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.berlinModel.in;
|
11
|
|
12
|
import static eu.etaxonomy.cdm.io.berlinModel.BerlinModelTransformer.NAME_FACT_ALSO_PUBLISHED_IN;
|
13
|
import static eu.etaxonomy.cdm.io.berlinModel.BerlinModelTransformer.NAME_FACT_BIBLIOGRAPHY;
|
14
|
import static eu.etaxonomy.cdm.io.berlinModel.BerlinModelTransformer.NAME_FACT_PROTOLOGUE;
|
15
|
|
16
|
import java.io.File;
|
17
|
import java.io.IOException;
|
18
|
import java.net.MalformedURLException;
|
19
|
import java.net.URI;
|
20
|
import java.net.URISyntaxException;
|
21
|
import java.net.URL;
|
22
|
import java.sql.ResultSet;
|
23
|
import java.sql.SQLException;
|
24
|
import java.util.HashMap;
|
25
|
import java.util.HashSet;
|
26
|
import java.util.Map;
|
27
|
import java.util.Set;
|
28
|
|
29
|
import org.apache.commons.lang.StringUtils;
|
30
|
import org.apache.http.HttpException;
|
31
|
import org.apache.log4j.Logger;
|
32
|
import org.springframework.stereotype.Component;
|
33
|
|
34
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
35
|
import eu.etaxonomy.cdm.common.media.ImageInfo;
|
36
|
import eu.etaxonomy.cdm.io.berlinModel.in.validation.BerlinModelNameFactsImportValidator;
|
37
|
import eu.etaxonomy.cdm.io.common.IOValidator;
|
38
|
import eu.etaxonomy.cdm.io.common.ResultSetPartitioner;
|
39
|
import eu.etaxonomy.cdm.model.agent.Person;
|
40
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
41
|
import eu.etaxonomy.cdm.model.common.Language;
|
42
|
import eu.etaxonomy.cdm.model.common.OriginalSourceType;
|
43
|
import eu.etaxonomy.cdm.model.description.Feature;
|
44
|
import eu.etaxonomy.cdm.model.description.TaxonNameDescription;
|
45
|
import eu.etaxonomy.cdm.model.description.TextData;
|
46
|
import eu.etaxonomy.cdm.model.media.ImageFile;
|
47
|
import eu.etaxonomy.cdm.model.media.Media;
|
48
|
import eu.etaxonomy.cdm.model.media.MediaRepresentation;
|
49
|
import eu.etaxonomy.cdm.model.media.MediaRepresentationPart;
|
50
|
import eu.etaxonomy.cdm.model.name.TaxonName;
|
51
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
52
|
|
53
|
|
54
|
/**
|
55
|
* @author a.mueller
|
56
|
* @created 20.03.2008
|
57
|
* @version 1.0
|
58
|
*/
|
59
|
@Component
|
60
|
public class BerlinModelNameFactsImport extends BerlinModelImportBase {
|
61
|
private static final Logger logger = Logger.getLogger(BerlinModelNameFactsImport.class);
|
62
|
|
63
|
public static final String NAMESPACE = "NameFact";
|
64
|
|
65
|
/**
|
66
|
* write info message after modCount iterations
|
67
|
*/
|
68
|
private int modCount = 500;
|
69
|
private static final String pluralString = "name facts";
|
70
|
private static final String dbTableName = "NameFact";
|
71
|
|
72
|
|
73
|
public BerlinModelNameFactsImport(){
|
74
|
super(dbTableName, pluralString);
|
75
|
}
|
76
|
|
77
|
|
78
|
|
79
|
|
80
|
@Override
|
81
|
protected String getIdQuery(BerlinModelImportState state) {
|
82
|
if (StringUtils.isNotEmpty(state.getConfig().getNameIdTable())){
|
83
|
String result = super.getIdQuery(state);
|
84
|
result += " WHERE ptNameFk IN (SELECT NameId FROM " + state.getConfig().getNameIdTable() + ")";
|
85
|
return result;
|
86
|
}else{
|
87
|
return super.getIdQuery(state);
|
88
|
}
|
89
|
}
|
90
|
|
91
|
|
92
|
|
93
|
|
94
|
/* (non-Javadoc)
|
95
|
* @see eu.etaxonomy.cdm.io.berlinModel.in.BerlinModelImportBase#getRecordQuery(eu.etaxonomy.cdm.io.berlinModel.in.BerlinModelImportConfigurator)
|
96
|
*/
|
97
|
@Override
|
98
|
protected String getRecordQuery(BerlinModelImportConfigurator config) {
|
99
|
String strQuery =
|
100
|
" SELECT NameFact.*, Name.NameID as nameId, NameFactCategory.NameFactCategory " +
|
101
|
" FROM NameFact INNER JOIN " +
|
102
|
" Name ON NameFact.PTNameFk = Name.NameId INNER JOIN "+
|
103
|
" NameFactCategory ON NameFactCategory.NameFactCategoryID = NameFact.NameFactCategoryFK " +
|
104
|
" WHERE (NameFactId IN ("+ ID_LIST_TOKEN+") )";
|
105
|
return strQuery;
|
106
|
}
|
107
|
|
108
|
@Override
|
109
|
public boolean doPartition(ResultSetPartitioner partitioner, BerlinModelImportState state) {
|
110
|
boolean success = true ;
|
111
|
BerlinModelImportConfigurator config = state.getConfig();
|
112
|
Set<TaxonName> nameToSave = new HashSet<>();
|
113
|
Map<String, TaxonName> nameMap = partitioner.getObjectMap(BerlinModelTaxonNameImport.NAMESPACE);
|
114
|
Map<String, Reference> refMap = partitioner.getObjectMap(BerlinModelReferenceImport.REFERENCE_NAMESPACE);
|
115
|
|
116
|
ResultSet rs = partitioner.getResultSet();
|
117
|
|
118
|
Reference sourceRef = state.getTransactionalSourceReference();
|
119
|
try {
|
120
|
int i = 0;
|
121
|
//for each reference
|
122
|
while (rs.next() && (config.getMaximumNumberOfNameFacts() == 0 || i < config.getMaximumNumberOfNameFacts())){
|
123
|
|
124
|
if ((i++ % modCount) == 0 && i!= 1 ){ logger.info("NameFacts handled: " + (i-1));}
|
125
|
|
126
|
int nameFactId = rs.getInt("nameFactId");
|
127
|
int nameId = rs.getInt("nameId");
|
128
|
Object nameFactRefFkObj = rs.getObject("nameFactRefFk");
|
129
|
String nameFactRefDetail = rs.getString("nameFactRefDetail");
|
130
|
|
131
|
String category = CdmUtils.Nz(rs.getString("NameFactCategory"));
|
132
|
String nameFact = CdmUtils.Nz(rs.getString("nameFact"));
|
133
|
|
134
|
TaxonName taxonNameBase = nameMap.get(String.valueOf(nameId));
|
135
|
String nameFactRefFk = String.valueOf(nameFactRefFkObj);
|
136
|
Reference citation = refMap.get(nameFactRefFk);
|
137
|
|
138
|
if (taxonNameBase != null){
|
139
|
//PROTOLOGUE
|
140
|
if (category.equalsIgnoreCase(NAME_FACT_PROTOLOGUE)){
|
141
|
//Reference ref = (Reference)taxonNameBase.getNomenclaturalReference();
|
142
|
//ref = Book.NewInstance();
|
143
|
try{
|
144
|
Media media = getMedia(nameFact, config.getMediaUrl(), config.getMediaPath());
|
145
|
if (media.getRepresentations().size() > 0){
|
146
|
TaxonNameDescription description = TaxonNameDescription.NewInstance();
|
147
|
TextData protolog = TextData.NewInstance(Feature.PROTOLOGUE());
|
148
|
protolog.addMedia(media);
|
149
|
protolog.addSource(OriginalSourceType.Import, String.valueOf(nameFactId), NAMESPACE, null, null, null, null);
|
150
|
description.addElement(protolog);
|
151
|
taxonNameBase.addDescription(description);
|
152
|
if (citation != null){
|
153
|
description.addSource(OriginalSourceType.PrimaryTaxonomicSource, null, null, citation, null);
|
154
|
protolog.addSource(OriginalSourceType.PrimaryTaxonomicSource, null, null, citation, nameFactRefDetail, null, null);
|
155
|
}
|
156
|
}//end NAME_FACT_PROTOLOGUE
|
157
|
}catch(NullPointerException e){
|
158
|
logger.warn("MediaUrl and/or MediaPath not set. Could not get protologue.");
|
159
|
success = false;
|
160
|
}
|
161
|
}else if (category.equalsIgnoreCase(NAME_FACT_ALSO_PUBLISHED_IN)){
|
162
|
if (StringUtils.isNotBlank(nameFact)){
|
163
|
TaxonNameDescription description = TaxonNameDescription.NewInstance();
|
164
|
TextData additionalPublication = TextData.NewInstance(Feature.ADDITIONAL_PUBLICATION());
|
165
|
//TODO language
|
166
|
Language language = Language.DEFAULT();
|
167
|
additionalPublication.putText(language, nameFact);
|
168
|
additionalPublication.addSource(OriginalSourceType.Import, String.valueOf(nameFactId), NAMESPACE, null,null, null, null);
|
169
|
if (citation != null || isNotBlank(nameFactRefDetail)){
|
170
|
additionalPublication.addSource(OriginalSourceType.PrimaryTaxonomicSource, null, null, citation, nameFactRefDetail, null, null);
|
171
|
}
|
172
|
description.addElement(additionalPublication);
|
173
|
taxonNameBase.addDescription(description);
|
174
|
}
|
175
|
}else if (category.equalsIgnoreCase(NAME_FACT_BIBLIOGRAPHY)){
|
176
|
if (StringUtils.isNotBlank(nameFact)){
|
177
|
TaxonNameDescription description = TaxonNameDescription.NewInstance();
|
178
|
TextData bibliography = TextData.NewInstance(Feature.CITATION());
|
179
|
//TODO language
|
180
|
Language language = Language.DEFAULT();
|
181
|
bibliography.putText(language, nameFact);
|
182
|
bibliography.addSource(OriginalSourceType.Import, String.valueOf(nameFactId), NAMESPACE, null,null, null, null);
|
183
|
if (citation != null || isNotBlank(nameFactRefDetail)){
|
184
|
bibliography.addSource(OriginalSourceType.PrimaryTaxonomicSource, null, null, citation, nameFactRefDetail, null, null);
|
185
|
}
|
186
|
description.addElement(bibliography);
|
187
|
taxonNameBase.addDescription(description);
|
188
|
}
|
189
|
}else {
|
190
|
//TODO
|
191
|
logger.warn("NameFactCategory '" + category + "' not yet implemented");
|
192
|
success = false;
|
193
|
}
|
194
|
|
195
|
//TODO
|
196
|
// DoubtfulFlag bit Checked
|
197
|
// PublishFlag bit Checked
|
198
|
// Created_When datetime Checked
|
199
|
// Updated_When datetime Checked
|
200
|
// Created_Who nvarchar(255) Checked
|
201
|
// Updated_Who nvarchar(255) Checked
|
202
|
// Notes nvarchar(1000) Checked
|
203
|
|
204
|
nameToSave.add(taxonNameBase);
|
205
|
}else{
|
206
|
//TODO
|
207
|
logger.warn("TaxonName for NameFact " + nameFactId + " does not exist in store");
|
208
|
success = false;
|
209
|
}
|
210
|
//put
|
211
|
}
|
212
|
if (config.getMaximumNumberOfNameFacts() != 0 && i >= config.getMaximumNumberOfNameFacts() - 1){
|
213
|
logger.warn("ONLY " + config.getMaximumNumberOfNameFacts() + " NAMEFACTS imported !!!" )
|
214
|
;};
|
215
|
logger.info("Names to save: " + nameToSave.size());
|
216
|
getNameService().save(nameToSave);
|
217
|
return success;
|
218
|
} catch (SQLException e) {
|
219
|
logger.error("SQLException:" + e);
|
220
|
return false;
|
221
|
}
|
222
|
|
223
|
}
|
224
|
|
225
|
|
226
|
@Override
|
227
|
public Map<Object, Map<String, ? extends CdmBase>> getRelatedObjectsForPartition(ResultSet rs, BerlinModelImportState state) {
|
228
|
String nameSpace;
|
229
|
Class<?> cdmClass;
|
230
|
Set<String> idSet;
|
231
|
Map<Object, Map<String, ? extends CdmBase>> result = new HashMap<Object, Map<String, ? extends CdmBase>>();
|
232
|
|
233
|
try{
|
234
|
Set<String> nameIdSet = new HashSet<String>();
|
235
|
Set<String> referenceIdSet = new HashSet<String>();
|
236
|
while (rs.next()){
|
237
|
handleForeignKey(rs, nameIdSet, "PTnameFk");
|
238
|
handleForeignKey(rs, referenceIdSet, "nameFactRefFk");
|
239
|
}
|
240
|
|
241
|
//name map
|
242
|
nameSpace = BerlinModelTaxonNameImport.NAMESPACE;
|
243
|
cdmClass = TaxonName.class;
|
244
|
idSet = nameIdSet;
|
245
|
Map<String, Person> objectMap = (Map<String, Person>)getCommonService().getSourcedObjectsByIdInSource(cdmClass, idSet, nameSpace);
|
246
|
result.put(nameSpace, objectMap);
|
247
|
|
248
|
//reference map
|
249
|
nameSpace = BerlinModelReferenceImport.REFERENCE_NAMESPACE;
|
250
|
cdmClass = Reference.class;
|
251
|
idSet = referenceIdSet;
|
252
|
Map<String, Reference> referenceMap = (Map<String, Reference>)getCommonService().getSourcedObjectsByIdInSource(cdmClass, idSet, nameSpace);
|
253
|
result.put(nameSpace, referenceMap);
|
254
|
|
255
|
|
256
|
} catch (SQLException e) {
|
257
|
throw new RuntimeException(e);
|
258
|
}
|
259
|
return result;
|
260
|
}
|
261
|
|
262
|
|
263
|
//FIXME gibt es da keine allgemeine Methode in common?
|
264
|
public Media getMedia(String nameFact, URL mediaUrl, File mediaPath){
|
265
|
if (mediaUrl == null){
|
266
|
logger.warn("Media Url should not be null");
|
267
|
return null;
|
268
|
}
|
269
|
String mimeTypeTif = "image/tiff";
|
270
|
String mimeTypeJpg = "image/jpeg";
|
271
|
String mimeTypePng = "image/png";
|
272
|
String mimeTypePdf = "application/pdf";
|
273
|
String suffixTif = "tif";
|
274
|
String suffixJpg = "jpg";
|
275
|
String suffixPng = "png";
|
276
|
String suffixPdf = "pdf";
|
277
|
|
278
|
String sep = File.separator;
|
279
|
Integer size = null;
|
280
|
|
281
|
logger.debug("Getting media for NameFact: " + nameFact);
|
282
|
|
283
|
Media media = Media.NewInstance();
|
284
|
|
285
|
String mediaUrlString = mediaUrl.toString();
|
286
|
|
287
|
//tiff
|
288
|
String urlStringTif = mediaUrlString + "tif/" + nameFact + "." + suffixTif;
|
289
|
File file = new File(mediaPath, "tif" + sep + nameFact + "." + suffixTif);
|
290
|
MediaRepresentation representationTif = MediaRepresentation.NewInstance(mimeTypeTif, suffixTif);
|
291
|
if (file.exists()){
|
292
|
representationTif.addRepresentationPart(makeImage(urlStringTif, size, file));
|
293
|
}
|
294
|
if(representationTif.getParts().size() > 0){
|
295
|
media.addRepresentation(representationTif);
|
296
|
}
|
297
|
// end tif
|
298
|
// jpg
|
299
|
boolean fileExists = true;
|
300
|
int jpgCount = 0;
|
301
|
MediaRepresentation representationJpg = MediaRepresentation.NewInstance(mimeTypeJpg, suffixJpg);
|
302
|
while(fileExists){
|
303
|
String urlStringJpeg = mediaUrlString + "cmd_jpg/" + nameFact + "_page_000" + jpgCount + "." + suffixJpg;
|
304
|
file = new File(mediaPath, "cmd_jpg" + sep + nameFact + "_page_000" + jpgCount + "." + suffixJpg);
|
305
|
jpgCount++;
|
306
|
if (file.exists()){
|
307
|
representationJpg.addRepresentationPart(makeImage(urlStringJpeg, size, file));
|
308
|
}else{
|
309
|
fileExists = false;
|
310
|
}
|
311
|
}
|
312
|
if(representationJpg.getParts().size() > 0){
|
313
|
media.addRepresentation(representationJpg);
|
314
|
}
|
315
|
// end jpg
|
316
|
//png
|
317
|
String urlStringPng = mediaUrlString + "png/" + nameFact + "." + suffixPng;
|
318
|
file = new File(mediaPath, "png" + sep + nameFact + "." + suffixPng);
|
319
|
MediaRepresentation representationPng = MediaRepresentation.NewInstance(mimeTypePng, suffixPng);
|
320
|
if (file.exists()){
|
321
|
representationPng.addRepresentationPart(makeImage(urlStringPng, size, file));
|
322
|
}else{
|
323
|
fileExists = true;
|
324
|
int pngCount = 0;
|
325
|
while (fileExists){
|
326
|
pngCount++;
|
327
|
urlStringPng = mediaUrlString + "png/" + nameFact + "00" + pngCount + "." + suffixPng;
|
328
|
file = new File(mediaPath, "png" + sep + nameFact + "00" + pngCount + "." + suffixPng);
|
329
|
|
330
|
if (file.exists()){
|
331
|
representationPng.addRepresentationPart(makeImage(urlStringPng, size, file));
|
332
|
}else{
|
333
|
fileExists = false;
|
334
|
}
|
335
|
}
|
336
|
}
|
337
|
if(representationPng.getParts().size() > 0){
|
338
|
media.addRepresentation(representationPng);
|
339
|
}
|
340
|
//end png
|
341
|
//pdf
|
342
|
String urlStringPdf = mediaUrlString + "pdf/" + nameFact + "." + suffixPdf;
|
343
|
URI uriPdf;
|
344
|
try {
|
345
|
uriPdf = new URI(urlStringPdf);
|
346
|
file = new File(mediaPath, "pdf" + sep + nameFact + "." + suffixPdf);
|
347
|
MediaRepresentation representationPdf = MediaRepresentation.NewInstance(mimeTypePdf, suffixPdf);
|
348
|
if (file.exists()){
|
349
|
representationPdf.addRepresentationPart(MediaRepresentationPart.NewInstance(uriPdf, size));
|
350
|
}else{
|
351
|
fileExists = true;
|
352
|
int pdfCount = 0;
|
353
|
while (fileExists){
|
354
|
pdfCount++;
|
355
|
urlStringPdf = mediaUrlString + "pdf/" + nameFact + "00" + pdfCount + "." + suffixPdf;
|
356
|
file = new File(mediaPath, "pdf/" + sep + nameFact + "00" + pdfCount + "." + suffixPdf);
|
357
|
|
358
|
if (file.exists()){
|
359
|
representationPdf.addRepresentationPart(MediaRepresentationPart.NewInstance(uriPdf, size));
|
360
|
}else{
|
361
|
fileExists = false;
|
362
|
}
|
363
|
}
|
364
|
}
|
365
|
if(representationPdf.getParts().size() > 0){
|
366
|
media.addRepresentation(representationPdf);
|
367
|
}
|
368
|
} catch (URISyntaxException e) {
|
369
|
e.printStackTrace();
|
370
|
logger.error("URISyntaxException" + urlStringPdf);
|
371
|
}
|
372
|
//end pdf
|
373
|
|
374
|
if(logger.isDebugEnabled()){
|
375
|
for (MediaRepresentation rep : media.getRepresentations()){
|
376
|
for (MediaRepresentationPart part : rep.getParts()){
|
377
|
logger.debug("in representation: " + part.getUri());
|
378
|
}
|
379
|
}
|
380
|
}
|
381
|
|
382
|
return media;
|
383
|
}
|
384
|
|
385
|
|
386
|
private ImageFile makeImage(String imageUri, Integer size, File file){
|
387
|
ImageInfo imageMetaData = null;
|
388
|
URI uri;
|
389
|
try {
|
390
|
uri = new URI(imageUri);
|
391
|
try {
|
392
|
imageMetaData = ImageInfo.NewInstance(uri, 0);
|
393
|
} catch (IOException e) {
|
394
|
logger.error("IOError reading image metadata." , e);
|
395
|
} catch (HttpException e) {
|
396
|
logger.error("HttpException reading image metadata." , e);
|
397
|
}
|
398
|
ImageFile image = ImageFile.NewInstance(uri, size, imageMetaData);
|
399
|
return image;
|
400
|
} catch (URISyntaxException e1) {
|
401
|
logger.warn("URISyntaxException: " + imageUri);
|
402
|
return null;
|
403
|
}
|
404
|
|
405
|
}
|
406
|
|
407
|
|
408
|
/* (non-Javadoc)
|
409
|
* @see eu.etaxonomy.cdm.io.common.CdmIoBase#doCheck(eu.etaxonomy.cdm.io.common.IoStateBase)
|
410
|
*/
|
411
|
@Override
|
412
|
protected boolean doCheck(BerlinModelImportState state){
|
413
|
IOValidator<BerlinModelImportState> validator = new BerlinModelNameFactsImportValidator();
|
414
|
return validator.validate(state);
|
415
|
}
|
416
|
|
417
|
|
418
|
/* (non-Javadoc)
|
419
|
* @see eu.etaxonomy.cdm.io.common.CdmIoBase#isIgnore(eu.etaxonomy.cdm.io.common.IImportConfigurator)
|
420
|
*/
|
421
|
@Override
|
422
|
protected boolean isIgnore(BerlinModelImportState state){
|
423
|
return ! state.getConfig().isDoNameFacts();
|
424
|
}
|
425
|
|
426
|
|
427
|
|
428
|
//for testing only
|
429
|
public static void main(String[] args) {
|
430
|
|
431
|
BerlinModelNameFactsImport nf = new BerlinModelNameFactsImport();
|
432
|
|
433
|
URL url;
|
434
|
try {
|
435
|
url = new URL("http://wp5.e-taxonomy.eu/dataportal/cichorieae/media/protolog/");
|
436
|
File path = new File("/Volumes/protolog/protolog/");
|
437
|
if(path.exists()){
|
438
|
String fact = "Acanthocephalus_amplexifolius";
|
439
|
// make getMedia public for this to work
|
440
|
Media media = nf.getMedia(fact, url, path);
|
441
|
logger.info(media);
|
442
|
for (MediaRepresentation rep : media.getRepresentations()){
|
443
|
logger.info(rep.getMimeType());
|
444
|
for (MediaRepresentationPart part : rep.getParts()){
|
445
|
logger.info(part.getUri());
|
446
|
}
|
447
|
}
|
448
|
}
|
449
|
} catch (MalformedURLException e) {
|
450
|
e.printStackTrace();
|
451
|
}
|
452
|
}
|
453
|
}
|