
|
|
664
|
result.figurePart = getCData(state, reader, next);
|
|
665
|
} else if (next.isCharacters()) {
|
|
666
|
text += next.asCharacters().getData();
|
|
667
|
} else {
|
|
668
|
fireUnexpectedEvent(next, 0);
|
|
669
|
}
|
|
670
|
}
|
|
671
|
throw new IllegalStateException("<figureRef> has no end tag");
|
|
672
|
}
|
|
673
|
|
|
674
|
|
|
675
|
private void registerFigureDemand(MarkupImportState state, XMLEvent next, AnnotatableEntity entity, String figureRef) {
|
|
676
|
Media existingFigure = state.getFigure(figureRef);
|
|
677
|
if (existingFigure != null) {
|
|
678
|
attachFigure(state, next, entity, existingFigure);
|
|
679
|
} else {
|
|
680
|
Set<AnnotatableEntity> demands = state.getFigureDemands(figureRef);
|
|
681
|
if (demands == null) {
|
|
682
|
demands = new HashSet<AnnotatableEntity>();
|
|
683
|
state.putFigureDemands(figureRef, demands);
|
|
684
|
}
|
|
685
|
demands.add(entity);
|
|
686
|
}
|
|
687
|
}
|
|
688
|
|
|
689
|
private List<DescriptionElementBase> makeCommonNameString(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException{
|
|
690
|
|
|
691
|
List<DescriptionElementBase> result = new ArrayList<>();
|
|
692
|
|
|
693
|
checkNoAttributes(parentEvent);
|
|
694
|
|
|
695
|
while (reader.hasNext()) {
|
|
696
|
XMLEvent next = readNoWhitespace(reader);
|
|
697
|
if (isMyEndingElement(next, parentEvent)) {
|
|
698
|
if (result.isEmpty()){
|
|
699
|
fireWarningEvent("Common name was not created", next, 4);
|
|
700
|
}
|
|
701
|
return result;
|
|
702
|
} else if (isStartingElement(next, VERNACULAR_NAMES)) {
|
|
703
|
result = makeVernacularNames(state, reader, next);
|
|
704
|
} else if (isStartingElement(next, SUB_HEADING)) {
|
|
705
|
String subheading = getCData(state, reader, next);
|
|
706
|
if (! subheading.matches("(Nom(s)? vernaculaire(s)?\\:|Vern.)")){
|
|
707
|
fireWarningEvent("Subheading for vernacular name not recognized: " + subheading, next, 4);
|
|
708
|
}
|
|
709
|
} else if (next.isCharacters()) {
|
|
710
|
String chars = next.asCharacters().toString().trim();
|
|
711
|
if (chars.equals(".")){
|
|
712
|
//do nothing
|
|
713
|
}else{
|
|
714
|
fireWarningEvent("Character not handled in vernacular name: " + chars, next, 4);
|
|
715
|
}
|
|
716
|
} else if (isStartingElement(next, REFERENCES)) {
|
|
717
|
handleNotYetImplementedElement(next);
|
|
718
|
}else {
|
|
719
|
handleUnexpectedElement(next);
|
|
720
|
}
|
|
721
|
}
|
|
722
|
throw new IllegalStateException("closing tag is missing");
|
|
723
|
}
|
|
724
|
|
|
725
|
private List<DescriptionElementBase> makeVernacularNames(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException{
|
|
726
|
|
|
727
|
List<DescriptionElementBase> result = new ArrayList<>();
|
|
728
|
checkNoAttributes(parentEvent);
|
|
729
|
|
|
730
|
while (reader.hasNext()) {
|
|
731
|
XMLEvent next = readNoWhitespace(reader);
|
|
732
|
if (isMyEndingElement(next, parentEvent)) {
|
|
733
|
state.removeCurrentAreas();
|
|
734
|
return result;
|
|
735
|
} else if (isStartingElement(next, VERNACULAR_NAME)) {
|
|
736
|
List<CommonTaxonName> names = makeSingleVernacularName(state, reader, next);
|
|
737
|
result.addAll(names);
|
|
738
|
} else if (isStartingElement(next, SUB_HEADING)) {
|
|
739
|
makeVernacularNamesSubHeading(state, reader, next);
|
|
740
|
} else {
|
|
741
|
handleUnexpectedElement(next);
|
|
742
|
}
|
|
743
|
}
|
|
744
|
throw new IllegalStateException("closing tag is missing");
|
|
745
|
}
|
|
746
|
|
|
747
|
private void makeVernacularNamesSubHeading(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
748
|
checkNoAttributes(parentEvent);
|
|
749
|
|
|
750
|
String text = "";
|
|
751
|
while (reader.hasNext()) {
|
|
752
|
XMLEvent next = readNoWhitespace(reader);
|
|
753
|
if (isMyEndingElement(next, parentEvent)) {
|
|
754
|
if (StringUtils.isNotBlank(text)){
|
|
755
|
NamedArea area = getCommonNameArea(text);
|
|
756
|
if (area != null){
|
|
757
|
state.removeCurrentAreas();
|
|
758
|
state.addCurrentArea(area);
|
|
759
|
}else{
|
|
760
|
fireWarningEvent("Vernacular subheading not recognized", next, 8);
|
|
761
|
}
|
|
762
|
}
|
|
763
|
|
|
764
|
return ;
|
|
765
|
} else if (next.isCharacters()) {
|
|
766
|
text += next.asCharacters().getData();
|
|
767
|
} else {
|
|
768
|
handleUnexpectedElement(next);
|
|
769
|
}
|
|
770
|
}
|
|
771
|
throw new IllegalStateException("closing tag is missing");
|
|
772
|
}
|
|
773
|
|
|
774
|
private NamedArea getCommonNameArea(String text) {
|
|
775
|
if (text.endsWith(":")){
|
|
776
|
text = text.substring(0, text.length()-1);
|
|
777
|
}
|
|
778
|
|
|
779
|
// for now we do it hardcoded
|
|
780
|
if (text.equalsIgnoreCase("Guyana")){
|
|
781
|
return Country.GUYANAREPUBLICOF();
|
|
782
|
}else if (text.equalsIgnoreCase("Suriname")){
|
|
783
|
return Country.SURINAMEREPUBLICOF();
|
|
784
|
}else if (text.equalsIgnoreCase("French Guiana")){
|
|
785
|
return Country.FRENCHGUIANA();
|
|
786
|
}
|
|
787
|
return null;
|
|
788
|
}
|
|
789
|
|
|
790
|
private List<CommonTaxonName> makeSingleVernacularName(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException{
|
|
791
|
|
|
792
|
checkNoAttributes(parentEvent);
|
|
793
|
List<CommonTaxonName> result = new ArrayList<>();
|
|
794
|
|
|
795
|
Language language = state.getDefaultLanguage();
|
|
796
|
while (reader.hasNext()) {
|
|
797
|
XMLEvent next = readNoWhitespace(reader);
|
|
798
|
if (isMyEndingElement(next, parentEvent)) {
|
|
799
|
for (CommonTaxonName commonName : result){
|
|
800
|
commonName.setLanguage(language);
|
|
801
|
}
|
|
802
|
// if (isNotBlank(name)){
|
|
803
|
// result.setName(name);
|
|
804
|
// }else{
|
|
805
|
// fireWarningEvent("No name string for common name", parentEvent, 4);
|
|
806
|
// }
|
|
807
|
|
|
808
|
return result;
|
|
809
|
} else if (isStartingElement(next, NAME)) {
|
|
810
|
//TODO test
|
|
811
|
CommonTaxonName name = handleVernacularNameName(state, reader, next);
|
|
812
|
if (name != null){
|
|
813
|
result.add(name);
|
|
814
|
}
|
|
815
|
} else if (isStartingElement(next, LOCAL_LANGUAGE)) {
|
|
816
|
Language localLanguage = handleLocalLanguage(state, reader, next);
|
|
817
|
if (localLanguage != null){
|
|
818
|
language = localLanguage;
|
|
819
|
}
|
|
820
|
} else if (isStartingElement(next, TRANSLATION)) {
|
|
821
|
//TODO
|
|
822
|
handleNotYetImplementedElement(next);
|
|
823
|
} else if (isStartingElement(next, LOCALITY)) {
|
|
824
|
//TODO
|
|
825
|
handleNotYetImplementedElement(next);
|
|
826
|
} else if (isStartingElement(next, ANNOTATION)){
|
|
827
|
//TODO
|
|
828
|
handleNotYetImplementedElement(next);
|
|
829
|
} else if (isStartingElement(next, FOOTNOTE_REF)) {
|
|
830
|
//TODO
|
|
831
|
handleNotYetImplementedElement(next);
|
|
832
|
} else if (next.isCharacters()) {
|
|
833
|
String chars = next.asCharacters().toString().trim();
|
|
834
|
if (chars.equals("(") || chars.equals(")") || chars.equals(",")){
|
|
835
|
//do nothing
|
|
836
|
}else{
|
|
837
|
fireWarningEvent("Character not handled in vernacular name: " + chars, next, 4);
|
|
838
|
}
|
|
839
|
} else {
|
|
840
|
handleUnexpectedElement(next);
|
|
841
|
}
|
|
842
|
}
|
|
843
|
throw new IllegalStateException("closing tag is missing");
|
|
844
|
}
|
|
845
|
|
|
846
|
private CommonTaxonName handleVernacularNameName(MarkupImportState state, XMLEventReader reader,
|
|
847
|
XMLEvent parentEvent) throws XMLStreamException {
|
|
848
|
//attributes
|
|
849
|
Map<String, Attribute> attributes = getAttributes(parentEvent);
|
|
850
|
this.checkAndRemoveAttributeValue(attributes, CLASS, "vernacular");
|
|
851
|
this.checkNoAttributes(attributes, parentEvent);
|
|
852
|
|
|
853
|
//
|
|
854
|
String text = getCData(state, reader, parentEvent, false);
|
|
855
|
CommonTaxonName name = CommonTaxonName.NewInstance(text, null);
|
|
856
|
if (! state.getCurrentAreas().isEmpty()){
|
|
857
|
if (state.getCurrentAreas().size() > 1){
|
|
858
|
fireWarningEvent("Multiple areas for common name not yet covered by CDM", parentEvent , 8);
|
|
859
|
}else{
|
|
860
|
name.setArea(state.getCurrentAreas().iterator().next());
|
|
861
|
}
|
|
862
|
}
|
|
863
|
return name;
|
|
864
|
}
|
|
865
|
|
|
866
|
private Language handleLocalLanguage(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
867
|
//attributes
|
|
868
|
Map<String, Attribute> attributes = getAttributes(parentEvent);
|
|
869
|
boolean doubtful = getAndRemoveBooleanAttributeValue(parentEvent, attributes, DOUBTFUL, false);
|
|
870
|
boolean unknown = getAndRemoveBooleanAttributeValue(parentEvent, attributes, UNKNOWN, false);
|
|
871
|
this.checkNoAttributes(attributes, parentEvent);
|
|
872
|
|
|
873
|
if (doubtful == true){
|
|
874
|
fireWarningEvent("Doubtful not yet implemented for local language", parentEvent, 2);
|
|
875
|
}
|
|
876
|
if (unknown == true){
|
|
877
|
fireWarningEvent("Unknown not yet implemented for local language ", parentEvent, 2);
|
|
878
|
}
|
|
879
|
|
|
880
|
//
|
|
881
|
String text = getCData(state, reader, parentEvent);
|
|
882
|
Language lang = makeLanguageByLangStr(state, text);
|
|
883
|
return lang;
|
|
884
|
|
|
885
|
}
|
|
886
|
|
|
887
|
private List<DescriptionElementBase> makeVernacular(MarkupImportState state, String subheading, String commonNameString) throws XMLStreamException {
|
|
888
|
List<DescriptionElementBase> result = new ArrayList<>();
|
|
889
|
Reference sourceReference = state.getConfig().getSourceReference();
|
|
890
|
String[] splits = commonNameString.split(",");
|
|
891
|
for (String split : splits){
|
|
892
|
split = split.trim();
|
|
893
|
if (! split.matches(".*\\(.*\\)\\.?")){
|
|
894
|
fireWarningEvent("Common name string '"+split+"' does not match given pattern", state.getReader().peek(), 4);
|
|
895
|
}
|
|
896
|
|
|
897
|
String name = split.replaceAll("\\(.*\\)", "").replace(".", "").trim();
|
|
898
|
String languageStr = split.replaceFirst(".*\\(", "").replaceAll("\\)\\.?", "").trim();
|
|
899
|
|
|
900
|
Language language = null;
|
|
901
|
if (StringUtils.isNotBlank(languageStr)){
|
|
902
|
language = makeLanguageByLangStr(state, languageStr);
|
|
903
|
}
|
|
904
|
DescriptionElementBase commonName;
|
|
905
|
if (name != null && name.length() < 255 ){
|
|
906
|
NamedArea area = null;
|
|
907
|
commonName = CommonTaxonName.NewInstance(name, language, area);
|
|
908
|
commonName.addPrimaryTaxonomicSource(sourceReference);
|
|
909
|
}else{
|
|
910
|
if (language == null){
|
|
911
|
language = getDefaultLanguage(state);
|
|
912
|
}
|
|
913
|
commonName = TextData.NewInstance(Feature.COMMON_NAME(), name, language, null);
|
|
914
|
commonName.addPrimaryTaxonomicSource(sourceReference);
|
|
915
|
String warning = "Vernacular feature is >255 size. Therefore it is handled as TextData, not CommonTaxonName: " + name;
|
|
916
|
fireWarningEvent(warning, state.getReader().peek(), 1);
|
|
917
|
}
|
|
918
|
result.add(commonName);
|
|
919
|
}
|
|
920
|
|
|
921
|
return result;
|
|
922
|
}
|
|
923
|
|
|
924
|
private Language makeLanguageByLangStr(MarkupImportState state, String languageStr) throws XMLStreamException {
|
|
925
|
try {
|
|
926
|
Language language = state.getTransformer().getLanguageByKey(languageStr);
|
|
927
|
if (language == null){
|
|
928
|
UUID langUuid = state.getTransformer().getLanguageUuid(languageStr);
|
|
929
|
TermVocabulary<?> voc = null;
|
|
930
|
language = getLanguage(state, langUuid, languageStr, languageStr, null, voc);
|
|
931
|
}
|
|
932
|
if (language == null){
|
|
933
|
String warning = "Language " + languageStr + " not recognized by transformer";
|
|
934
|
fireWarningEvent(warning, state.getReader().peek(), 4);
|
|
935
|
}
|
|
936
|
return language;
|
|
937
|
} catch (UndefinedTransformerMethodException e) {
|
|
938
|
throw new RuntimeException(e);
|
|
939
|
}
|
|
940
|
}
|
|
941
|
|
|
942
|
private String handleHeading(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent)throws XMLStreamException {
|
|
943
|
checkNoAttributes(parentEvent);
|
|
944
|
|
|
945
|
String text = "";
|
|
946
|
while (reader.hasNext()) {
|
|
947
|
XMLEvent next = readNoWhitespace(reader);
|
|
948
|
if (isMyEndingElement(next, parentEvent)) {
|
|
949
|
return text;
|
|
950
|
} else if (next.isStartElement()) {
|
|
951
|
if (isStartingElement(next, FOOTNOTE)) {
|
|
952
|
handleNotYetImplementedElement(next);
|
|
953
|
} else {
|
|
954
|
handleUnexpectedStartElement(next.asStartElement());
|
|
955
|
}
|
|
956
|
} else if (next.isCharacters()) {
|
|
957
|
text += next.asCharacters().getData();
|
|
958
|
} else {
|
|
959
|
handleUnexpectedEndElement(next.asEndElement());
|
|
960
|
}
|
|
961
|
}
|
|
962
|
throw new IllegalStateException("<String> has no closing tag");
|
|
963
|
}
|
|
964
|
|
|
965
|
private List<Reference> handleReferences(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
966
|
// attributes
|
|
967
|
Map<String, Attribute> attributes = getAttributes(parentEvent);
|
|
968
|
String bibliography = getAndRemoveAttributeValue(attributes,
|
|
969
|
BIBLIOGRAPHY);
|
|
970
|
String serialsAbbreviations = getAndRemoveAttributeValue(attributes,
|
|
971
|
SERIALS_ABBREVIATIONS);
|
|
972
|
if (isNotBlank(bibliography) || isNotBlank(serialsAbbreviations)) {
|
|
973
|
String message = "Attributes not yet implemented for <references>";
|
|
974
|
fireWarningEvent(message, parentEvent, 4);
|
|
975
|
}
|
|
976
|
|
|
977
|
List<Reference> result = new ArrayList<>();
|
|
978
|
|
|
979
|
// elements
|
|
980
|
while (reader.hasNext()) {
|
|
981
|
XMLEvent next = readNoWhitespace(reader);
|
|
982
|
if (next.isEndElement()) {
|
|
983
|
if (isMyEndingElement(next, parentEvent)) {
|
|
984
|
return result;
|
|
985
|
} else {
|
|
986
|
if (isEndingElement(next, HEADING)) {
|
|
987
|
// NOT YET IMPLEMENTED
|
|
988
|
popUnimplemented(next.asEndElement());
|
|
989
|
} else if (isEndingElement(next, WRITER)) {
|
|
990
|
// NOT YET IMPLEMENTED
|
|
991
|
popUnimplemented(next.asEndElement());
|
|
992
|
} else if (isEndingElement(next, FOOTNOTE)) {
|
|
993
|
// NOT YET IMPLEMENTED
|
|
994
|
popUnimplemented(next.asEndElement());
|
|
995
|
} else if (isEndingElement(next, STRING)) {
|
|
996
|
// NOT YET IMPLEMENTED
|
|
997
|
popUnimplemented(next.asEndElement());
|
|
998
|
} else if (isEndingElement(next, REF_NUM)) {
|
|
999
|
// NOT YET IMPLEMENTED
|
|
1000
|
popUnimplemented(next.asEndElement());
|
|
1001
|
} else {
|
|
1002
|
handleUnexpectedEndElement(next.asEndElement());
|
|
1003
|
}
|
|
1004
|
}
|
|
1005
|
} else if (next.isStartElement()) {
|
|
1006
|
if (isStartingElement(next, HEADING)) {
|
|
1007
|
handleNotYetImplementedElement(next);
|
|
1008
|
} else if (isStartingElement(next, SUB_HEADING)) {
|
|
1009
|
String subheading = getCData(state, reader, next).trim();
|
|
1010
|
String excludePattern = "(i?)(References?|Literature):?";
|
|
1011
|
if (!subheading.matches(excludePattern)) {
|
|
1012
|
fireNotYetImplementedElement(next.getLocation(), next.asStartElement().getName(), 0);
|
|
1013
|
}
|
|
1014
|
} else if (isStartingElement(next, WRITER)) {
|
|
1015
|
handleNotYetImplementedElement(next);
|
|
1016
|
} else if (isStartingElement(next, FOOTNOTE)) {
|
|
1017
|
handleNotYetImplementedElement(next);
|
|
1018
|
} else if (isStartingElement(next, STRING)) {
|
|
1019
|
handleNotYetImplementedElement(next);
|
|
1020
|
} else if (isStartingElement(next, REF_NUM)) {
|
|
1021
|
handleNotYetImplementedElement(next);
|
|
1022
|
} else if (isStartingElement(next, REFERENCE)) {
|
|
1023
|
Reference ref = nomenclatureImport.handleReference(state, reader, next);
|
|
1024
|
result.add(ref);
|
|
1025
|
} else {
|
|
1026
|
handleUnexpectedStartElement(next);
|
|
1027
|
}
|
|
1028
|
} else {
|
|
1029
|
handleUnexpectedElement(next);
|
|
1030
|
}
|
|
1031
|
}
|
|
1032
|
throw new IllegalStateException("<References> has no closing tag");
|
|
1033
|
}
|
|
1034
|
|
|
1035
|
|
|
1036
|
/**
|
|
1037
|
* Returns all the included text and tags as string. The result should look
|
|
1038
|
* similar to the original xml part.
|
|
1039
|
*/
|
|
1040
|
private String getTaggedCData(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
1041
|
checkNoAttributes(parentEvent);
|
|
1042
|
|
|
1043
|
String text = getXmlTag(parentEvent);
|
|
1044
|
while (reader.hasNext()) {
|
|
1045
|
XMLEvent next = readNoWhitespace(reader);
|
|
1046
|
if (isMyEndingElement(next, parentEvent)) {
|
|
1047
|
text += getXmlTag(next);
|
|
1048
|
return text;
|
|
1049
|
} else if (next.isStartElement()) {
|
|
1050
|
text += getTaggedCData(state, reader, next);
|
|
1051
|
} else if (next.isEndElement()) {
|
|
1052
|
//is this needed?
|
|
1053
|
text += getTaggedCData(state, reader, next);
|
|
1054
|
} else if (next.isCharacters()) {
|
|
1055
|
text += next.asCharacters().getData();
|
|
1056
|
} else {
|
|
1057
|
handleUnexpectedEndElement(next.asEndElement());
|
|
1058
|
}
|
|
1059
|
}
|
|
1060
|
throw new IllegalStateException("Some tag has no closing tag");
|
|
1061
|
}
|
|
1062
|
}
|