|
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.strategy.parser;
|
|
11
|
|
|
12
|
import java.util.regex.Matcher;
|
|
13
|
import java.util.regex.Pattern;
|
|
14
|
|
|
15
|
import org.apache.log4j.Logger;
|
|
16
|
import org.joda.time.DateTimeFieldType;
|
|
17
|
import org.joda.time.Partial;
|
|
18
|
|
|
19
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
|
20
|
import eu.etaxonomy.cdm.model.agent.Person;
|
|
21
|
import eu.etaxonomy.cdm.model.agent.Team;
|
|
22
|
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
|
|
23
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
|
24
|
import eu.etaxonomy.cdm.model.common.IParsable;
|
|
25
|
import eu.etaxonomy.cdm.model.common.TimePeriod;
|
|
26
|
import eu.etaxonomy.cdm.model.name.BacterialName;
|
|
27
|
import eu.etaxonomy.cdm.model.name.BotanicalName;
|
|
28
|
import eu.etaxonomy.cdm.model.name.CultivarPlantName;
|
|
29
|
import eu.etaxonomy.cdm.model.name.NomenclaturalCode;
|
|
30
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
|
|
31
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatusType;
|
|
32
|
import eu.etaxonomy.cdm.model.name.NonViralName;
|
|
33
|
import eu.etaxonomy.cdm.model.name.Rank;
|
|
34
|
import eu.etaxonomy.cdm.model.name.TaxonNameBase;
|
|
35
|
import eu.etaxonomy.cdm.model.name.ZoologicalName;
|
|
36
|
import eu.etaxonomy.cdm.model.reference.IBook;
|
|
37
|
import eu.etaxonomy.cdm.model.reference.IBookSection;
|
|
38
|
import eu.etaxonomy.cdm.model.reference.INomenclaturalReference;
|
|
39
|
import eu.etaxonomy.cdm.model.reference.IVolumeReference;
|
|
40
|
import eu.etaxonomy.cdm.model.reference.ReferenceBase;
|
|
41
|
import eu.etaxonomy.cdm.model.reference.ReferenceFactory;
|
|
42
|
import eu.etaxonomy.cdm.model.reference.ReferenceType;
|
|
43
|
import eu.etaxonomy.cdm.strategy.exceptions.StringNotParsableException;
|
|
44
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
|
45
|
|
|
46
|
|
|
47
|
/**
|
|
48
|
* @author a.mueller
|
|
49
|
*
|
|
50
|
*/
|
|
51
|
public class NonViralNameParserImpl extends NonViralNameParserImplRegExBase implements INonViralNameParser<NonViralName> {
|
|
52
|
private static final Logger logger = Logger.getLogger(NonViralNameParserImpl.class);
|
|
53
|
|
|
54
|
// good intro: http://java.sun.com/docs/books/tutorial/essential/regex/index.html
|
|
55
|
|
|
56
|
final static boolean MAKE_EMPTY = true;
|
|
57
|
final static boolean MAKE_NOT_EMPTY = false;
|
|
58
|
|
|
59
|
private boolean authorIsAlwaysTeam = true;
|
|
60
|
private ReferenceFactory refFactory = ReferenceFactory.newInstance();
|
|
61
|
|
|
62
|
|
|
63
|
public static NonViralNameParserImpl NewInstance(){
|
|
64
|
return new NonViralNameParserImpl();
|
|
65
|
}
|
|
66
|
|
|
67
|
/* (non-Javadoc)
|
|
68
|
* @see eu.etaxonomy.cdm.strategy.ITaxonNameParser#parseSubGenericSimpleName(java.lang.String)
|
|
69
|
*/
|
|
70
|
public NonViralName parseSimpleName(String simpleName){
|
|
71
|
return parseSimpleName(simpleName, null, null);
|
|
72
|
}
|
|
73
|
|
|
74
|
|
|
75
|
/* (non-Javadoc)
|
|
76
|
* @see eu.etaxonomy.cdm.strategy.parser.INonViralNameParser#parseSimpleName(java.lang.String, eu.etaxonomy.cdm.model.name.NomenclaturalCode, eu.etaxonomy.cdm.model.name.Rank)
|
|
77
|
*/
|
|
78
|
public NonViralName parseSimpleName(String simpleName, NomenclaturalCode code, Rank rank){
|
|
79
|
//"parseSimpleName() not yet implemented. Uses parseFullName() instead");
|
|
80
|
return parseFullName(simpleName, code, rank);
|
|
81
|
}
|
|
82
|
|
|
83
|
public void parseSimpleName(NonViralName nameToBeFilled, String simpleNameString, Rank rank, boolean makeEmpty){
|
|
84
|
//"parseSimpleName() not yet implemented. Uses parseFullName() instead");
|
|
85
|
parseFullName(nameToBeFilled, simpleNameString, rank, makeEmpty);
|
|
86
|
}
|
|
87
|
|
|
88
|
|
|
89
|
public NonViralName getNonViralNameInstance(String fullString, NomenclaturalCode code){
|
|
90
|
return getNonViralNameInstance(fullString, code, null);
|
|
91
|
}
|
|
92
|
|
|
93
|
public NonViralName getNonViralNameInstance(String fullString, NomenclaturalCode code, Rank rank){
|
|
94
|
NonViralName result = null;
|
|
95
|
if(code ==null) {
|
|
96
|
boolean isBotanicalName = anyBotanicFullNamePattern.matcher(fullString).find();
|
|
97
|
boolean isZoologicalName = anyZooFullNamePattern.matcher(fullString).find();;
|
|
98
|
boolean isBacteriologicalName = false;
|
|
99
|
boolean isCultivatedPlantName = false;
|
|
100
|
if ( (isBotanicalName || isCultivatedPlantName) && ! isZoologicalName && !isBacteriologicalName){
|
|
101
|
if (isBotanicalName){
|
|
102
|
result = BotanicalName.NewInstance(rank);
|
|
103
|
}else{
|
|
104
|
result = CultivarPlantName.NewInstance(rank);
|
|
105
|
}
|
|
106
|
}else if ( isZoologicalName /*&& ! isBotanicalName*/ && !isBacteriologicalName && !isCultivatedPlantName){
|
|
107
|
result = ZoologicalName.NewInstance(rank);
|
|
108
|
}else if ( isZoologicalName && ! isBotanicalName && !isBacteriologicalName && !isCultivatedPlantName){
|
|
109
|
result = BacterialName.NewInstance(rank);
|
|
110
|
}else {
|
|
111
|
result = NonViralName.NewInstance(rank);
|
|
112
|
}
|
|
113
|
} else {
|
|
114
|
switch (code) {
|
|
115
|
case ICBN:
|
|
116
|
result = BotanicalName.NewInstance(rank);
|
|
117
|
break;
|
|
118
|
case ICZN:
|
|
119
|
result = ZoologicalName.NewInstance(rank);
|
|
120
|
break;
|
|
121
|
case ICNCP:
|
|
122
|
logger.warn("ICNCP parsing not yet implemented");
|
|
123
|
result = CultivarPlantName.NewInstance(rank);
|
|
124
|
break;
|
|
125
|
case ICNB:
|
|
126
|
logger.warn("ICNB not yet implemented");
|
|
127
|
result = BacterialName.NewInstance(rank);
|
|
128
|
break;
|
|
129
|
case ICVCN:
|
|
130
|
logger.error("Viral name is not a NonViralName !!");
|
|
131
|
break;
|
|
132
|
default:
|
|
133
|
// FIXME Unreachable code
|
|
134
|
logger.error("Unknown Nomenclatural Code !!");
|
|
135
|
}
|
|
136
|
}
|
|
137
|
return result;
|
|
138
|
}
|
|
139
|
|
|
140
|
|
|
141
|
/* (non-Javadoc)
|
|
142
|
* @see eu.etaxonomy.cdm.strategy.parser.INonViralNameParser#parseFullReference(java.lang.String)
|
|
143
|
*/
|
|
144
|
public NonViralName parseReferencedName(String fullReferenceString) {
|
|
145
|
return parseReferencedName(fullReferenceString, null, null);
|
|
146
|
}
|
|
147
|
|
|
148
|
/* (non-Javadoc)
|
|
149
|
* @see eu.etaxonomy.cdm.strategy.ITaxonNameParser#parseFullReference(java.lang.String, eu.etaxonomy.cdm.model.name.Rank)
|
|
150
|
*/
|
|
151
|
public NonViralName parseReferencedName(String fullReferenceString, NomenclaturalCode nomCode, Rank rank) {
|
|
152
|
if (fullReferenceString == null){
|
|
153
|
return null;
|
|
154
|
}else{
|
|
155
|
NonViralName result = getNonViralNameInstance(fullReferenceString, nomCode, rank);
|
|
156
|
parseReferencedName(result, fullReferenceString, rank, MAKE_EMPTY);
|
|
157
|
return result;
|
|
158
|
}
|
|
159
|
}
|
|
160
|
|
|
161
|
private String standardize(NonViralName nameToBeFilled, String fullReferenceString, boolean makeEmpty){
|
|
162
|
//Check null and standardize
|
|
163
|
if (fullReferenceString == null){
|
|
164
|
//return null;
|
|
165
|
return null;
|
|
166
|
}
|
|
167
|
if (makeEmpty){
|
|
168
|
makeEmpty(nameToBeFilled);
|
|
169
|
}
|
|
170
|
fullReferenceString = fullReferenceString.replaceAll(oWs , " ");
|
|
171
|
fullReferenceString = fullReferenceString.trim();
|
|
172
|
if ("".equals(fullReferenceString)){
|
|
173
|
fullReferenceString = null;
|
|
174
|
}
|
|
175
|
return fullReferenceString;
|
|
176
|
}
|
|
177
|
|
|
178
|
/**
|
|
179
|
* Returns the regEx to be used for the full-name depending on the code
|
|
180
|
* @param nameToBeFilled
|
|
181
|
* @return
|
|
182
|
*/
|
|
183
|
private String getLocalFullName(NonViralName nameToBeFilled){
|
|
184
|
if (nameToBeFilled instanceof ZoologicalName){
|
|
185
|
return anyZooFullName;
|
|
186
|
}else if (nameToBeFilled instanceof BotanicalName) {
|
|
187
|
return anyBotanicFullName;
|
|
188
|
}else if (nameToBeFilled instanceof NonViralName) {
|
|
189
|
return anyBotanicFullName; //TODO ?
|
|
190
|
}else{
|
|
191
|
logger.warn("nameToBeFilled class not supported ("+nameToBeFilled.getClass()+")");
|
|
192
|
return null;
|
|
193
|
}
|
|
194
|
}
|
|
195
|
|
|
196
|
/**
|
|
197
|
* Returns the regEx to be used for the fsimple-name depending on the code
|
|
198
|
* @param nameToBeFilled
|
|
199
|
* @return
|
|
200
|
*/
|
|
201
|
private String getLocalSimpleName(NonViralName nameToBeFilled){
|
|
202
|
if (nameToBeFilled instanceof ZoologicalName){
|
|
203
|
return anyZooName;
|
|
204
|
}else if (nameToBeFilled instanceof NonViralName){
|
|
205
|
return anyZooName; //TODO ?
|
|
206
|
}else if (nameToBeFilled instanceof BotanicalName) {
|
|
207
|
return anyBotanicName;
|
|
208
|
}else{
|
|
209
|
logger.warn("nameToBeFilled class not supported ("+nameToBeFilled.getClass()+")");
|
|
210
|
return null;
|
|
211
|
}
|
|
212
|
}
|
|
213
|
|
|
214
|
private Matcher getMatcher(String regEx, String matchString){
|
|
215
|
Pattern pattern = Pattern.compile(regEx);
|
|
216
|
Matcher matcher = pattern.matcher(matchString);
|
|
217
|
return matcher;
|
|
218
|
}
|
|
219
|
|
|
220
|
/* (non-Javadoc)
|
|
221
|
* @see eu.etaxonomy.cdm.strategy.ITaxonNameParser#parseFullReference(eu.etaxonomy.cdm.model.name.BotanicalName, java.lang.String, eu.etaxonomy.cdm.model.name.Rank, boolean)
|
|
222
|
*/
|
|
223
|
public void parseReferencedName(NonViralName nameToBeFilled, String fullReferenceString, Rank rank, boolean makeEmpty) {
|
|
224
|
//standardize
|
|
225
|
fullReferenceString = standardize(nameToBeFilled, fullReferenceString, makeEmpty);
|
|
226
|
if (fullReferenceString == null){
|
|
227
|
return;
|
|
228
|
}
|
|
229
|
// happens already in standardize(...)
|
|
230
|
// makeProblemEmpty(nameToBeFilled);
|
|
231
|
|
|
232
|
//make nomenclatural status and replace it by empty string
|
|
233
|
fullReferenceString = parseNomStatus(fullReferenceString, nameToBeFilled);
|
|
234
|
nameToBeFilled.setProblemEnds(fullReferenceString.length());
|
|
235
|
|
|
236
|
//get full name reg
|
|
237
|
String localFullName = getLocalFullName(nameToBeFilled);
|
|
238
|
//get full name reg
|
|
239
|
String localSimpleName = getLocalSimpleName(nameToBeFilled);
|
|
240
|
|
|
241
|
//separate name and reference part
|
|
242
|
String nameAndRefSeparator = "(^" + localFullName + ")("+ referenceSeperator + ")";
|
|
243
|
Matcher nameAndRefSeparatorMatcher = getMatcher (nameAndRefSeparator, fullReferenceString);
|
|
244
|
|
|
245
|
Matcher onlyNameMatcher = getMatcher (localFullName, fullReferenceString);
|
|
246
|
Matcher onlySimpleNameMatcher = getMatcher (localSimpleName, fullReferenceString);
|
|
247
|
|
|
248
|
if (nameAndRefSeparatorMatcher.find()){
|
|
249
|
makeNameWithReference(nameToBeFilled, fullReferenceString, nameAndRefSeparatorMatcher, rank, makeEmpty);
|
|
250
|
}else if (onlyNameMatcher.matches()){
|
|
251
|
makeEmpty = false;
|
|
252
|
parseFullName(nameToBeFilled, fullReferenceString, rank, makeEmpty);
|
|
253
|
}else if (onlySimpleNameMatcher.matches()){
|
|
254
|
makeEmpty = false;
|
|
255
|
parseFullName(nameToBeFilled, fullReferenceString, rank, makeEmpty); //simpleName not yet implemented
|
|
256
|
}else{
|
|
257
|
makeNoFullRefMatch(nameToBeFilled, fullReferenceString, rank);
|
|
258
|
}
|
|
259
|
//problem handling. Start and end solved in subroutines
|
|
260
|
if (! nameToBeFilled.hasProblem()){
|
|
261
|
makeProblemEmpty(nameToBeFilled);
|
|
262
|
}
|
|
263
|
}
|
|
264
|
|
|
265
|
private void makeProblemEmpty(IParsable parsable){
|
|
266
|
boolean hasCheckRank = parsable.hasProblem(ParserProblem.CheckRank);
|
|
267
|
parsable.setParsingProblem(0);
|
|
268
|
if (hasCheckRank){
|
|
269
|
parsable.addParsingProblem(ParserProblem.CheckRank);
|
|
270
|
}
|
|
271
|
parsable.setProblemStarts(-1);
|
|
272
|
parsable.setProblemEnds(-1);
|
|
273
|
}
|
|
274
|
|
|
275
|
private void makeNoFullRefMatch(NonViralName nameToBeFilled, String fullReferenceString, Rank rank){
|
|
276
|
//try to parse first part as name, but keep in mind full string is not parsable
|
|
277
|
int start = 0;
|
|
278
|
|
|
279
|
String localFullName = getLocalFullName(nameToBeFilled);
|
|
280
|
Matcher fullNameMatcher = getMatcher (pStart + localFullName, fullReferenceString);
|
|
281
|
if (fullNameMatcher.find()){
|
|
282
|
String fullNameString = fullNameMatcher.group(0);
|
|
283
|
nameToBeFilled.setProtectedNameCache(false);
|
|
284
|
parseFullName(nameToBeFilled, fullNameString, rank, false);
|
|
285
|
String sure = nameToBeFilled.getNameCache();
|
|
286
|
start = sure.length();
|
|
287
|
}
|
|
288
|
|
|
289
|
// String localSimpleName = getLocalSimpleName(nameToBeFilled);
|
|
290
|
// Matcher simpleNameMatcher = getMatcher (start + localSimpleName, fullReferenceString);
|
|
291
|
// if (simpleNameMatcher.find()){
|
|
292
|
// String simpleNameString = simpleNameMatcher.group(0);
|
|
293
|
// parseFullName(nameToBeFilled, simpleNameString, rank, false);
|
|
294
|
// start = simpleNameString.length();
|
|
295
|
// }
|
|
296
|
|
|
297
|
//don't parse if name can't be separated
|
|
298
|
nameToBeFilled.addParsingProblem(ParserProblem.NameReferenceSeparation);
|
|
299
|
nameToBeFilled.setTitleCache(fullReferenceString,true);
|
|
300
|
nameToBeFilled.setFullTitleCache(fullReferenceString,true);
|
|
301
|
// FIXME Quick fix, otherwise search would not deliver results for unparsable names
|
|
302
|
nameToBeFilled.setNameCache(fullReferenceString,true);
|
|
303
|
// END
|
|
304
|
nameToBeFilled.setProblemStarts(start);
|
|
305
|
nameToBeFilled.setProblemEnds(fullReferenceString.length());
|
|
306
|
logger.info("no applicable parsing rule could be found for \"" + fullReferenceString + "\"");
|
|
307
|
}
|
|
308
|
|
|
309
|
private void makeNameWithReference(NonViralName nameToBeFilled,
|
|
310
|
String fullReferenceString,
|
|
311
|
Matcher nameAndRefSeparatorMatcher,
|
|
312
|
Rank rank,
|
|
313
|
boolean makeEmpty){
|
|
314
|
|
|
315
|
String nameAndSeparator = nameAndRefSeparatorMatcher.group(0);
|
|
316
|
String name = nameAndRefSeparatorMatcher.group(1);
|
|
317
|
String referenceString = fullReferenceString.substring(nameAndRefSeparatorMatcher.end());
|
|
318
|
|
|
319
|
// is reference an in ref?
|
|
320
|
String separator = nameAndSeparator.substring(name.length());
|
|
321
|
boolean isInReference = separator.matches(inReferenceSeparator);
|
|
322
|
|
|
323
|
//parse subparts
|
|
324
|
|
|
325
|
int oldProblemEnds = nameToBeFilled.getProblemEnds();
|
|
326
|
parseFullName(nameToBeFilled, name, rank, makeEmpty);
|
|
327
|
nameToBeFilled.setProblemEnds(oldProblemEnds);
|
|
328
|
|
|
329
|
//zoological new combinations should not have a nom. reference to be parsed
|
|
330
|
if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
|
331
|
ZoologicalName zooName = CdmBase.deproxy(nameToBeFilled, ZoologicalName.class);
|
|
332
|
//is name new combination?
|
|
333
|
if (zooName.getBasionymAuthorTeam() != null || zooName.getOriginalPublicationYear() != null){
|
|
334
|
ParserProblem parserProblem = ParserProblem.NewCombinationHasPublication;
|
|
335
|
zooName.addParsingProblem(parserProblem);
|
|
336
|
nameToBeFilled.setProblemStarts((nameToBeFilled.getProblemStarts()> -1) ? nameToBeFilled.getProblemStarts(): name.length());
|
|
337
|
nameToBeFilled.setProblemEnds(Math.max(fullReferenceString.length(), nameToBeFilled.getProblemEnds()));
|
|
338
|
}
|
|
339
|
}
|
|
340
|
|
|
341
|
parseReference(nameToBeFilled, referenceString, isInReference);
|
|
342
|
INomenclaturalReference ref = (INomenclaturalReference)nameToBeFilled.getNomenclaturalReference();
|
|
343
|
|
|
344
|
//problem start
|
|
345
|
int start = nameToBeFilled.getProblemStarts();
|
|
346
|
int nameLength = name.length();
|
|
347
|
int nameAndSeparatorLength = nameAndSeparator.length();
|
|
348
|
int fullRefLength = nameToBeFilled.getFullTitleCache().length();
|
|
349
|
|
|
350
|
if (nameToBeFilled.isProtectedTitleCache() || nameToBeFilled.getParsingProblems().contains(ParserProblem.CheckRank)){
|
|
351
|
start = Math.max(0, start);
|
|
352
|
}else{
|
|
353
|
if (ref != null && ref.getParsingProblem()!=0){
|
|
354
|
start = Math.max(nameAndSeparatorLength, start);
|
|
355
|
//TODO search within ref
|
|
356
|
}
|
|
357
|
}
|
|
358
|
|
|
359
|
//end
|
|
360
|
int end = nameToBeFilled.getProblemEnds();
|
|
361
|
|
|
362
|
if (ref != null && ref.getParsingProblem()!=0){
|
|
363
|
end = Math.min(nameAndSeparatorLength + ref.getProblemEnds(), end);
|
|
364
|
}else{
|
|
365
|
if (nameToBeFilled.isProtectedTitleCache() ){
|
|
366
|
end = Math.min(end, nameAndSeparatorLength);
|
|
367
|
//TODO search within name
|
|
368
|
}
|
|
369
|
}
|
|
370
|
nameToBeFilled.setProblemStarts(start);
|
|
371
|
nameToBeFilled.setProblemEnds(end);
|
|
372
|
|
|
373
|
//delegate has problem to name
|
|
374
|
if (ref != null && ref.getParsingProblem()!=0){
|
|
375
|
nameToBeFilled.addParsingProblems(ref.getParsingProblem());
|
|
376
|
}
|
|
377
|
|
|
378
|
ReferenceBase nomRef;
|
|
379
|
if ( (nomRef = (ReferenceBase)nameToBeFilled.getNomenclaturalReference()) != null ){
|
|
380
|
nomRef.setAuthorTeam((TeamOrPersonBase)nameToBeFilled.getCombinationAuthorTeam());
|
|
381
|
}
|
|
382
|
}
|
|
383
|
|
|
384
|
//TODO make it an Array of status
|
|
385
|
/**
|
|
386
|
* Extracts a {@link NomenclaturalStatus} from the reference String and adds it to the @link {@link TaxonNameBase}.
|
|
387
|
* The nomenclatural status part ist deleted from the reference String.
|
|
388
|
* @return String the new (shortend) reference String
|
|
389
|
*/
|
|
390
|
private String parseNomStatus(String fullString, NonViralName nameToBeFilled) {
|
|
391
|
String statusString;
|
|
392
|
Pattern hasStatusPattern = Pattern.compile("(" + pNomStatusPhrase + ")");
|
|
393
|
Matcher hasStatusMatcher = hasStatusPattern.matcher(fullString);
|
|
394
|
|
|
395
|
if (hasStatusMatcher.find()) {
|
|
396
|
String statusPhrase = hasStatusMatcher.group(0);
|
|
397
|
|
|
398
|
Pattern statusPattern = Pattern.compile(pNomStatus);
|
|
399
|
Matcher statusMatcher = statusPattern.matcher(statusPhrase);
|
|
400
|
statusMatcher.find();
|
|
401
|
statusString = statusMatcher.group(0);
|
|
402
|
try {
|
|
403
|
NomenclaturalStatusType nomStatusType = NomenclaturalStatusType.getNomenclaturalStatusTypeByAbbreviation(statusString);
|
|
404
|
NomenclaturalStatus nomStatus = NomenclaturalStatus.NewInstance(nomStatusType);
|
|
405
|
nameToBeFilled.addStatus(nomStatus);
|
|
406
|
|
|
407
|
fullString = fullString.replace(statusPhrase, "");
|
|
408
|
} catch (UnknownCdmTypeException e) {
|
|
409
|
//Do nothing
|
|
410
|
}
|
|
411
|
}
|
|
412
|
return fullString;
|
|
413
|
}
|
|
414
|
|
|
415
|
|
|
416
|
private void parseReference(NonViralName nameToBeFilled, String strReference, boolean isInReference){
|
|
417
|
|
|
418
|
INomenclaturalReference ref;
|
|
419
|
String originalStrReference = strReference;
|
|
420
|
|
|
421
|
//End (just delete end (e.g. '.', may be ambigous for yearPhrase, but no real information gets lost
|
|
422
|
Matcher endMatcher = getMatcher(referenceEnd + end, strReference);
|
|
423
|
if (endMatcher.find()){
|
|
424
|
String endPart = endMatcher.group(0);
|
|
425
|
strReference = strReference.substring(0, strReference.length() - endPart.length());
|
|
426
|
}
|
|
427
|
|
|
428
|
// String pDetailYear = ".*" + detailSeparator + detail + fWs + yearSeperator + fWs + yearPhrase + fWs + end;
|
|
429
|
// Matcher detailYearMatcher = getMatcher(pDetailYear, strReference);
|
|
430
|
|
|
431
|
String strReferenceWithYear = strReference;
|
|
432
|
//year
|
|
433
|
String yearPart = null;
|
|
434
|
String pYearPhrase = yearSeperator + fWs + yearPhrase + fWs + end;
|
|
435
|
Matcher yearPhraseMatcher = getMatcher(pYearPhrase, strReference);
|
|
436
|
if (yearPhraseMatcher.find()){
|
|
437
|
yearPart = yearPhraseMatcher.group(0);
|
|
438
|
strReference = strReference.substring(0, strReference.length() - yearPart.length());
|
|
439
|
yearPart = yearPart.replaceFirst(pStart + yearSeperator, "").trim();
|
|
440
|
}else{
|
|
441
|
if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
|
442
|
ZoologicalName zooName = CdmBase.deproxy(nameToBeFilled, ZoologicalName.class);
|
|
443
|
yearPart = String.valueOf(zooName.getPublicationYear());
|
|
444
|
//continue
|
|
445
|
}else{
|
|
446
|
ref = makeDetailYearUnparsable(nameToBeFilled,strReference);
|
|
447
|
ref.setDatePublished(TimePeriod.parseString(yearPart));
|
|
448
|
return;
|
|
449
|
}
|
|
450
|
}
|
|
451
|
|
|
452
|
|
|
453
|
//detail
|
|
454
|
String pDetailPhrase = detailSeparator + fWs + detail + fWs + end;
|
|
455
|
Matcher detailPhraseMatcher = getMatcher(pDetailPhrase, strReference);
|
|
456
|
if (detailPhraseMatcher.find()){
|
|
457
|
String detailPart = detailPhraseMatcher.group(0);
|
|
458
|
strReference = strReference.substring(0, strReference.length() - detailPart.length());
|
|
459
|
detailPart = detailPart.replaceFirst(pStart + detailSeparator, "").trim();
|
|
460
|
nameToBeFilled.setNomenclaturalMicroReference(detailPart);
|
|
461
|
}else{
|
|
462
|
makeDetailYearUnparsable(nameToBeFilled, strReferenceWithYear);
|
|
463
|
return;
|
|
464
|
}
|
|
465
|
//parse title and author
|
|
466
|
ref = parseReferenceTitle(strReference, yearPart, isInReference);
|
|
467
|
if (ref.hasProblem()){
|
|
468
|
ref.setTitleCache( (isInReference?"in ":"") + originalStrReference,true);
|
|
469
|
}
|
|
470
|
nameToBeFilled.setNomenclaturalReference((ReferenceBase)ref);
|
|
471
|
int end = Math.min(strReference.length(), ref.getProblemEnds());
|
|
472
|
ref.setProblemEnds(end);
|
|
473
|
}
|
|
474
|
|
|
475
|
/**
|
|
476
|
* @param nameToBeFilled
|
|
477
|
* @param strReference
|
|
478
|
* @return
|
|
479
|
*/
|
|
480
|
private INomenclaturalReference makeDetailYearUnparsable(NonViralName nameToBeFilled, String strReference) {
|
|
481
|
INomenclaturalReference ref;
|
|
482
|
//ref = Generic.NewInstance();
|
|
483
|
|
|
484
|
ref = refFactory.newGeneric();
|
|
485
|
ref.setTitleCache(strReference,true);
|
|
486
|
ref.setProblemEnds(strReference.length());
|
|
487
|
ref.addParsingProblem(ParserProblem.CheckDetailOrYear);
|
|
488
|
nameToBeFilled.addParsingProblem(ParserProblem.CheckDetailOrYear);
|
|
489
|
nameToBeFilled.setNomenclaturalReference((ReferenceBase)ref);
|
|
490
|
return ref;
|
|
491
|
}
|
|
492
|
|
|
493
|
/**
|
|
494
|
* Parses the referenceTitlePart, including the author volume and edition.
|
|
495
|
* @param reference
|
|
496
|
* @param year
|
|
497
|
* @return
|
|
498
|
*/
|
|
499
|
private INomenclaturalReference parseReferenceTitle(String strReference, String year, boolean isInReference){
|
|
500
|
IBook result = null;
|
|
501
|
|
|
502
|
Matcher refSineDetailMatcher = referenceSineDetailPattern.matcher(strReference);
|
|
503
|
if (! refSineDetailMatcher.matches()){
|
|
504
|
//TODO ?
|
|
505
|
}
|
|
506
|
|
|
507
|
Matcher articleMatcher = getMatcher(pArticleReference, strReference);
|
|
508
|
|
|
509
|
Matcher softArticleMatcher = getMatcher(pSoftArticleReference, strReference);
|
|
510
|
Matcher bookMatcher = getMatcher(pBookReference, strReference);
|
|
511
|
Matcher bookSectionMatcher = getMatcher(pBookSectionReference, strReference);
|
|
512
|
|
|
513
|
|
|
514
|
if(isInReference == false){
|
|
515
|
if (bookMatcher.matches() ){
|
|
516
|
result = parseBook(strReference);
|
|
517
|
}else{
|
|
518
|
logger.warn("Non-InRef must be book but does not match book");
|
|
519
|
result = refFactory.newBook();
|
|
520
|
makeUnparsableRefTitle(result, strReference);
|
|
521
|
}
|
|
522
|
}else{ //inRef
|
|
523
|
if (articleMatcher.matches()){
|
|
524
|
//article without separators like ","
|
|
525
|
result = parseArticle(strReference);
|
|
526
|
}else if (softArticleMatcher.matches()){
|
|
527
|
result = parseArticle(strReference);
|
|
528
|
}else if (bookSectionMatcher.matches()){
|
|
529
|
result = parseBookSection(strReference);
|
|
530
|
}else{
|
|
531
|
result = refFactory.newGeneric();
|
|
532
|
makeUnparsableRefTitle(result, "in " + strReference);
|
|
533
|
}
|
|
534
|
}
|
|
535
|
//make year
|
|
536
|
if (makeYear(result, year) == false){
|
|
537
|
//TODO
|
|
538
|
logger.warn("Year could not be parsed");
|
|
539
|
}
|
|
540
|
result.setProblemStarts(0);
|
|
541
|
result.setProblemEnds(strReference.length());
|
|
542
|
return result;
|
|
543
|
}
|
|
544
|
|
|
545
|
private void makeUnparsableRefTitle(INomenclaturalReference result, String reference){
|
|
546
|
result.setTitleCache(reference,true);
|
|
547
|
result.addParsingProblem(ParserProblem.UnparsableReferenceTitle);
|
|
548
|
}
|
|
549
|
|
|
550
|
/**
|
|
551
|
* Parses a single date string. If the string is not parsable a StringNotParsableException is thrown
|
|
552
|
* @param singleDateString
|
|
553
|
* @return
|
|
554
|
* @throws StringNotParsableException
|
|
555
|
*/
|
|
556
|
private static Partial parseSingleDate(String singleDateString)
|
|
557
|
throws StringNotParsableException{
|
|
558
|
Partial dt = new Partial();
|
|
559
|
if (CdmUtils.isNumeric(singleDateString)){
|
|
560
|
try {
|
|
561
|
Integer year = Integer.valueOf(singleDateString.trim());
|
|
562
|
if (year > 1750 && year < 2050){
|
|
563
|
dt = dt.with(DateTimeFieldType.year(), year);
|
|
564
|
}else{
|
|
565
|
dt = null;
|
|
566
|
}
|
|
567
|
} catch (NumberFormatException e) {
|
|
568
|
logger.debug("Not a Integer format in getCalendar()");
|
|
569
|
throw new StringNotParsableException(singleDateString + "is not parsable as a single Date");
|
|
570
|
}
|
|
571
|
}
|
|
572
|
return dt;
|
|
573
|
}
|
|
574
|
|
|
575
|
|
|
576
|
/**
|
|
577
|
* Parses the publication date part.
|
|
578
|
* @param nomRef
|
|
579
|
* @param year
|
|
580
|
* @return If the string is not parsable <code>false</code>
|
|
581
|
* is returned. <code>True</code> otherwise
|
|
582
|
*/
|
|
583
|
private boolean makeYear(INomenclaturalReference nomRef, String year){
|
|
584
|
boolean result = true;
|
|
585
|
if (year == null){
|
|
586
|
return false;
|
|
587
|
}
|
|
588
|
if ("".equals(year.trim())){
|
|
589
|
return true;
|
|
590
|
}
|
|
591
|
TimePeriod datePublished = TimePeriod.parseString(year);
|
|
592
|
|
|
593
|
if (nomRef.getType().equals(ReferenceType.BookSection)){
|
|
594
|
handleBookSectionYear((IBookSection)nomRef, datePublished);
|
|
595
|
}else if (nomRef instanceof ReferenceBase){
|
|
596
|
((ReferenceBase)nomRef).setDatePublished(datePublished);
|
|
597
|
}else{
|
|
598
|
throw new ClassCastException("nom Ref is not of type ReferenceBase but " + (nomRef == null? "(null)" : nomRef.getClass()));
|
|
599
|
}
|
|
600
|
return result;
|
|
601
|
}
|
|
602
|
|
|
603
|
private String makeVolume(IVolumeReference nomRef, String strReference){
|
|
604
|
//volume
|
|
605
|
String volPart = null;
|
|
606
|
String pVolPhrase = volumeSeparator + volume + end;
|
|
607
|
Matcher volPhraseMatcher = getMatcher(pVolPhrase, strReference);
|
|
608
|
if (volPhraseMatcher.find()){
|
|
609
|
volPart = volPhraseMatcher.group(0);
|
|
610
|
strReference = strReference.substring(0, strReference.length() - volPart.length());
|
|
611
|
volPart = volPart.replaceFirst(pStart + volumeSeparator, "").trim();
|
|
612
|
nomRef.setVolume(volPart);
|
|
613
|
}
|
|
614
|
return strReference;
|
|
615
|
}
|
|
616
|
|
|
617
|
private String makeEdition(IBook book, String strReference){
|
|
618
|
//volume
|
|
619
|
String editionPart = null;
|
|
620
|
Matcher editionPhraseMatcher = getMatcher(pEditionPart, strReference);
|
|
621
|
|
|
622
|
Matcher editionVolumeMatcher = getMatcher(pEditionVolPart, strReference);
|
|
623
|
boolean isEditionAndVol = editionVolumeMatcher.find();
|
|
624
|
|
|
625
|
if (editionPhraseMatcher.find()){
|
|
626
|
editionPart = editionPhraseMatcher.group(0);
|
|
627
|
int pos = strReference.indexOf(editionPart);
|
|
628
|
int posEnd = pos + editionPart.length();
|
|
629
|
if (isEditionAndVol){
|
|
630
|
posEnd++; //delete also comma
|
|
631
|
}
|
|
632
|
strReference = strReference.substring(0, pos) + strReference.substring(posEnd);
|
|
633
|
editionPart = editionPart.replaceFirst(pStart + editionSeparator, "").trim();
|
|
634
|
book.setEdition(editionPart);
|
|
635
|
}
|
|
636
|
return strReference;
|
|
637
|
}
|
|
638
|
|
|
639
|
private IBook parseBook(String reference){
|
|
640
|
IBook result = refFactory.newBook();
|
|
641
|
reference = makeEdition(result, reference);
|
|
642
|
reference = makeVolume(result, reference);
|
|
643
|
result.setTitle(reference);
|
|
644
|
return result;
|
|
645
|
}
|
|
646
|
|
|
647
|
|
|
648
|
private ReferenceBase parseArticle(String reference){
|
|
649
|
//if (articlePatter)
|
|
650
|
//(type, author, title, volume, editor, series;
|
|
651
|
ReferenceBase result = refFactory.newArticle();
|
|
652
|
reference = makeVolume(result, reference);
|
|
653
|
ReferenceBase inJournal = refFactory.newJournal();
|
|
654
|
inJournal.setTitle(reference);
|
|
655
|
result.setInReference(inJournal);
|
|
656
|
return result;
|
|
657
|
}
|
|
658
|
|
|
659
|
private ReferenceBase parseBookSection(String reference){
|
|
660
|
ReferenceBase result = refFactory.newBookSection();
|
|
661
|
String[] parts = reference.split(referenceAuthorSeparator, 2);
|
|
662
|
if (parts.length != 2){
|
|
663
|
logger.warn("Unexpected number of parts");
|
|
664
|
result.setTitleCache(reference,true);
|
|
665
|
}else{
|
|
666
|
String authorString = parts[0];
|
|
667
|
String bookString = parts[1];
|
|
668
|
|
|
669
|
TeamOrPersonBase<?> authorTeam = author(authorString);
|
|
670
|
IBook inBook = parseBook(bookString);
|
|
671
|
inBook.setAuthorTeam(authorTeam);
|
|
672
|
result.setInBook(inBook);
|
|
673
|
}
|
|
674
|
return result;
|
|
675
|
}
|
|
676
|
|
|
677
|
/**
|
|
678
|
* If the publication date of a book section and it's inBook do differ this is usually
|
|
679
|
* caused by the fact that a book has been published during a period, because originally
|
|
680
|
* it consisted of several parts that only later where put together to one book.
|
|
681
|
* If so, the book section's publication date may be a point in time (year or month of year)
|
|
682
|
* whereas the books publication date may be a period of several years.
|
|
683
|
* Therefore a valid nomenclatural reference string should use the book sections
|
|
684
|
* publication date rather then the book's publication date.<BR>
|
|
685
|
* This method in general adds the publication date to the book section.
|
|
686
|
* An exception exists if the publication date is a period. Then the parser
|
|
687
|
* assumes that the nomenclatural reference string does not follow the above rule but
|
|
688
|
* the books publication date is set.
|
|
689
|
* @param bookSection
|
|
690
|
* @param datePublished
|
|
691
|
*/
|
|
692
|
private void handleBookSectionYear(IBookSection bookSection, TimePeriod datePublished){
|
|
693
|
if (datePublished == null || datePublished.getStart() == null || bookSection == null){
|
|
694
|
return;
|
|
695
|
}
|
|
696
|
if (datePublished.isPeriod() && bookSection.getInBook() != null){
|
|
697
|
bookSection.getInBook().setDatePublished(datePublished);
|
|
698
|
}else{
|
|
699
|
bookSection.setDatePublished(datePublished);
|
|
700
|
}
|
|
701
|
}
|
|
702
|
|
|
703
|
|
|
704
|
/* (non-Javadoc)
|
|
705
|
* @see eu.etaxonomy.cdm.strategy.parser.INonViralNameParser#parseFullName(java.lang.String)
|
|
706
|
*/
|
|
707
|
public NonViralName parseFullName(String fullNameString){
|
|
708
|
return parseFullName(fullNameString, null, null);
|
|
709
|
}
|
|
710
|
|
|
711
|
|
|
712
|
/* (non-Javadoc)
|
|
713
|
* @see eu.etaxonomy.cdm.strategy.ITaxonNameParser#parseFullName(java.lang.String, eu.etaxonomy.cdm.model.name.Rank)
|
|
714
|
*/
|
|
715
|
public NonViralName parseFullName(String fullNameString, NomenclaturalCode nomCode, Rank rank) {
|
|
716
|
|
|
717
|
if (fullNameString == null){
|
|
718
|
return null;
|
|
719
|
}else{
|
|
720
|
NonViralName result = getNonViralNameInstance(fullNameString, nomCode, rank);
|
|
721
|
parseFullName(result, fullNameString, rank, false);
|
|
722
|
return result;
|
|
723
|
}
|
|
724
|
}
|
|
725
|
|
|
726
|
|
|
727
|
public void parseFullName(NonViralName nameToBeFilled, String fullNameString, Rank rank, boolean makeEmpty) {
|
|
728
|
//TODO prol. etc.
|
|
729
|
boolean hasCheckRankProblem = false; //was rank guessed in a previous parsing process?
|
|
730
|
if (nameToBeFilled == null){
|
|
731
|
logger.warn("name is null!");
|
|
732
|
}else{
|
|
733
|
hasCheckRankProblem = nameToBeFilled.hasProblem(ParserProblem.CheckRank);
|
|
734
|
nameToBeFilled.removeParsingProblem(ParserProblem.CheckRank);
|
|
735
|
}
|
|
736
|
String authorString = null;
|
|
737
|
|
|
738
|
if (fullNameString == null){
|
|
739
|
return;
|
|
740
|
}
|
|
741
|
|
|
742
|
if (makeEmpty){
|
|
743
|
makeEmpty(nameToBeFilled);
|
|
744
|
}
|
|
745
|
fullNameString.replaceAll(oWs , " ");
|
|
746
|
//TODO
|
|
747
|
// OLD: fullName = oWsRE.subst(fullName, " "); //substitute multiple whitespaces
|
|
748
|
fullNameString = fullNameString.trim();
|
|
749
|
|
|
750
|
String[] epi = pattern.split(fullNameString);
|
|
751
|
try {
|
|
752
|
//cultivars //TODO 2 implement cultivars
|
|
753
|
// if ( cultivarMarkerRE.match(fullName) ){ funktioniert noch nicht, da es z.B. auch Namen gibt, wie 't Hart
|
|
754
|
// result = parseCultivar(fullName);
|
|
755
|
// }
|
|
756
|
//hybrids //TODO 2 implement hybrids
|
|
757
|
//else
|
|
758
|
if (hybridPattern.matcher(fullNameString).matches() ){
|
|
759
|
nameToBeFilled = parseHybrid(fullNameString);
|
|
760
|
}
|
|
761
|
else if (genusOrSupraGenusPattern.matcher(fullNameString).matches()){
|
|
762
|
//supraGeneric
|
|
763
|
if (rank != null && ! hasCheckRankProblem && (rank.isSupraGeneric()|| rank.isGenus())){
|
|
764
|
nameToBeFilled.setRank(rank);
|
|
765
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
766
|
}
|
|
767
|
//genus or guess rank
|
|
768
|
else {
|
|
769
|
rank = guessUninomialRank(nameToBeFilled, epi[0]);
|
|
770
|
nameToBeFilled.setRank(rank);
|
|
771
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
772
|
nameToBeFilled.addParsingProblem(ParserProblem.CheckRank);
|
|
773
|
nameToBeFilled.setProblemStarts(0);
|
|
774
|
nameToBeFilled.setProblemEnds(epi[0].length());
|
|
775
|
}
|
|
776
|
authorString = fullNameString.substring(epi[0].length());
|
|
777
|
}
|
|
778
|
//infra genus
|
|
779
|
else if (infraGenusPattern.matcher(fullNameString).matches()){
|
|
780
|
nameToBeFilled.setRank(Rank.getRankByAbbreviation(epi[1]));
|
|
781
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
782
|
nameToBeFilled.setInfraGenericEpithet(epi[2]);
|
|
783
|
authorString = fullNameString.substring(epi[0].length() + 1 + epi[1].length()+ 1 + epi[2].length());
|
|
784
|
}
|
|
785
|
//aggr. or group
|
|
786
|
else if (aggrOrGroupPattern.matcher(fullNameString).matches()){
|
|
787
|
nameToBeFilled.setRank(Rank.getRankByAbbreviation(epi[2]));
|
|
788
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
789
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
|
790
|
}
|
|
791
|
//species
|
|
792
|
else if (speciesPattern.matcher(fullNameString).matches()){
|
|
793
|
nameToBeFilled.setRank(Rank.SPECIES());
|
|
794
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
795
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
|
796
|
authorString = fullNameString.substring(epi[0].length() + 1 + epi[1].length());
|
|
797
|
}
|
|
798
|
//autonym
|
|
799
|
else if (autonymPattern.matcher(fullNameString).matches()){
|
|
800
|
nameToBeFilled.setRank(Rank.getRankByAbbreviation(epi[epi.length - 2]));
|
|
801
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
802
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
|
803
|
nameToBeFilled.setInfraSpecificEpithet(epi[epi.length - 1]);
|
|
804
|
int lenSpecies = 2 + epi[0].length()+epi[1].length();
|
|
805
|
int lenInfraSpecies = 2 + epi[epi.length - 2].length() + epi[epi.length - 1].length();
|
|
806
|
authorString = fullNameString.substring(lenSpecies, fullNameString.length() - lenInfraSpecies);
|
|
807
|
}
|
|
808
|
//infraSpecies
|
|
809
|
else if (infraSpeciesPattern.matcher(fullNameString).matches()){
|
|
810
|
String infraSpecRankEpi = epi[2];
|
|
811
|
String infraSpecEpi = epi[3];
|
|
812
|
if ("tax.".equals(infraSpecRankEpi)){
|
|
813
|
infraSpecRankEpi += " " + epi[3];
|
|
814
|
infraSpecEpi = epi[4];
|
|
815
|
}
|
|
816
|
nameToBeFilled.setRank(Rank.getRankByAbbreviation(infraSpecRankEpi));
|
|
817
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
818
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
|
819
|
nameToBeFilled.setInfraSpecificEpithet(infraSpecEpi);
|
|
820
|
authorString = fullNameString.substring(epi[0].length()+ 1 + epi[1].length() +1 + infraSpecRankEpi.length() + 1 + infraSpecEpi.length());
|
|
821
|
}//old infraSpecies
|
|
822
|
else if (oldInfraSpeciesPattern.matcher(fullNameString).matches()){
|
|
823
|
boolean implemented = false;
|
|
824
|
if (implemented){
|
|
825
|
nameToBeFilled.setRank(Rank.getRankByNameOrAbbreviation(epi[2]));
|
|
826
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
|
827
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
|
828
|
//TODO result.setUnnamedNamePhrase(epi[2] + " " + epi[3]);
|
|
829
|
authorString = fullNameString.substring(epi[0].length()+ 1 + epi[1].length() +1 + epi[2].length() + 1 + epi[3].length());
|
|
830
|
}else{
|
|
831
|
nameToBeFilled.addParsingProblem(ParserProblem.OldInfraSpeciesNotSupported);
|
|
832
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
|
833
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
|
834
|
nameToBeFilled.setNameCache(fullNameString,true);
|
|
835
|
// END
|
|
836
|
logger.info("Name string " + fullNameString + " could not be parsed because UnnnamedNamePhrase is not yet implemented!");
|
|
837
|
}
|
|
838
|
}
|
|
839
|
//none
|
|
840
|
else{
|
|
841
|
nameToBeFilled.addParsingProblem(ParserProblem.UnparsableNamePart);
|
|
842
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
|
843
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
|
844
|
nameToBeFilled.setNameCache(fullNameString,true);
|
|
845
|
// END
|
|
846
|
logger.info("no applicable parsing rule could be found for \"" + fullNameString + "\"");
|
|
847
|
}
|
|
848
|
//authors
|
|
849
|
if (nameToBeFilled != null && authorString != null && authorString.trim().length() > 0 ){
|
|
850
|
TeamOrPersonBase<?>[] authors = new TeamOrPersonBase[4];
|
|
851
|
Integer[] years = new Integer[4];
|
|
852
|
try {
|
|
853
|
Class<? extends NonViralName> clazz = nameToBeFilled.getClass();
|
|
854
|
fullAuthors(authorString, authors, years, clazz);
|
|
855
|
} catch (StringNotParsableException e) {
|
|
856
|
nameToBeFilled.addParsingProblem(ParserProblem.UnparsableAuthorPart);
|
|
857
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
|
858
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
|
859
|
nameToBeFilled.setNameCache(fullNameString,true);
|
|
860
|
// END
|
|
861
|
logger.info("no applicable parsing rule could be found for \"" + fullNameString + "\"");;
|
|
862
|
}
|
|
863
|
nameToBeFilled.setCombinationAuthorTeam(authors[0]);
|
|
864
|
nameToBeFilled.setExCombinationAuthorTeam(authors[1]);
|
|
865
|
nameToBeFilled.setBasionymAuthorTeam(authors[2]);
|
|
866
|
nameToBeFilled.setExBasionymAuthorTeam(authors[3]);
|
|
867
|
if (nameToBeFilled instanceof ZoologicalName){
|
|
868
|
ZoologicalName zooName = (ZoologicalName)nameToBeFilled;
|
|
869
|
zooName.setPublicationYear(years[0]);
|
|
870
|
zooName.setOriginalPublicationYear(years[2]);
|
|
871
|
}
|
|
872
|
}
|
|
873
|
//return
|
|
874
|
if (nameToBeFilled != null){
|
|
875
|
//return(BotanicalName)result;
|
|
876
|
return;
|
|
877
|
}
|
|
878
|
} catch (UnknownCdmTypeException e) {
|
|
879
|
nameToBeFilled.addParsingProblem(ParserProblem.RankNotSupported);
|
|
880
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
|
881
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
|
882
|
nameToBeFilled.setNameCache(fullNameString,true);
|
|
883
|
// END
|
|
884
|
logger.info("unknown rank (" + (rank == null? "null":rank) + ") or abbreviation in string " + fullNameString);
|
|
885
|
//return result;
|
|
886
|
return;
|
|
887
|
}
|
|
888
|
}
|
|
889
|
|
|
890
|
|
|
891
|
|
|
892
|
/**
|
|
893
|
* Guesses the rank of uninomial depending on the typical endings for ranks
|
|
894
|
* @param nameToBeFilled
|
|
895
|
* @param string
|
|
896
|
*/
|
|
897
|
private Rank guessUninomialRank(NonViralName nameToBeFilled, String uninomial) {
|
|
898
|
Rank result = Rank.GENUS();
|
|
899
|
if (nameToBeFilled.isInstanceOf(BotanicalName.class)){
|
|
900
|
if (false){
|
|
901
|
//
|
|
902
|
}else if (uninomial.endsWith("phyta") || uninomial.endsWith("mycota") ){ //plants, fungi
|
|
903
|
result = Rank.SECTION_BOTANY();
|
|
904
|
}else if (uninomial.endsWith("bionta")){
|
|
905
|
result = Rank.SUBKINGDOM(); //TODO
|
|
906
|
}else if (uninomial.endsWith("phytina")|| uninomial.endsWith("mycotina") ){ //plants, fungi
|
|
907
|
result = Rank.SUBSECTION_BOTANY();
|
|
908
|
}else if (uninomial.endsWith("opsida") || uninomial.endsWith("phyceae") || uninomial.endsWith("mycetes")){ //plants, algae, fungi
|
|
909
|
result = Rank.CLASS();
|
|
910
|
}else if (uninomial.endsWith("idae") || uninomial.endsWith("phycidae") || uninomial.endsWith("mycetidae")){ //plants, algae, fungi
|
|
911
|
result = Rank.SUBCLASS();
|
|
912
|
}else if (uninomial.endsWith("ales")){
|
|
913
|
result = Rank.ORDER();
|
|
914
|
}else if (uninomial.endsWith("ineae")){
|
|
915
|
result = Rank.SUBORDER();
|
|
916
|
}else if (uninomial.endsWith("aceae")){
|
|
917
|
result = Rank.FAMILY();
|
|
918
|
}else if (uninomial.endsWith("oideae")){
|
|
919
|
result = Rank.SUBFAMILY();
|
|
920
|
}else if (uninomial.endsWith("eae")){
|
|
921
|
result = Rank.TRIBE();
|
|
922
|
}else if (uninomial.endsWith("inae")){
|
|
923
|
result = Rank.SUBTRIBE();
|
|
924
|
}else if (uninomial.endsWith("ota")){
|
|
925
|
result = Rank.KINGDOM(); //TODO
|
|
926
|
}
|
|
927
|
}else if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
|
928
|
if (false){
|
|
929
|
//
|
|
930
|
}else if (uninomial.endsWith("oideae")){
|
|
931
|
result = Rank.SUPERFAMILY();
|
|
932
|
}else if (uninomial.endsWith("idae")){
|
|
933
|
result = Rank.FAMILY();
|
|
934
|
}else if (uninomial.endsWith("inae")){
|
|
935
|
result = Rank.SUBFAMILY();
|
|
936
|
}else if (uninomial.endsWith("inae")){
|
|
937
|
result = Rank.SUBFAMILY();
|
|
938
|
}else if (uninomial.endsWith("ini")){
|
|
939
|
result = Rank.TRIBE();
|
|
940
|
}else if (uninomial.endsWith("ina")){
|
|
941
|
result = Rank.SUBTRIBE();
|
|
942
|
}
|
|
943
|
}else{
|
|
944
|
//
|
|
945
|
}
|
|
946
|
return result;
|
|
947
|
}
|
|
948
|
|
|
949
|
/**
|
|
950
|
* Parses the fullAuthorString
|
|
951
|
* @param fullAuthorString
|
|
952
|
* @return array of Teams containing the Team[0],
|
|
953
|
* ExTeam[1], BasionymTeam[2], ExBasionymTeam[3]
|
|
954
|
*/
|
|
955
|
protected void fullAuthors (String fullAuthorString, TeamOrPersonBase<?>[] authors, Integer[] years, Class<? extends NonViralName> clazz)
|
|
956
|
throws StringNotParsableException{
|
|
957
|
fullAuthorString = fullAuthorString.trim();
|
|
958
|
if (fullAuthorString == null || clazz == null){
|
|
959
|
return;
|
|
960
|
}
|
|
961
|
//Botanic
|
|
962
|
if ( BotanicalName.class.isAssignableFrom(clazz) ){
|
|
963
|
if (! fullBotanicAuthorStringPattern.matcher(fullAuthorString).matches() ){
|
|
964
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
|
965
|
}
|
|
966
|
}
|
|
967
|
//Zoo
|
|
968
|
else if ( ZoologicalName.class.isAssignableFrom(clazz) ){
|
|
969
|
if (! fullZooAuthorStringPattern.matcher(fullAuthorString).matches() ){
|
|
970
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
|
971
|
}
|
|
972
|
}else {
|
|
973
|
//TODO
|
|
974
|
logger.warn ("not yet implemented");
|
|
975
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
|
976
|
}
|
|
977
|
fullAuthorsChecked(fullAuthorString, authors, years);
|
|
978
|
}
|
|
979
|
|
|
980
|
/*
|
|
981
|
* like fullTeams but without trim and match check
|
|
982
|
*/
|
|
983
|
protected void fullAuthorsChecked (String fullAuthorString, TeamOrPersonBase<?>[] authors, Integer[] years){
|
|
984
|
int authorTeamStart = 0;
|
|
985
|
Matcher basionymMatcher = basionymPattern.matcher(fullAuthorString);
|
|
986
|
|
|
987
|
if (basionymMatcher.find(0)){
|
|
988
|
|
|
989
|
String basString = basionymMatcher.group();
|
|
990
|
basString = basString.replaceFirst(basStart, "");
|
|
991
|
basString = basString.replaceAll(basEnd, "").trim();
|
|
992
|
authorTeamStart = basionymMatcher.end(1) + 1;
|
|
993
|
|
|
994
|
TeamOrPersonBase<?>[] basAuthors = new TeamOrPersonBase[2];
|
|
995
|
Integer[] basYears = new Integer[2];
|
|
996
|
authorsAndEx(basString, basAuthors, basYears);
|
|
997
|
authors[2]= basAuthors[0];
|
|
998
|
years[2] = basYears[0];
|
|
999
|
authors[3]= basAuthors[1];
|
|
1000
|
years[3] = basYears[1];
|
|
1001
|
}
|
|
1002
|
if (fullAuthorString.length() >= authorTeamStart){
|
|
1003
|
TeamOrPersonBase<?>[] combinationAuthors = new TeamOrPersonBase[2];;
|
|
1004
|
Integer[] combinationYears = new Integer[2];
|
|
1005
|
authorsAndEx(fullAuthorString.substring(authorTeamStart), combinationAuthors, combinationYears);
|
|
1006
|
authors[0]= combinationAuthors[0] ;
|
|
1007
|
years[0] = combinationYears[0];
|
|
1008
|
authors[1]= combinationAuthors[1];
|
|
1009
|
years[1] = combinationYears[1];
|
|
1010
|
}
|
|
1011
|
}
|
|
1012
|
|
|
1013
|
|
|
1014
|
/**
|
|
1015
|
* Parses the author and ex-author String
|
|
1016
|
* @param authorTeamString String representing the author and the ex-author team
|
|
1017
|
* @return array of Teams containing the Team[0] and the ExTeam[1]
|
|
1018
|
*/
|
|
1019
|
protected void authorsAndEx (String authorTeamString, TeamOrPersonBase<?>[] authors, Integer[] years){
|
|
1020
|
//TODO noch allgemeiner am anfang durch Replace etc.
|
|
1021
|
authorTeamString = authorTeamString.trim();
|
|
1022
|
authorTeamString = authorTeamString.replaceFirst(oWs + "ex" + oWs, " ex. " );
|
|
1023
|
int authorEnd = authorTeamString.length();
|
|
1024
|
|
|
1025
|
Matcher exAuthorMatcher = exAuthorPattern.matcher(authorTeamString);
|
|
1026
|
if (exAuthorMatcher.find(0)){
|
|
1027
|
int exAuthorBegin = exAuthorMatcher.end(0);
|
|
1028
|
String exString = authorTeamString.substring(exAuthorBegin).trim();
|
|
1029
|
authorEnd = exAuthorMatcher.start(0);
|
|
1030
|
authors [1] = author(exString);
|
|
1031
|
}
|
|
1032
|
zooOrBotanicAuthor(authorTeamString.substring(0, authorEnd), authors, years );
|
|
1033
|
}
|
|
1034
|
|
|
1035
|
/**
|
|
1036
|
* Parses the authorString and if it matches an botanical or zoological authorTeam it fills
|
|
1037
|
* the computes the AuthorTeam and fills it into the first field of the team array. Same applies
|
|
1038
|
* to the year in case of an zoological name.
|
|
1039
|
* @param authorString
|
|
1040
|
* @param team
|
|
1041
|
* @param year
|
|
1042
|
*/
|
|
1043
|
protected void zooOrBotanicAuthor(String authorString, TeamOrPersonBase<?>[] team, Integer[] year){
|
|
1044
|
if (authorString == null){
|
|
1045
|
return;
|
|
1046
|
}else if ((authorString = authorString.trim()).length() == 0){
|
|
1047
|
return;
|
|
1048
|
}
|
|
1049
|
Matcher zooAuthorAddidtionMatcher = zooAuthorAddidtionPattern.matcher(authorString);
|
|
1050
|
if (zooAuthorAddidtionMatcher.find()){
|
|
1051
|
int index = zooAuthorAddidtionMatcher.start(0);
|
|
1052
|
String strYear = authorString.substring(index);
|
|
1053
|
strYear = strYear.replaceAll(zooAuthorYearSeperator, "").trim();
|
|
1054
|
year[0] = Integer.valueOf(strYear);
|
|
1055
|
authorString = authorString.substring(0, index).trim();
|
|
1056
|
}
|
|
1057
|
team[0] = author(authorString);
|
|
1058
|
}
|
|
1059
|
|
|
1060
|
|
|
1061
|
/**
|
|
1062
|
* Parses an authorTeam String and returns the Team
|
|
1063
|
* !!! TODO (atomization not yet implemented)
|
|
1064
|
* @param authorTeamString String representing the author team
|
|
1065
|
* @return an Team
|
|
1066
|
*/
|
|
1067
|
protected TeamOrPersonBase<?> author (String authorString){
|
|
1068
|
if (authorString == null){
|
|
1069
|
return null;
|
|
1070
|
}else if ((authorString = authorString.trim()).length() == 0){
|
|
1071
|
return null;
|
|
1072
|
}else if (! teamSplitterPattern.matcher(authorString).find() && ! authorIsAlwaysTeam){
|
|
1073
|
//1 Person
|
|
1074
|
Person result = Person.NewInstance();
|
|
1075
|
result.setNomenclaturalTitle(authorString);
|
|
1076
|
return result;
|
|
1077
|
}else{
|
|
1078
|
return parsedTeam(authorString);
|
|
1079
|
}
|
|
1080
|
|
|
1081
|
}
|
|
1082
|
|
|
1083
|
/**
|
|
1084
|
* Parses an authorString (reprsenting a team into the single authors and add
|
|
1085
|
* them to the return Team.
|
|
1086
|
* @param authorString
|
|
1087
|
* @return Team
|
|
1088
|
*/
|
|
1089
|
protected Team parsedTeam(String authorString){
|
|
1090
|
Team result = Team.NewInstance();
|
|
1091
|
String[] authors = authorString.split(teamSplitter);
|
|
1092
|
for (String author : authors){
|
|
1093
|
Person person = Person.NewInstance();
|
|
1094
|
person.setNomenclaturalTitle(author);
|
|
1095
|
result.addTeamMember(person);
|
|
1096
|
}
|
|
1097
|
return result;
|
|
1098
|
}
|
|
1099
|
|
|
1100
|
|
|
1101
|
//Parsing of the given full name that has been identified as hybrid already somewhere else.
|
|
1102
|
private BotanicalName parseHybrid(String fullName){
|
|
1103
|
logger.warn("parseHybrid --> function not yet implemented");
|
|
1104
|
BotanicalName result = BotanicalName.NewInstance(null);
|
|
1105
|
result.setTitleCache(fullName,true);
|
|
1106
|
return result;
|
|
1107
|
}
|
|
1108
|
|
|
1109
|
// // Parsing of the given full name that has been identified as a cultivar already somwhere else.
|
|
1110
|
// // The ... cv. ... syntax is not covered here as it is not according the rules for naming cultivars.
|
|
1111
|
public BotanicalName parseCultivar(String fullName) throws StringNotParsableException{
|
|
1112
|
CultivarPlantName result = null;
|
|
1113
|
String[] words = oWsPattern.split(fullName);
|
|
1114
|
|
|
1115
|
/* ---------------------------------------------------------------------------------
|
|
1116
|
* cultivar
|
|
1117
|
* ---------------------------------------------------------------------------------*/
|
|
1118
|
if (fullName.indexOf(" '") != 0){
|
|
1119
|
//TODO location of 'xx' is probably not arbitrary
|
|
1120
|
Matcher cultivarMatcher = cultivarPattern.matcher(fullName);
|
|
1121
|
if (cultivarMatcher.find()){
|
|
1122
|
String namePart = fullName.replaceFirst(cultivar, "");
|
|
1123
|
|
|
1124
|
String cultivarPart = cultivarMatcher.group(0).replace("'","").trim();
|
|
1125
|
//OLD: String cultivarPart = cultivarRE.getParen(0).replace("'","").trim();
|
|
1126
|
|
|
1127
|
result = (CultivarPlantName)parseFullName(namePart);
|
|
1128
|
result.setCultivarName(cultivarPart);
|
|
1129
|
}
|
|
1130
|
}else if (fullName.indexOf(" cv.") != 0){
|
|
1131
|
// cv. is old form (not official)
|
|
1132
|
throw new StringNotParsableException("Cultivars with only cv. not yet implemented in name parser!");
|
|
1133
|
}
|
|
1134
|
|
|
1135
|
/* ---------------------------------------------------------------------------------
|
|
1136
|
* cultivar group
|
|
1137
|
* ---------------------------------------------------------------------------------
|
|
1138
|
*/
|
|
1139
|
// TODO in work
|
|
1140
|
//Ann. this is not the official way of noting cultivar groups
|
|
1141
|
String group = oWs + "Group" + oWs + capitalEpiWord + end;
|
|
1142
|
Pattern groupRE = Pattern.compile(group);
|
|
1143
|
Matcher groupMatcher = groupRE.matcher(fullName);
|
|
1144
|
if (groupMatcher.find()){
|
|
1145
|
if (! words[words.length - 2].equals("group")){
|
|
1146
|
throw new StringNotParsableException ("fct ParseHybrid --> term before cultivar group name in " + fullName + " should be 'group'");
|
|
1147
|
}else{
|
|
1148
|
|
|
1149
|
String namePart = fullName.substring(0, groupMatcher.start(0) - 0);
|
|
1150
|
//OLD: String namePart = fullName.substring(0, groupRE.getParenStart(0) - 0);
|
|
1151
|
|
|
1152
|
String cultivarPart = words[words.length -1];
|
|
1153
|
result = (CultivarPlantName)parseFullName(namePart);
|
|
1154
|
if (result != null){
|
|
1155
|
result.setCultivarName(cultivarPart);
|
|
1156
|
|
|
1157
|
//OLD: result.setCultivarGroupName(cultivarPart);
|
|
1158
|
}
|
|
1159
|
}
|
|
1160
|
|
|
1161
|
}
|
|
1162
|
// // ---------------------------------------------------------------------------------
|
|
1163
|
// if ( result = "" ){
|
|
1164
|
// return "I: fct ParseCultivar: --> could not parse cultivar " + fullName;
|
|
1165
|
// }else{
|
|
1166
|
// return result;
|
|
1167
|
// }
|
|
1168
|
return result; //TODO
|
|
1169
|
}
|
|
1170
|
|
|
1171
|
|
|
1172
|
private void makeEmpty(NonViralName nameToBeFilled){
|
|
1173
|
nameToBeFilled.setRank(null);
|
|
1174
|
nameToBeFilled.setTitleCache(null, false);
|
|
1175
|
nameToBeFilled.setFullTitleCache(null, false);
|
|
1176
|
nameToBeFilled.setNameCache(null, false);
|
|
1177
|
|
|
1178
|
nameToBeFilled.setAppendedPhrase(null);
|
|
1179
|
nameToBeFilled.setBasionymAuthorTeam(null);
|
|
1180
|
nameToBeFilled.setCombinationAuthorTeam(null);
|
|
1181
|
nameToBeFilled.setExBasionymAuthorTeam(null);
|
|
1182
|
nameToBeFilled.setExCombinationAuthorTeam(null);
|
|
1183
|
nameToBeFilled.setAuthorshipCache(null, false);
|
|
1184
|
|
|
1185
|
|
|
1186
|
//delete problems except check rank
|
|
1187
|
makeProblemEmpty(nameToBeFilled);
|
|
1188
|
|
|
1189
|
// TODO ?
|
|
1190
|
//nameToBeFilled.setHomotypicalGroup(newHomotypicalGroup);
|
|
1191
|
|
|
1192
|
|
|
1193
|
nameToBeFilled.setGenusOrUninomial(null);
|
|
1194
|
nameToBeFilled.setInfraGenericEpithet(null);
|
|
1195
|
nameToBeFilled.setSpecificEpithet(null);
|
|
1196
|
nameToBeFilled.setInfraSpecificEpithet(null);
|
|
1197
|
|
|
1198
|
nameToBeFilled.setNomenclaturalMicroReference(null);
|
|
1199
|
nameToBeFilled.setNomenclaturalReference(null);
|
|
1200
|
|
|
1201
|
nameToBeFilled.setHybridFormula(false);
|
|
1202
|
nameToBeFilled.setMonomHybrid(false);
|
|
1203
|
nameToBeFilled.setBinomHybrid(false);
|
|
1204
|
nameToBeFilled.setTrinomHybrid(false);
|
|
1205
|
|
|
1206
|
if (nameToBeFilled.isInstanceOf(BotanicalName.class)){
|
|
1207
|
BotanicalName botanicalName = (BotanicalName)nameToBeFilled;
|
|
1208
|
botanicalName.setAnamorphic(false);
|
|
1209
|
}
|
|
1210
|
|
|
1211
|
if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
|
1212
|
ZoologicalName zoologicalName = (ZoologicalName)nameToBeFilled;
|
|
1213
|
zoologicalName.setBreed(null);
|
|
1214
|
zoologicalName.setOriginalPublicationYear(null);
|
|
1215
|
|
|
1216
|
}
|
|
1217
|
}
|
|
1218
|
|
|
1219
|
|
|
1220
|
|
|
1221
|
}
|