1 |
ce7c7aa3
|
Andreas Müller
|
/**
|
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.HashSet;
|
13 |
|
|
import java.util.Set;
|
14 |
|
|
import java.util.regex.Matcher;
|
15 |
|
|
import java.util.regex.Pattern;
|
16 |
|
|
|
17 |
|
|
import org.apache.commons.lang.StringUtils;
|
18 |
|
|
import org.apache.log4j.Logger;
|
19 |
|
|
import org.joda.time.DateTimeFieldType;
|
20 |
|
|
import org.joda.time.Partial;
|
21 |
|
|
|
22 |
|
|
import eu.etaxonomy.cdm.common.CdmUtils;
|
23 |
|
|
import eu.etaxonomy.cdm.hibernate.HibernateProxyHelper;
|
24 |
|
|
import eu.etaxonomy.cdm.model.agent.Person;
|
25 |
|
|
import eu.etaxonomy.cdm.model.agent.Team;
|
26 |
|
|
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase;
|
27 |
|
|
import eu.etaxonomy.cdm.model.common.CdmBase;
|
28 |
|
|
import eu.etaxonomy.cdm.model.common.IParsable;
|
29 |
|
|
import eu.etaxonomy.cdm.model.common.TimePeriod;
|
30 |
|
|
import eu.etaxonomy.cdm.model.name.BacterialName;
|
31 |
|
|
import eu.etaxonomy.cdm.model.name.BotanicalName;
|
32 |
|
|
import eu.etaxonomy.cdm.model.name.CultivarPlantName;
|
33 |
|
|
import eu.etaxonomy.cdm.model.name.HybridRelationship;
|
34 |
|
|
import eu.etaxonomy.cdm.model.name.HybridRelationshipType;
|
35 |
|
|
import eu.etaxonomy.cdm.model.name.NomenclaturalCode;
|
36 |
|
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatus;
|
37 |
|
|
import eu.etaxonomy.cdm.model.name.NomenclaturalStatusType;
|
38 |
|
|
import eu.etaxonomy.cdm.model.name.NonViralName;
|
39 |
|
|
import eu.etaxonomy.cdm.model.name.Rank;
|
40 |
|
|
import eu.etaxonomy.cdm.model.name.TaxonNameBase;
|
41 |
|
|
import eu.etaxonomy.cdm.model.name.ZoologicalName;
|
42 |
|
|
import eu.etaxonomy.cdm.model.reference.IBook;
|
43 |
|
|
import eu.etaxonomy.cdm.model.reference.IBookSection;
|
44 |
|
|
import eu.etaxonomy.cdm.model.reference.INomenclaturalReference;
|
45 |
|
|
import eu.etaxonomy.cdm.model.reference.IVolumeReference;
|
46 |
|
|
import eu.etaxonomy.cdm.model.reference.Reference;
|
47 |
|
|
import eu.etaxonomy.cdm.model.reference.ReferenceFactory;
|
48 |
|
|
import eu.etaxonomy.cdm.model.reference.ReferenceType;
|
49 |
|
|
import eu.etaxonomy.cdm.strategy.exceptions.StringNotParsableException;
|
50 |
|
|
import eu.etaxonomy.cdm.strategy.exceptions.UnknownCdmTypeException;
|
51 |
|
|
|
52 |
|
|
|
53 |
|
|
/**
|
54 |
|
|
* @author a.mueller
|
55 |
|
|
*
|
56 |
|
|
*/
|
57 |
|
|
public class NonViralNameParserImpl extends NonViralNameParserImplRegExBase implements INonViralNameParser<NonViralName> {
|
58 |
|
|
private static final Logger logger = Logger.getLogger(NonViralNameParserImpl.class);
|
59 |
|
|
|
60 |
|
|
// good intro: http://java.sun.com/docs/books/tutorial/essential/regex/index.html
|
61 |
|
|
|
62 |
|
|
final static boolean MAKE_EMPTY = true;
|
63 |
|
|
final static boolean MAKE_NOT_EMPTY = false;
|
64 |
|
|
|
65 |
|
|
private final boolean authorIsAlwaysTeam = false;
|
66 |
|
|
|
67 |
|
|
public static NonViralNameParserImpl NewInstance(){
|
68 |
|
|
return new NonViralNameParserImpl();
|
69 |
|
|
}
|
70 |
|
|
|
71 |
|
|
@Override
|
72 |
|
|
public NonViralName parseSimpleName(String simpleName){
|
73 |
|
|
return parseSimpleName(simpleName, null, null);
|
74 |
|
|
}
|
75 |
|
|
|
76 |
|
|
@Override
|
77 |
|
|
public NonViralName parseSimpleName(String simpleName, NomenclaturalCode code, Rank rank){
|
78 |
|
|
//"parseSimpleName() not yet implemented. Uses parseFullName() instead");
|
79 |
|
|
return parseFullName(simpleName, code, rank);
|
80 |
|
|
}
|
81 |
|
|
|
82 |
|
|
public void parseSimpleName(NonViralName nameToBeFilled, String simpleNameString, Rank rank, boolean makeEmpty){
|
83 |
|
|
//"parseSimpleName() not yet implemented. Uses parseFullName() instead");
|
84 |
|
|
parseFullName(nameToBeFilled, simpleNameString, rank, makeEmpty);
|
85 |
|
|
}
|
86 |
|
|
|
87 |
|
|
public NonViralName getNonViralNameInstance(String fullString, NomenclaturalCode code){
|
88 |
|
|
return getNonViralNameInstance(fullString, code, null);
|
89 |
|
|
}
|
90 |
|
|
|
91 |
|
|
public NonViralName getNonViralNameInstance(String fullString, NomenclaturalCode code, Rank rank){
|
92 |
|
|
NonViralName<?> result = null;
|
93 |
|
|
if(code ==null) {
|
94 |
|
|
boolean isBotanicalName = anyBotanicFullNamePattern.matcher(fullString).find();
|
95 |
|
|
boolean isZoologicalName = anyZooFullNamePattern.matcher(fullString).find();;
|
96 |
|
|
boolean isBacteriologicalName = false;
|
97 |
|
|
boolean isCultivatedPlantName = false;
|
98 |
|
|
if ( (isBotanicalName || isCultivatedPlantName) && ! isZoologicalName && !isBacteriologicalName){
|
99 |
|
|
if (isBotanicalName){
|
100 |
|
|
result = BotanicalName.NewInstance(rank);
|
101 |
|
|
}else{
|
102 |
|
|
result = CultivarPlantName.NewInstance(rank);
|
103 |
|
|
}
|
104 |
|
|
}else if ( isZoologicalName /*&& ! isBotanicalName*/ && !isBacteriologicalName && !isCultivatedPlantName){
|
105 |
|
|
result = ZoologicalName.NewInstance(rank);
|
106 |
|
|
}else if ( isZoologicalName && ! isBotanicalName && !isBacteriologicalName && !isCultivatedPlantName){
|
107 |
|
|
result = BacterialName.NewInstance(rank);
|
108 |
|
|
}else {
|
109 |
|
|
result = NonViralName.NewInstance(rank);
|
110 |
|
|
}
|
111 |
|
|
} else {
|
112 |
|
|
switch (code) {
|
113 |
|
|
case ICNAFP:
|
114 |
|
|
result = BotanicalName.NewInstance(rank);
|
115 |
|
|
break;
|
116 |
|
|
case ICZN:
|
117 |
|
|
result = ZoologicalName.NewInstance(rank);
|
118 |
|
|
break;
|
119 |
|
|
case ICNCP:
|
120 |
|
|
logger.warn("ICNCP parsing not yet implemented");
|
121 |
|
|
result = CultivarPlantName.NewInstance(rank);
|
122 |
|
|
break;
|
123 |
|
|
case ICNB:
|
124 |
|
|
logger.warn("ICNB not yet implemented");
|
125 |
|
|
result = BacterialName.NewInstance(rank);
|
126 |
|
|
break;
|
127 |
|
|
case ICVCN:
|
128 |
|
|
logger.error("Viral name is not a NonViralName !!");
|
129 |
|
|
break;
|
130 |
|
|
default:
|
131 |
|
|
// FIXME Unreachable code
|
132 |
|
|
logger.error("Unknown Nomenclatural Code !!");
|
133 |
|
|
}
|
134 |
|
|
}
|
135 |
|
|
return result;
|
136 |
|
|
}
|
137 |
|
|
|
138 |
|
|
@Override
|
139 |
|
|
public NonViralName parseReferencedName(String fullReferenceString) {
|
140 |
|
|
return parseReferencedName(fullReferenceString, null, null);
|
141 |
|
|
}
|
142 |
|
|
|
143 |
|
|
@Override
|
144 |
|
|
public NonViralName parseReferencedName(String fullReferenceString, NomenclaturalCode nomCode, Rank rank) {
|
145 |
|
|
if (fullReferenceString == null){
|
146 |
|
|
return null;
|
147 |
|
|
}else{
|
148 |
|
|
NonViralName<?> result = getNonViralNameInstance(fullReferenceString, nomCode, rank);
|
149 |
|
|
parseReferencedName(result, fullReferenceString, rank, MAKE_EMPTY);
|
150 |
|
|
return result;
|
151 |
|
|
}
|
152 |
|
|
}
|
153 |
|
|
|
154 |
|
|
private String standardize(NonViralName<?> nameToBeFilled, String fullReferenceString, boolean makeEmpty){
|
155 |
|
|
//Check null and standardize
|
156 |
|
|
if (fullReferenceString == null){
|
157 |
|
|
//return null;
|
158 |
|
|
return null;
|
159 |
|
|
}
|
160 |
|
|
if (makeEmpty){
|
161 |
|
|
makeEmpty(nameToBeFilled);
|
162 |
|
|
}
|
163 |
|
|
fullReferenceString = fullReferenceString.replaceAll(oWs , " ");
|
164 |
|
|
fullReferenceString = fullReferenceString.trim();
|
165 |
|
|
if ("".equals(fullReferenceString)){
|
166 |
|
|
fullReferenceString = null;
|
167 |
|
|
}
|
168 |
|
|
return fullReferenceString;
|
169 |
|
|
}
|
170 |
|
|
|
171 |
|
|
/**
|
172 |
|
|
* Returns the regEx to be used for the full-name depending on the code
|
173 |
|
|
* @param nameToBeFilled
|
174 |
|
|
* @return
|
175 |
|
|
*/
|
176 |
|
|
private String getCodeSpecificFullNameRegEx(NonViralName<?> nameToBeFilledOrig){
|
177 |
|
|
NonViralName<?> nameToBeFilled = HibernateProxyHelper.deproxy(nameToBeFilledOrig, NonViralName.class);
|
178 |
|
|
if (nameToBeFilled instanceof ZoologicalName){
|
179 |
|
|
return anyZooFullName;
|
180 |
|
|
}else if (nameToBeFilled instanceof BotanicalName) {
|
181 |
|
|
return anyBotanicFullName;
|
182 |
|
|
}else if (nameToBeFilled instanceof NonViralName) {
|
183 |
|
|
return anyBotanicFullName; //TODO ?
|
184 |
|
|
}else{
|
185 |
|
|
logger.warn("nameToBeFilled class not supported ("+nameToBeFilled.getClass()+")");
|
186 |
|
|
return null;
|
187 |
|
|
}
|
188 |
|
|
}
|
189 |
|
|
|
190 |
|
|
/**
|
191 |
|
|
* Returns the regEx to be used for the fsimple-name depending on the code
|
192 |
|
|
* @param nameToBeFilled
|
193 |
|
|
* @return
|
194 |
|
|
*/
|
195 |
|
|
private String getCodeSpecificSimpleNameRegEx(NonViralName<?> nameToBeFilled){
|
196 |
|
|
nameToBeFilled = HibernateProxyHelper.deproxy(nameToBeFilled, NonViralName.class);
|
197 |
|
|
|
198 |
|
|
if (nameToBeFilled instanceof ZoologicalName){
|
199 |
|
|
return anyZooName;
|
200 |
|
|
}else if (nameToBeFilled instanceof NonViralName){
|
201 |
|
|
return anyZooName; //TODO ?
|
202 |
|
|
}else if (nameToBeFilled instanceof BotanicalName) {
|
203 |
|
|
return anyBotanicName;
|
204 |
|
|
}else{
|
205 |
|
|
logger.warn("nameToBeFilled class not supported ("+nameToBeFilled.getClass()+")");
|
206 |
|
|
return null;
|
207 |
|
|
}
|
208 |
|
|
}
|
209 |
|
|
|
210 |
|
|
private Matcher getMatcher(String regEx, String matchString){
|
211 |
|
|
Pattern pattern = Pattern.compile(regEx);
|
212 |
|
|
Matcher matcher = pattern.matcher(matchString);
|
213 |
|
|
return matcher;
|
214 |
|
|
}
|
215 |
|
|
|
216 |
|
|
@Override
|
217 |
|
|
public void parseReferencedName(NonViralName nameToBeFilled, String fullReferenceStringOrig, Rank rank, boolean makeEmpty) {
|
218 |
|
|
//standardize
|
219 |
|
|
String fullReferenceString = standardize(nameToBeFilled, fullReferenceStringOrig, makeEmpty);
|
220 |
|
|
if (fullReferenceString == null){
|
221 |
|
|
return;
|
222 |
|
|
}
|
223 |
|
|
// happens already in standardize(...)
|
224 |
|
|
// makeProblemEmpty(nameToBeFilled);
|
225 |
|
|
|
226 |
|
|
//make nomenclatural status and replace it by empty string
|
227 |
|
|
fullReferenceString = parseNomStatus(fullReferenceString, nameToBeFilled, makeEmpty);
|
228 |
|
|
nameToBeFilled.setProblemEnds(fullReferenceString.length());
|
229 |
|
|
|
230 |
|
|
//get full name reg
|
231 |
|
|
String localFullNameRegEx = getCodeSpecificFullNameRegEx(nameToBeFilled);
|
232 |
|
|
//get full name reg
|
233 |
|
|
String localSimpleNameRegEx = getCodeSpecificSimpleNameRegEx(nameToBeFilled);
|
234 |
|
|
|
235 |
|
|
//separate name and reference part
|
236 |
|
|
String nameAndRefSeparatorRegEx = "(^" + localFullNameRegEx + ")("+ referenceSeperator + ")";
|
237 |
|
|
Matcher nameAndRefSeparatorMatcher = getMatcher (nameAndRefSeparatorRegEx, fullReferenceString);
|
238 |
|
|
|
239 |
|
|
Matcher onlyNameMatcher = getMatcher (localFullNameRegEx, fullReferenceString);
|
240 |
|
|
Matcher hybridMatcher = hybridFormulaPattern.matcher(fullReferenceString);
|
241 |
|
|
Matcher onlySimpleNameMatcher = getMatcher (localSimpleNameRegEx, fullReferenceString);
|
242 |
|
|
|
243 |
|
|
if (onlyNameMatcher.matches()){
|
244 |
|
|
makeEmpty = false;
|
245 |
|
|
parseFullName(nameToBeFilled, fullReferenceString, rank, makeEmpty);
|
246 |
|
|
} else if (nameAndRefSeparatorMatcher.find()){
|
247 |
|
|
makeNameWithReference(nameToBeFilled, fullReferenceString, nameAndRefSeparatorMatcher, rank, makeEmpty);
|
248 |
|
|
}else if (hybridMatcher.matches() ){
|
249 |
|
|
//I do not remember why we need makeEmpty = false for onlyNameMatcher,
|
250 |
|
|
//but for hybridMatcher we need to remove old Hybrid Relationships if necessary, therefore
|
251 |
|
|
//I removed it from here
|
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 = getCodeSpecificFullNameRegEx(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.getBasionymAuthorship() != 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 = 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 |
|
|
Reference<?> nomRef;
|
379 |
|
|
if ( (nomRef = (Reference<?>)nameToBeFilled.getNomenclaturalReference()) != null ){
|
380 |
|
|
nomRef.setAuthorship(nameToBeFilled.getCombinationAuthorship());
|
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 |
|
|
public String parseNomStatus(String fullString, NonViralName<?> nameToBeFilled, boolean makeEmpty) {
|
391 |
|
|
Set<NomenclaturalStatusType> existingStatusTypeSet = new HashSet<NomenclaturalStatusType>();
|
392 |
|
|
Set<NomenclaturalStatusType> newStatusTypeSet = new HashSet<NomenclaturalStatusType>();
|
393 |
|
|
for (NomenclaturalStatus existingStatus : nameToBeFilled.getStatus()){
|
394 |
|
|
existingStatusTypeSet.add(existingStatus.getType());
|
395 |
|
|
}
|
396 |
|
|
|
397 |
|
|
String statusString;
|
398 |
|
|
Pattern hasStatusPattern = Pattern.compile("(" + pNomStatusPhrase + ")");
|
399 |
|
|
Matcher hasStatusMatcher = hasStatusPattern.matcher(fullString);
|
400 |
|
|
|
401 |
|
|
if (hasStatusMatcher.find()) {
|
402 |
|
|
String statusPhrase = hasStatusMatcher.group(0);
|
403 |
|
|
|
404 |
|
|
Pattern statusPattern = Pattern.compile(pNomStatus);
|
405 |
|
|
Matcher statusMatcher = statusPattern.matcher(statusPhrase);
|
406 |
|
|
statusMatcher.find();
|
407 |
|
|
statusString = statusMatcher.group(0);
|
408 |
|
|
try {
|
409 |
|
|
NomenclaturalStatusType nomStatusType = NomenclaturalStatusType.getNomenclaturalStatusTypeByAbbreviation(statusString, nameToBeFilled);
|
410 |
|
|
if (! existingStatusTypeSet.contains(nomStatusType)){
|
411 |
|
|
NomenclaturalStatus nomStatus = NomenclaturalStatus.NewInstance(nomStatusType);
|
412 |
|
|
nameToBeFilled.addStatus(nomStatus);
|
413 |
|
|
}
|
414 |
|
|
newStatusTypeSet.add(nomStatusType);
|
415 |
|
|
fullString = fullString.replace(statusPhrase, "");
|
416 |
|
|
} catch (UnknownCdmTypeException e) {
|
417 |
|
|
//Do nothing
|
418 |
|
|
}
|
419 |
|
|
}
|
420 |
|
|
//remove not existing nom status
|
421 |
|
|
if (makeEmpty){
|
422 |
|
|
Set<NomenclaturalStatus> tmpStatus = new HashSet<NomenclaturalStatus>();
|
423 |
|
|
tmpStatus.addAll(nameToBeFilled.getStatus());
|
424 |
|
|
for (NomenclaturalStatus status : tmpStatus){
|
425 |
|
|
if (! newStatusTypeSet.contains(status.getType())){
|
426 |
|
|
nameToBeFilled.removeStatus(status);
|
427 |
|
|
}
|
428 |
|
|
}
|
429 |
|
|
}
|
430 |
|
|
|
431 |
|
|
return fullString;
|
432 |
|
|
}
|
433 |
|
|
|
434 |
|
|
|
435 |
|
|
private void parseReference(NonViralName<?> nameToBeFilled, String strReference, boolean isInReference){
|
436 |
|
|
|
437 |
|
|
INomenclaturalReference ref;
|
438 |
|
|
String originalStrReference = strReference;
|
439 |
|
|
|
440 |
|
|
//End (just delete end (e.g. '.', may be ambigous for yearPhrase, but no real information gets lost
|
441 |
|
|
Matcher endMatcher = getMatcher(referenceEnd + end, strReference);
|
442 |
|
|
if (endMatcher.find()){
|
443 |
|
|
String endPart = endMatcher.group(0);
|
444 |
|
|
strReference = strReference.substring(0, strReference.length() - endPart.length());
|
445 |
|
|
}
|
446 |
|
|
|
447 |
|
|
// String pDetailYear = ".*" + detailSeparator + detail + fWs + yearSeperator + fWs + yearPhrase + fWs + end;
|
448 |
|
|
// Matcher detailYearMatcher = getMatcher(pDetailYear, strReference);
|
449 |
|
|
|
450 |
|
|
String strReferenceWithYear = strReference;
|
451 |
|
|
//year
|
452 |
|
|
String yearPart = null;
|
453 |
|
|
String pYearPhrase = yearSeperator + fWs + yearPhrase + fWs + end;
|
454 |
|
|
Matcher yearPhraseMatcher = getMatcher(pYearPhrase, strReference);
|
455 |
|
|
if (yearPhraseMatcher.find()){
|
456 |
|
|
yearPart = yearPhraseMatcher.group(0);
|
457 |
|
|
strReference = strReference.substring(0, strReference.length() - yearPart.length());
|
458 |
|
|
yearPart = yearPart.replaceFirst(pStart + yearSeperator, "").trim();
|
459 |
|
|
}else{
|
460 |
|
|
if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
461 |
|
|
ZoologicalName zooName = CdmBase.deproxy(nameToBeFilled, ZoologicalName.class);
|
462 |
|
|
yearPart = String.valueOf(zooName.getPublicationYear());
|
463 |
|
|
//continue
|
464 |
|
|
}else{
|
465 |
|
|
ref = makeDetailYearUnparsable(nameToBeFilled,strReference);
|
466 |
|
|
ref.setDatePublished(TimePeriodParser.parseString(yearPart));
|
467 |
|
|
return;
|
468 |
|
|
}
|
469 |
|
|
}
|
470 |
|
|
|
471 |
|
|
|
472 |
|
|
//detail
|
473 |
|
|
String pDetailPhrase = detailSeparator + fWs + detail + fWs + end;
|
474 |
|
|
Matcher detailPhraseMatcher = getMatcher(pDetailPhrase, strReference);
|
475 |
|
|
if (detailPhraseMatcher.find()){
|
476 |
|
|
String detailPart = detailPhraseMatcher.group(0);
|
477 |
|
|
strReference = strReference.substring(0, strReference.length() - detailPart.length());
|
478 |
|
|
detailPart = detailPart.replaceFirst(pStart + detailSeparator, "").trim();
|
479 |
|
|
nameToBeFilled.setNomenclaturalMicroReference(detailPart);
|
480 |
|
|
}else{
|
481 |
|
|
makeDetailYearUnparsable(nameToBeFilled, strReferenceWithYear);
|
482 |
|
|
return;
|
483 |
|
|
}
|
484 |
|
|
//parse title and author
|
485 |
|
|
ref = parseReferenceTitle(strReference, yearPart, isInReference);
|
486 |
|
|
if (ref.hasProblem()){
|
487 |
|
|
ref.setTitleCache( (isInReference ? "in ":"") + originalStrReference, true);
|
488 |
|
|
ref.setAbbrevTitleCache( (isInReference ? "in ":"") + originalStrReference, true);
|
489 |
|
|
}
|
490 |
|
|
nameToBeFilled.setNomenclaturalReference(ref);
|
491 |
|
|
int end = Math.min(strReference.length(), ref.getProblemEnds());
|
492 |
|
|
ref.setProblemEnds(end);
|
493 |
|
|
}
|
494 |
|
|
|
495 |
|
|
/**
|
496 |
|
|
* @param nameToBeFilled
|
497 |
|
|
* @param strReference
|
498 |
|
|
* @return
|
499 |
|
|
*/
|
500 |
|
|
private INomenclaturalReference makeDetailYearUnparsable(NonViralName<?> nameToBeFilled, String strReference) {
|
501 |
|
|
INomenclaturalReference ref;
|
502 |
|
|
//ref = Generic.NewInstance();
|
503 |
|
|
|
504 |
|
|
ref = ReferenceFactory.newGeneric();
|
505 |
|
|
ref.setTitleCache(strReference,true);
|
506 |
|
|
ref.setProblemEnds(strReference.length());
|
507 |
|
|
ref.addParsingProblem(ParserProblem.CheckDetailOrYear);
|
508 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.CheckDetailOrYear);
|
509 |
|
|
nameToBeFilled.setNomenclaturalReference(ref);
|
510 |
|
|
return ref;
|
511 |
|
|
}
|
512 |
|
|
|
513 |
|
|
/**
|
514 |
|
|
* Parses the referenceTitlePart, including the author volume and edition.
|
515 |
|
|
* @param reference
|
516 |
|
|
* @param year
|
517 |
|
|
* @return
|
518 |
|
|
*/
|
519 |
|
|
private INomenclaturalReference parseReferenceTitle(String strReference, String year, boolean isInReference){
|
520 |
|
|
IBook result = null;
|
521 |
|
|
|
522 |
|
|
Matcher refSineDetailMatcher = referenceSineDetailPattern.matcher(strReference);
|
523 |
|
|
if (! refSineDetailMatcher.matches()){
|
524 |
|
|
//TODO ?
|
525 |
|
|
}
|
526 |
|
|
|
527 |
|
|
Matcher articleMatcher = getMatcher(pArticleReference, strReference);
|
528 |
|
|
Matcher bookMatcher = getMatcher(pBookReference, strReference);
|
529 |
|
|
|
530 |
|
|
Matcher softArticleMatcher = getMatcher(pSoftArticleReference, strReference);
|
531 |
|
|
Matcher bookSectionMatcher = getMatcher(pBookSectionReference, strReference);
|
532 |
|
|
|
533 |
|
|
|
534 |
|
|
if(isInReference == false){
|
535 |
|
|
if (bookMatcher.matches() ){
|
536 |
|
|
result = parseBook(strReference);
|
537 |
|
|
}else{
|
538 |
|
|
logger.warn("Non-InRef must be book but does not match book");
|
539 |
|
|
result = ReferenceFactory.newBook();
|
540 |
|
|
makeUnparsableRefTitle(result, strReference);
|
541 |
|
|
}
|
542 |
|
|
}else{ //inRef
|
543 |
|
|
if (articleMatcher.matches()){
|
544 |
|
|
//article without separators like ","
|
545 |
|
|
result = parseArticle(strReference);
|
546 |
|
|
}else if (softArticleMatcher.matches()){
|
547 |
|
|
result = parseArticle(strReference);
|
548 |
|
|
}else if (bookSectionMatcher.matches()){
|
549 |
|
|
result = parseBookSection(strReference);
|
550 |
|
|
}else{
|
551 |
|
|
result = ReferenceFactory.newGeneric();
|
552 |
|
|
makeUnparsableRefTitle(result, "in " + strReference);
|
553 |
|
|
}
|
554 |
|
|
}
|
555 |
|
|
//make year
|
556 |
|
|
if (makeYear(result, year) == false){
|
557 |
|
|
//TODO
|
558 |
|
|
logger.warn("Year could not be parsed");
|
559 |
|
|
}
|
560 |
|
|
result.setProblemStarts(0);
|
561 |
|
|
result.setProblemEnds(strReference.length());
|
562 |
|
|
return result;
|
563 |
|
|
}
|
564 |
|
|
|
565 |
|
|
private void makeUnparsableRefTitle(INomenclaturalReference result, String reference){
|
566 |
|
|
result.setTitleCache(reference,true);
|
567 |
|
|
result.setAbbrevTitleCache(reference,true);
|
568 |
|
|
result.addParsingProblem(ParserProblem.UnparsableReferenceTitle);
|
569 |
|
|
}
|
570 |
|
|
|
571 |
|
|
/**
|
572 |
|
|
* Parses a single date string. If the string is not parsable a StringNotParsableException is thrown
|
573 |
|
|
* @param singleDateString
|
574 |
|
|
* @return
|
575 |
|
|
* @throws StringNotParsableException
|
576 |
|
|
*/
|
577 |
|
|
private static Partial parseSingleDate(String singleDateString)
|
578 |
|
|
throws StringNotParsableException{
|
579 |
|
|
Partial dt = new Partial();
|
580 |
|
|
if (CdmUtils.isNumeric(singleDateString)){
|
581 |
|
|
try {
|
582 |
|
|
Integer year = Integer.valueOf(singleDateString.trim());
|
583 |
|
|
if (year > 1750 && year < 2050){
|
584 |
|
|
dt = dt.with(DateTimeFieldType.year(), year);
|
585 |
|
|
}else{
|
586 |
|
|
dt = null;
|
587 |
|
|
}
|
588 |
|
|
} catch (NumberFormatException e) {
|
589 |
|
|
logger.debug("Not a Integer format in getCalendar()");
|
590 |
|
|
throw new StringNotParsableException(singleDateString + "is not parsable as a single Date");
|
591 |
|
|
}
|
592 |
|
|
}
|
593 |
|
|
return dt;
|
594 |
|
|
}
|
595 |
|
|
|
596 |
|
|
|
597 |
|
|
/**
|
598 |
|
|
* Parses the publication date part.
|
599 |
|
|
* @param nomRef
|
600 |
|
|
* @param year
|
601 |
|
|
* @return If the string is not parsable <code>false</code>
|
602 |
|
|
* is returned. <code>True</code> otherwise
|
603 |
|
|
*/
|
604 |
|
|
private boolean makeYear(INomenclaturalReference nomRef, String year){
|
605 |
|
|
boolean result = true;
|
606 |
|
|
if (year == null){
|
607 |
|
|
return false;
|
608 |
|
|
}
|
609 |
|
|
if ("".equals(year.trim())){
|
610 |
|
|
return true;
|
611 |
|
|
}
|
612 |
|
|
TimePeriod datePublished = TimePeriodParser.parseString(year);
|
613 |
|
|
|
614 |
|
|
if (nomRef.getType().equals(ReferenceType.BookSection)){
|
615 |
|
|
handleBookSectionYear((IBookSection)nomRef, datePublished);
|
616 |
|
|
}else if (nomRef instanceof Reference){
|
617 |
|
|
((Reference)nomRef).setDatePublished(datePublished);
|
618 |
|
|
}else{
|
619 |
|
|
throw new ClassCastException("nom Ref is not of type Reference but " + (nomRef == null? "(null)" : nomRef.getClass()));
|
620 |
|
|
}
|
621 |
|
|
return result;
|
622 |
|
|
}
|
623 |
|
|
|
624 |
|
|
private String makeVolume(IVolumeReference nomRef, String strReference){
|
625 |
|
|
//volume
|
626 |
|
|
String volPart = null;
|
627 |
|
|
String pVolPhrase = volumeSeparator + volume + end;
|
628 |
|
|
Matcher volPhraseMatcher = getMatcher(pVolPhrase, strReference);
|
629 |
|
|
if (volPhraseMatcher.find()){
|
630 |
|
|
volPart = volPhraseMatcher.group(0);
|
631 |
|
|
strReference = strReference.substring(0, strReference.length() - volPart.length());
|
632 |
|
|
volPart = volPart.replaceFirst(pStart + volumeSeparator, "").trim();
|
633 |
|
|
nomRef.setVolume(volPart);
|
634 |
|
|
}
|
635 |
|
|
return strReference;
|
636 |
|
|
}
|
637 |
|
|
|
638 |
|
|
private String makeEdition(IBook book, String strReference){
|
639 |
|
|
//volume
|
640 |
|
|
String editionPart = null;
|
641 |
|
|
Matcher editionPhraseMatcher = getMatcher(pEditionPart, strReference);
|
642 |
|
|
|
643 |
|
|
Matcher editionVolumeMatcher = getMatcher(pEditionVolPart, strReference);
|
644 |
|
|
boolean isEditionAndVol = editionVolumeMatcher.find();
|
645 |
|
|
|
646 |
|
|
if (editionPhraseMatcher.find()){
|
647 |
|
|
editionPart = editionPhraseMatcher.group(0);
|
648 |
|
|
int pos = strReference.indexOf(editionPart);
|
649 |
|
|
int posEnd = pos + editionPart.length();
|
650 |
|
|
if (isEditionAndVol){
|
651 |
|
|
posEnd++; //delete also comma
|
652 |
|
|
}
|
653 |
|
|
strReference = strReference.substring(0, pos) + strReference.substring(posEnd);
|
654 |
|
|
editionPart = editionPart.replaceFirst(pStart + editionSeparator, "").trim();
|
655 |
|
|
book.setEdition(editionPart);
|
656 |
|
|
}
|
657 |
|
|
return strReference;
|
658 |
|
|
}
|
659 |
|
|
|
660 |
|
|
private IBook parseBook(String reference){
|
661 |
|
|
IBook result = ReferenceFactory.newBook();
|
662 |
|
|
reference = makeEdition(result, reference);
|
663 |
|
|
reference = makeVolume(result, reference);
|
664 |
|
|
result.setTitle(reference);
|
665 |
|
|
return result;
|
666 |
|
|
}
|
667 |
|
|
|
668 |
|
|
|
669 |
|
|
private Reference<?> parseArticle(String reference){
|
670 |
|
|
//if (articlePatter)
|
671 |
|
|
//(type, author, title, volume, editor, series;
|
672 |
|
|
Reference<?> result = ReferenceFactory.newArticle();
|
673 |
|
|
reference = makeVolume(result, reference);
|
674 |
|
|
Reference<?> inJournal = ReferenceFactory.newJournal();
|
675 |
|
|
inJournal.setTitle(reference);
|
676 |
|
|
result.setInReference(inJournal);
|
677 |
|
|
return result;
|
678 |
|
|
}
|
679 |
|
|
|
680 |
|
|
private Reference<?> parseBookSection(String reference){
|
681 |
|
|
Reference<?> result = ReferenceFactory.newBookSection();
|
682 |
c16ec678
|
Andreas Müller
|
|
683 |
ce7c7aa3
|
Andreas Müller
|
Pattern authorPattern = Pattern.compile("^" + authorTeam + referenceAuthorSeparator);
|
684 |
|
|
Matcher authorMatcher = authorPattern.matcher(reference);
|
685 |
|
|
boolean find = authorMatcher.find();
|
686 |
|
|
if (find){
|
687 |
|
|
String authorString = authorMatcher.group(0).trim();
|
688 |
|
|
String bookString = reference.substring(authorString.length()).trim();
|
689 |
|
|
authorString = authorString.substring(0, authorString.length() -1);
|
690 |
c16ec678
|
Andreas Müller
|
|
691 |
ce7c7aa3
|
Andreas Müller
|
TeamOrPersonBase<?> authorTeam = author(authorString);
|
692 |
|
|
IBook inBook = parseBook(bookString);
|
693 |
|
|
inBook.setAuthorship(authorTeam);
|
694 |
|
|
result.setInBook(inBook);
|
695 |
|
|
}else{
|
696 |
|
|
logger.warn("Unexpected non matching book section author part");
|
697 |
|
|
//TODO do we want to record a 'problem' here?
|
698 |
|
|
result.setTitleCache(reference,true);
|
699 |
|
|
}
|
700 |
|
|
|
701 |
|
|
return result;
|
702 |
|
|
}
|
703 |
|
|
|
704 |
|
|
/**
|
705 |
|
|
* If the publication date of a book section and it's inBook do differ this is usually
|
706 |
|
|
* caused by the fact that a book has been published during a period, because originally
|
707 |
|
|
* it consisted of several parts that only later where put together to one book.
|
708 |
|
|
* If so, the book section's publication date may be a point in time (year or month of year)
|
709 |
|
|
* whereas the books publication date may be a period of several years.
|
710 |
|
|
* Therefore a valid nomenclatural reference string should use the book sections
|
711 |
|
|
* publication date rather then the book's publication date.<BR>
|
712 |
|
|
* This method in general adds the publication date to the book section.
|
713 |
|
|
* An exception exists if the publication date is a period. Then the parser
|
714 |
|
|
* assumes that the nomenclatural reference string does not follow the above rule but
|
715 |
|
|
* the books publication date is set.
|
716 |
|
|
* @param bookSection
|
717 |
|
|
* @param datePublished
|
718 |
|
|
*/
|
719 |
|
|
private void handleBookSectionYear(IBookSection bookSection, TimePeriod datePublished){
|
720 |
|
|
if (datePublished == null || datePublished.getStart() == null || bookSection == null){
|
721 |
|
|
return;
|
722 |
|
|
}
|
723 |
|
|
if (datePublished.isPeriod() && bookSection.getInBook() != null){
|
724 |
|
|
bookSection.getInBook().setDatePublished(datePublished);
|
725 |
|
|
}else{
|
726 |
|
|
bookSection.setDatePublished(datePublished);
|
727 |
|
|
}
|
728 |
|
|
}
|
729 |
|
|
|
730 |
|
|
@Override
|
731 |
|
|
public NonViralName parseFullName(String fullNameString){
|
732 |
|
|
return parseFullName(fullNameString, null, null);
|
733 |
|
|
}
|
734 |
|
|
|
735 |
|
|
@Override
|
736 |
|
|
public NonViralName parseFullName(String fullNameString, NomenclaturalCode nomCode, Rank rank) {
|
737 |
|
|
|
738 |
|
|
if (fullNameString == null){
|
739 |
|
|
return null;
|
740 |
|
|
}else{
|
741 |
|
|
NonViralName<?> result = getNonViralNameInstance(fullNameString, nomCode, rank);
|
742 |
|
|
parseFullName(result, fullNameString, rank, false);
|
743 |
|
|
return result;
|
744 |
|
|
}
|
745 |
|
|
}
|
746 |
|
|
|
747 |
|
|
@Override
|
748 |
|
|
public void parseFullName(NonViralName nameToBeFilledOrig, String fullNameStringOrig, Rank rank, boolean makeEmpty) {
|
749 |
|
|
NonViralName<?> nameToBeFilled = nameToBeFilledOrig;
|
750 |
|
|
|
751 |
|
|
//TODO prol. etc.
|
752 |
|
|
boolean hasCheckRankProblem = false; //was rank guessed in a previous parsing process?
|
753 |
|
|
if (nameToBeFilled == null){
|
754 |
|
|
throw new IllegalArgumentException("NameToBeFilled must not be null in name parser");
|
755 |
|
|
}else{
|
756 |
|
|
hasCheckRankProblem = nameToBeFilled.hasProblem(ParserProblem.CheckRank);
|
757 |
|
|
nameToBeFilled.removeParsingProblem(ParserProblem.CheckRank);
|
758 |
|
|
}
|
759 |
|
|
String authorString = null;
|
760 |
|
|
if (fullNameStringOrig == null){
|
761 |
|
|
return;
|
762 |
|
|
}
|
763 |
|
|
if (makeEmpty){
|
764 |
|
|
makeEmpty(nameToBeFilled);
|
765 |
|
|
}
|
766 |
|
|
|
767 |
|
|
String fullNameString = fullNameStringOrig.replaceAll(oWs , " ").trim();
|
768 |
|
|
|
769 |
|
|
fullNameString = removeHybridBlanks(fullNameString);
|
770 |
|
|
String[] epi = pattern.split(fullNameString);
|
771 |
|
|
try {
|
772 |
|
|
//cultivars //TODO 2 implement cultivars
|
773 |
|
|
// if ( cultivarMarkerRE.match(fullName) ){ funktioniert noch nicht, da es z.B. auch Namen gibt, wie 't Hart
|
774 |
|
|
// result = parseCultivar(fullName);
|
775 |
|
|
// }
|
776 |
|
|
|
777 |
|
|
if (genusOrSupraGenusPattern.matcher(fullNameString).matches()){
|
778 |
|
|
//supraGeneric
|
779 |
|
|
if (rank != null && ! hasCheckRankProblem && (rank.isSupraGeneric()|| rank.isGenus())){
|
780 |
|
|
nameToBeFilled.setRank(rank);
|
781 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
782 |
|
|
}
|
783 |
|
|
//genus or guess rank
|
784 |
|
|
else {
|
785 |
|
|
rank = guessUninomialRank(nameToBeFilled, epi[0]);
|
786 |
|
|
nameToBeFilled.setRank(rank);
|
787 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
788 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.CheckRank);
|
789 |
|
|
nameToBeFilled.setProblemStarts(0);
|
790 |
|
|
nameToBeFilled.setProblemEnds(epi[0].length());
|
791 |
|
|
}
|
792 |
|
|
authorString = fullNameString.substring(epi[0].length());
|
793 |
|
|
}
|
794 |
|
|
//infra genus
|
795 |
|
|
else if (infraGenusPattern.matcher(fullNameString).matches()){
|
796 |
|
|
Rank infraGenericRank;
|
797 |
c16ec678
|
Andreas Müller
|
|
798 |
|
|
|
799 |
ce7c7aa3
|
Andreas Müller
|
if ("[unranked]".equals(epi[1])){
|
800 |
|
|
infraGenericRank = Rank.INFRAGENERICTAXON();
|
801 |
|
|
}else{
|
802 |
c16ec678
|
Andreas Müller
|
infraGenericRank = Rank.getRankByIdInVoc(epi[1], nameToBeFilledOrig.getNomenclaturalCode());
|
803 |
ce7c7aa3
|
Andreas Müller
|
}
|
804 |
|
|
nameToBeFilled.setRank(infraGenericRank);
|
805 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
806 |
|
|
nameToBeFilled.setInfraGenericEpithet(epi[2]);
|
807 |
|
|
authorString = fullNameString.substring(epi[0].length() + 1 + epi[1].length()+ 1 + epi[2].length());
|
808 |
|
|
}
|
809 |
|
|
//aggr. or group
|
810 |
|
|
else if (aggrOrGroupPattern.matcher(fullNameString).matches()){
|
811 |
|
|
nameToBeFilled.setRank(Rank.getRankByIdInVoc(epi[2]));
|
812 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
813 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
814 |
|
|
}
|
815 |
|
|
//species
|
816 |
|
|
else if (speciesPattern.matcher(fullNameString).matches()){
|
817 |
|
|
nameToBeFilled.setRank(Rank.SPECIES());
|
818 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
819 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
820 |
|
|
authorString = fullNameString.substring(epi[0].length() + 1 + epi[1].length());
|
821 |
|
|
}
|
822 |
|
|
//autonym
|
823 |
|
|
else if (autonymPattern.matcher(fullNameString).matches()){
|
824 |
|
|
nameToBeFilled.setRank(Rank.getRankByIdInVoc(epi[epi.length - 2]));
|
825 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
826 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
827 |
|
|
nameToBeFilled.setInfraSpecificEpithet(epi[epi.length - 1]);
|
828 |
|
|
int lenSpecies = 2 + epi[0].length()+epi[1].length();
|
829 |
|
|
int lenInfraSpecies = 2 + epi[epi.length - 2].length() + epi[epi.length - 1].length();
|
830 |
|
|
authorString = fullNameString.substring(lenSpecies, fullNameString.length() - lenInfraSpecies);
|
831 |
|
|
}
|
832 |
|
|
//infraSpecies
|
833 |
|
|
else if (infraSpeciesPattern.matcher(fullNameString).matches()){
|
834 |
|
|
String infraSpecRankMarker = epi[2];
|
835 |
|
|
String infraSpecEpi = epi[3];
|
836 |
|
|
if ("tax.".equals(infraSpecRankMarker)){
|
837 |
|
|
infraSpecRankMarker += " " + epi[3];
|
838 |
|
|
infraSpecEpi = epi[4];
|
839 |
|
|
}
|
840 |
|
|
Rank infraSpecificRank;
|
841 |
|
|
if ("[unranked]".equals(infraSpecRankMarker)){
|
842 |
|
|
infraSpecificRank = Rank.INFRASPECIFICTAXON();
|
843 |
|
|
}else{
|
844 |
|
|
infraSpecificRank = Rank.getRankByIdInVoc(infraSpecRankMarker);
|
845 |
|
|
}
|
846 |
|
|
nameToBeFilled.setRank(infraSpecificRank);
|
847 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
848 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
849 |
|
|
nameToBeFilled.setInfraSpecificEpithet(infraSpecEpi);
|
850 |
|
|
authorString = fullNameString.substring(epi[0].length()+ 1 + epi[1].length() +1 + infraSpecRankMarker.length() + 1 + infraSpecEpi.length());
|
851 |
|
|
|
852 |
|
|
}
|
853 |
|
|
//infraSpecies without marker
|
854 |
|
|
else if (zooInfraSpeciesPattern.matcher(fullNameString).matches()){
|
855 |
|
|
String infraSpecEpi = epi[2];
|
856 |
|
|
Rank infraSpecificRank = Rank.SUBSPECIES();
|
857 |
|
|
nameToBeFilled.setRank(infraSpecificRank);
|
858 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
859 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
860 |
|
|
nameToBeFilled.setInfraSpecificEpithet(infraSpecEpi);
|
861 |
|
|
authorString = fullNameString.substring(epi[0].length()+ 1 + epi[1].length() +1 + infraSpecEpi.length());
|
862 |
|
|
|
863 |
|
|
}//old infraSpecies
|
864 |
|
|
else if (oldInfraSpeciesPattern.matcher(fullNameString).matches()){
|
865 |
|
|
boolean implemented = false;
|
866 |
|
|
if (implemented){
|
867 |
|
|
nameToBeFilled.setRank(Rank.getRankByNameOrIdInVoc(epi[2]));
|
868 |
|
|
nameToBeFilled.setGenusOrUninomial(epi[0]);
|
869 |
|
|
nameToBeFilled.setSpecificEpithet(epi[1]);
|
870 |
|
|
//TODO result.setUnnamedNamePhrase(epi[2] + " " + epi[3]);
|
871 |
|
|
authorString = fullNameString.substring(epi[0].length()+ 1 + epi[1].length() +1 + epi[2].length() + 1 + epi[3].length());
|
872 |
|
|
}else{
|
873 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.OldInfraSpeciesNotSupported);
|
874 |
|
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
875 |
|
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
876 |
|
|
nameToBeFilled.setNameCache(fullNameString,true);
|
877 |
|
|
// END
|
878 |
|
|
logger.info("Name string " + fullNameString + " could not be parsed because UnnnamedNamePhrase is not yet implemented!");
|
879 |
|
|
}
|
880 |
|
|
}
|
881 |
|
|
//hybrid formula
|
882 |
|
|
else if (hybridFormulaPattern.matcher(fullNameString).matches()){
|
883 |
|
|
Set<HybridRelationship> existingRelations = new HashSet<HybridRelationship>();
|
884 |
|
|
Set<HybridRelationship> notToBeDeleted = new HashSet<HybridRelationship>();
|
885 |
|
|
|
886 |
|
|
for ( HybridRelationship rel : nameToBeFilled.getHybridChildRelations()){
|
887 |
|
|
existingRelations.add(rel);
|
888 |
|
|
}
|
889 |
|
|
|
890 |
|
|
String firstNameString = "";
|
891 |
|
|
String secondNameString = "";
|
892 |
|
|
boolean isFirstName = true;
|
893 |
|
|
for (String str : epi){
|
894 |
|
|
if (str.matches(hybridSign)){
|
895 |
|
|
isFirstName = false;
|
896 |
|
|
}else if(isFirstName){
|
897 |
|
|
firstNameString += " " + str;
|
898 |
|
|
}else {
|
899 |
|
|
secondNameString += " " + str;
|
900 |
|
|
}
|
901 |
|
|
}
|
902 |
|
|
nameToBeFilled.setHybridFormula(true);
|
903 |
|
|
NomenclaturalCode code = nameToBeFilled.getNomenclaturalCode();
|
904 |
|
|
NonViralName<?> firstName = this.parseFullName(firstNameString.trim(), code, rank);
|
905 |
|
|
NonViralName<?> secondName = this.parseFullName(secondNameString.trim(), code, rank);
|
906 |
|
|
HybridRelationship firstRel = nameToBeFilled.addHybridParent(firstName, HybridRelationshipType.FIRST_PARENT(), null);
|
907 |
|
|
HybridRelationship second = nameToBeFilled.addHybridParent(secondName, HybridRelationshipType.SECOND_PARENT(), null);
|
908 |
|
|
checkRelationExist(firstRel, existingRelations, notToBeDeleted);
|
909 |
|
|
checkRelationExist(second, existingRelations, notToBeDeleted);
|
910 |
|
|
|
911 |
|
|
Rank newRank;
|
912 |
|
|
Rank firstRank = firstName.getRank();
|
913 |
|
|
Rank secondRank = secondName.getRank();
|
914 |
|
|
|
915 |
|
|
if (firstRank == null || firstRank.isHigher(secondRank)){
|
916 |
|
|
newRank = secondRank;
|
917 |
|
|
}else{
|
918 |
|
|
newRank = firstRank;
|
919 |
|
|
}
|
920 |
|
|
nameToBeFilled.setRank(newRank);
|
921 |
|
|
//remove not existing hybrid relation
|
922 |
|
|
if (makeEmpty){
|
923 |
|
|
Set<HybridRelationship> tmpChildRels = new HashSet<HybridRelationship>();
|
924 |
|
|
tmpChildRels.addAll(nameToBeFilled.getHybridChildRelations());
|
925 |
|
|
for (HybridRelationship rel : tmpChildRels){
|
926 |
|
|
if (! notToBeDeleted.contains(rel)){
|
927 |
|
|
nameToBeFilled.removeHybridRelationship(rel);
|
928 |
|
|
}
|
929 |
|
|
}
|
930 |
|
|
}
|
931 |
|
|
}
|
932 |
|
|
//none
|
933 |
|
|
else{
|
934 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.UnparsableNamePart);
|
935 |
|
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
936 |
|
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
937 |
|
|
nameToBeFilled.setNameCache(fullNameString,true);
|
938 |
|
|
// END
|
939 |
|
|
logger.info("no applicable parsing rule could be found for \"" + fullNameString + "\"");
|
940 |
|
|
}
|
941 |
|
|
//hybrid bits
|
942 |
|
|
handleHybridBits(nameToBeFilled);
|
943 |
|
|
if (!nameToBeFilled.isHybridFormula()){
|
944 |
|
|
Set<HybridRelationship> hybridChildRelations = new HashSet<HybridRelationship>();
|
945 |
|
|
hybridChildRelations.addAll(nameToBeFilled.getHybridChildRelations());
|
946 |
c16ec678
|
Andreas Müller
|
|
947 |
ce7c7aa3
|
Andreas Müller
|
for (HybridRelationship hybridRelationship: hybridChildRelations){
|
948 |
|
|
nameToBeFilled.removeHybridRelationship(hybridRelationship);
|
949 |
|
|
}
|
950 |
|
|
}
|
951 |
|
|
|
952 |
|
|
//authors
|
953 |
|
|
if (StringUtils.isNotBlank(authorString) ){
|
954 |
|
|
handleAuthors(nameToBeFilled, fullNameString, authorString);
|
955 |
|
|
}
|
956 |
|
|
return;
|
957 |
|
|
} catch (UnknownCdmTypeException e) {
|
958 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.RankNotSupported);
|
959 |
|
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
960 |
|
|
// FIXME Quick fix, otherwise search would not deilver results for unparsable names
|
961 |
|
|
nameToBeFilled.setNameCache(fullNameString,true);
|
962 |
|
|
// END
|
963 |
|
|
logger.info("unknown rank (" + (rank == null? "null":rank) + ") or abbreviation in string " + fullNameString);
|
964 |
|
|
//return result;
|
965 |
|
|
return;
|
966 |
|
|
}
|
967 |
|
|
}
|
968 |
|
|
|
969 |
|
|
/**
|
970 |
|
|
* Checks if a hybrid relation exists in the Set of existing relations
|
971 |
|
|
* and <BR>
|
972 |
|
|
* if it does not adds it to relations not to be deleted <BR>
|
973 |
|
|
* if it does adds the existing relations to the relations not to be deleted
|
974 |
|
|
*
|
975 |
|
|
* @param firstRel
|
976 |
|
|
* @param existingRelations
|
977 |
|
|
* @param notToBeDeleted
|
978 |
|
|
*/
|
979 |
|
|
private void checkRelationExist(
|
980 |
|
|
HybridRelationship newRelation,
|
981 |
|
|
Set<HybridRelationship> existingRelations,
|
982 |
|
|
Set<HybridRelationship> notToBeDeleted) {
|
983 |
|
|
HybridRelationship relToKeep = newRelation;
|
984 |
|
|
for (HybridRelationship existingRelation : existingRelations){
|
985 |
|
|
if (existingRelation.equals(newRelation)){
|
986 |
|
|
relToKeep = existingRelation;
|
987 |
|
|
break;
|
988 |
|
|
}
|
989 |
|
|
}
|
990 |
|
|
notToBeDeleted.add(relToKeep);
|
991 |
|
|
}
|
992 |
|
|
|
993 |
|
|
private void handleHybridBits(NonViralName<?> nameToBeFilled) {
|
994 |
|
|
//uninomial
|
995 |
|
|
String uninomial = CdmUtils.Nz(nameToBeFilled.getGenusOrUninomial());
|
996 |
|
|
boolean isUninomialHybrid = uninomial.startsWith(hybridSign);
|
997 |
|
|
if (isUninomialHybrid){
|
998 |
|
|
nameToBeFilled.setMonomHybrid(true);
|
999 |
|
|
nameToBeFilled.setGenusOrUninomial(uninomial.replace(hybridSign, ""));
|
1000 |
|
|
}
|
1001 |
|
|
//infrageneric
|
1002 |
|
|
String infrageneric = CdmUtils.Nz(nameToBeFilled.getInfraGenericEpithet());
|
1003 |
|
|
boolean isInfraGenericHybrid = infrageneric.startsWith(hybridSign);
|
1004 |
|
|
if (isInfraGenericHybrid){
|
1005 |
|
|
nameToBeFilled.setBinomHybrid(true);
|
1006 |
|
|
nameToBeFilled.setInfraGenericEpithet(infrageneric.replace(hybridSign, ""));
|
1007 |
|
|
}
|
1008 |
|
|
//species Epi
|
1009 |
|
|
String speciesEpi = CdmUtils.Nz(nameToBeFilled.getSpecificEpithet());
|
1010 |
|
|
boolean isSpeciesHybrid = speciesEpi.startsWith(hybridSign);
|
1011 |
|
|
if (isSpeciesHybrid){
|
1012 |
|
|
if (StringUtils.isBlank(infrageneric)){
|
1013 |
|
|
nameToBeFilled.setBinomHybrid(true);
|
1014 |
|
|
}else{
|
1015 |
|
|
nameToBeFilled.setTrinomHybrid(true);
|
1016 |
|
|
}
|
1017 |
|
|
nameToBeFilled.setSpecificEpithet(speciesEpi.replace(hybridSign, ""));
|
1018 |
|
|
}
|
1019 |
|
|
//infra species
|
1020 |
|
|
String infraSpeciesEpi = CdmUtils.Nz(nameToBeFilled.getInfraSpecificEpithet());
|
1021 |
|
|
boolean isInfraSpeciesHybrid = infraSpeciesEpi.startsWith(hybridSign);
|
1022 |
|
|
if (isInfraSpeciesHybrid){
|
1023 |
|
|
nameToBeFilled.setTrinomHybrid(true);
|
1024 |
|
|
nameToBeFilled.setInfraSpecificEpithet(infraSpeciesEpi.replace(hybridSign, ""));
|
1025 |
|
|
}
|
1026 |
|
|
|
1027 |
|
|
}
|
1028 |
|
|
|
1029 |
|
|
private String removeHybridBlanks(String fullNameString) {
|
1030 |
|
|
String result = fullNameString
|
1031 |
|
|
.replaceAll(oWs + "[xX]" + oWs + "(?=[A-Z])", " " + hybridSign + " ")
|
1032 |
|
|
.replaceAll(hybridFull, " "+hybridSign).trim();
|
1033 |
|
|
return result;
|
1034 |
|
|
}
|
1035 |
|
|
|
1036 |
|
|
/**
|
1037 |
|
|
* Author parser for external use
|
1038 |
|
|
* @param nonViralName
|
1039 |
|
|
* @param authorString
|
1040 |
|
|
* @throws StringNotParsableException
|
1041 |
|
|
*/
|
1042 |
|
|
@Override
|
1043 |
|
|
public void parseAuthors(NonViralName nonViralNameOrig, String authorString) throws StringNotParsableException{
|
1044 |
|
|
NonViralName<?> nonViralName = nonViralNameOrig;
|
1045 |
|
|
TeamOrPersonBase<?>[] authors = new TeamOrPersonBase[4];
|
1046 |
|
|
Integer[] years = new Integer[4];
|
1047 |
|
|
Class<? extends NonViralName> clazz = nonViralName.getClass();
|
1048 |
|
|
fullAuthors(authorString, authors, years, clazz);
|
1049 |
|
|
nonViralName.setCombinationAuthorship(authors[0]);
|
1050 |
|
|
nonViralName.setExCombinationAuthorship(authors[1]);
|
1051 |
|
|
nonViralName.setBasionymAuthorship(authors[2]);
|
1052 |
|
|
nonViralName.setExBasionymAuthorship(authors[3]);
|
1053 |
|
|
if (nonViralName instanceof ZoologicalName){
|
1054 |
|
|
ZoologicalName zooName = CdmBase.deproxy(nonViralName, ZoologicalName.class);
|
1055 |
|
|
zooName.setPublicationYear(years[0]);
|
1056 |
|
|
zooName.setOriginalPublicationYear(years[2]);
|
1057 |
|
|
}
|
1058 |
|
|
}
|
1059 |
|
|
|
1060 |
|
|
/**
|
1061 |
|
|
* @param nameToBeFilled
|
1062 |
|
|
* @param fullNameString
|
1063 |
|
|
* @param authorString
|
1064 |
|
|
*/
|
1065 |
|
|
public void handleAuthors(NonViralName nameToBeFilledOrig, String fullNameString, String authorString) {
|
1066 |
|
|
NonViralName<?> nameToBeFilled = nameToBeFilledOrig;
|
1067 |
|
|
TeamOrPersonBase<?>[] authors = new TeamOrPersonBase[4];
|
1068 |
|
|
Integer[] years = new Integer[4];
|
1069 |
|
|
try {
|
1070 |
|
|
Class<? extends NonViralName> clazz = nameToBeFilled.getClass();
|
1071 |
|
|
fullAuthors(authorString, authors, years, clazz);
|
1072 |
|
|
} catch (StringNotParsableException e) {
|
1073 |
|
|
nameToBeFilled.addParsingProblem(ParserProblem.UnparsableAuthorPart);
|
1074 |
|
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
1075 |
|
|
// FIXME Quick fix, otherwise search would not deliver results for unparsable names
|
1076 |
|
|
nameToBeFilled.setNameCache(fullNameString,true);
|
1077 |
|
|
// END
|
1078 |
|
|
logger.info("no applicable parsing rule could be found for \"" + fullNameString + "\"");;
|
1079 |
|
|
}
|
1080 |
|
|
nameToBeFilled.setCombinationAuthorship(authors[0]);
|
1081 |
|
|
nameToBeFilled.setExCombinationAuthorship(authors[1]);
|
1082 |
|
|
nameToBeFilled.setBasionymAuthorship(authors[2]);
|
1083 |
|
|
nameToBeFilled.setExBasionymAuthorship(authors[3]);
|
1084 |
|
|
if (nameToBeFilled instanceof ZoologicalName){
|
1085 |
|
|
ZoologicalName zooName = (ZoologicalName)nameToBeFilled;
|
1086 |
|
|
zooName.setPublicationYear(years[0]);
|
1087 |
|
|
zooName.setOriginalPublicationYear(years[2]);
|
1088 |
|
|
}
|
1089 |
|
|
}
|
1090 |
|
|
|
1091 |
|
|
/**
|
1092 |
|
|
* Guesses the rank of uninomial depending on the typical endings for ranks
|
1093 |
|
|
* @param nameToBeFilled
|
1094 |
|
|
* @param string
|
1095 |
|
|
*/
|
1096 |
|
|
private Rank guessUninomialRank(NonViralName nameToBeFilled, String uninomial) {
|
1097 |
|
|
Rank result = Rank.GENUS();
|
1098 |
|
|
if (nameToBeFilled.isInstanceOf(BotanicalName.class)){
|
1099 |
|
|
if (false){
|
1100 |
|
|
//
|
1101 |
|
|
}else if (uninomial.endsWith("phyta") || uninomial.endsWith("mycota") ){ //plants, fungi
|
1102 |
|
|
result = Rank.SECTION_BOTANY();
|
1103 |
|
|
}else if (uninomial.endsWith("bionta")){
|
1104 |
|
|
result = Rank.SUBKINGDOM(); //TODO
|
1105 |
|
|
}else if (uninomial.endsWith("phytina")|| uninomial.endsWith("mycotina") ){ //plants, fungi
|
1106 |
|
|
result = Rank.SUBSECTION_BOTANY();
|
1107 |
|
|
}else if (uninomial.endsWith("opsida") || uninomial.endsWith("phyceae") || uninomial.endsWith("mycetes")){ //plants, algae, fungi
|
1108 |
|
|
result = Rank.CLASS();
|
1109 |
|
|
}else if (uninomial.endsWith("idae") || uninomial.endsWith("phycidae") || uninomial.endsWith("mycetidae")){ //plants, algae, fungi
|
1110 |
|
|
result = Rank.SUBCLASS();
|
1111 |
|
|
}else if (uninomial.endsWith("ales")){
|
1112 |
|
|
result = Rank.ORDER();
|
1113 |
|
|
}else if (uninomial.endsWith("ineae")){
|
1114 |
|
|
result = Rank.SUBORDER();
|
1115 |
|
|
}else if (uninomial.endsWith("aceae")){
|
1116 |
|
|
result = Rank.FAMILY();
|
1117 |
|
|
}else if (uninomial.endsWith("oideae")){
|
1118 |
|
|
result = Rank.SUBFAMILY();
|
1119 |
|
|
}else if (uninomial.endsWith("eae")){
|
1120 |
|
|
result = Rank.TRIBE();
|
1121 |
|
|
}else if (uninomial.endsWith("inae")){
|
1122 |
|
|
result = Rank.SUBTRIBE();
|
1123 |
|
|
}else if (uninomial.endsWith("ota")){
|
1124 |
|
|
result = Rank.KINGDOM(); //TODO
|
1125 |
|
|
}
|
1126 |
|
|
}else if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
1127 |
|
|
if (false){
|
1128 |
|
|
//
|
1129 |
|
|
}else if (uninomial.endsWith("oideae")){
|
1130 |
|
|
result = Rank.SUPERFAMILY();
|
1131 |
|
|
}else if (uninomial.endsWith("idae")){
|
1132 |
|
|
result = Rank.FAMILY();
|
1133 |
|
|
}else if (uninomial.endsWith("inae")){
|
1134 |
|
|
result = Rank.SUBFAMILY();
|
1135 |
|
|
}else if (uninomial.endsWith("inae")){
|
1136 |
|
|
result = Rank.SUBFAMILY();
|
1137 |
|
|
}else if (uninomial.endsWith("ini")){
|
1138 |
|
|
result = Rank.TRIBE();
|
1139 |
|
|
}else if (uninomial.endsWith("ina")){
|
1140 |
|
|
result = Rank.SUBTRIBE();
|
1141 |
|
|
}
|
1142 |
|
|
}else{
|
1143 |
|
|
//
|
1144 |
|
|
}
|
1145 |
|
|
return result;
|
1146 |
|
|
}
|
1147 |
|
|
|
1148 |
|
|
/**
|
1149 |
|
|
* Parses the fullAuthorString
|
1150 |
|
|
* @param fullAuthorString
|
1151 |
|
|
* @return array of Teams containing the Team[0],
|
1152 |
|
|
* ExTeam[1], BasionymTeam[2], ExBasionymTeam[3]
|
1153 |
|
|
*/
|
1154 |
|
|
protected void fullAuthors (String fullAuthorString, TeamOrPersonBase<?>[] authors, Integer[] years, Class<? extends NonViralName> clazz)
|
1155 |
|
|
throws StringNotParsableException{
|
1156 |
|
|
if (fullAuthorString == null || clazz == null){
|
1157 |
|
|
return;
|
1158 |
|
|
}
|
1159 |
|
|
fullAuthorString = fullAuthorString.trim();
|
1160 |
|
|
|
1161 |
|
|
//Botanic
|
1162 |
|
|
if ( BotanicalName.class.isAssignableFrom(clazz) ){
|
1163 |
|
|
if (! fullBotanicAuthorStringPattern.matcher(fullAuthorString).matches() ){
|
1164 |
|
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
1165 |
|
|
}
|
1166 |
|
|
}
|
1167 |
|
|
//Zoo
|
1168 |
|
|
else if ( ZoologicalName.class.isAssignableFrom(clazz) ){
|
1169 |
|
|
if (! fullZooAuthorStringPattern.matcher(fullAuthorString).matches() ){
|
1170 |
|
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
1171 |
|
|
}
|
1172 |
|
|
}else {
|
1173 |
|
|
//TODO
|
1174 |
|
|
logger.warn ("Full author String parsable only for defined BotanicalNames or ZoologicalNames but this is " + clazz.getSimpleName());
|
1175 |
|
|
throw new StringNotParsableException("fullAuthorString (" +fullAuthorString+") not parsable: ");
|
1176 |
|
|
}
|
1177 |
|
|
fullAuthorsChecked(fullAuthorString, authors, years);
|
1178 |
|
|
}
|
1179 |
|
|
|
1180 |
|
|
/*
|
1181 |
|
|
* like fullTeams but without trim and match check
|
1182 |
|
|
*/
|
1183 |
|
|
protected void fullAuthorsChecked (String fullAuthorString, TeamOrPersonBase<?>[] authors, Integer[] years){
|
1184 |
|
|
int authorShipStart = 0;
|
1185 |
|
|
Matcher basionymMatcher = basionymPattern.matcher(fullAuthorString);
|
1186 |
|
|
|
1187 |
|
|
if (basionymMatcher.find(0)){
|
1188 |
|
|
|
1189 |
|
|
String basString = basionymMatcher.group();
|
1190 |
|
|
basString = basString.replaceFirst(basStart, "");
|
1191 |
|
|
basString = basString.replaceAll(basEnd, "").trim();
|
1192 |
|
|
authorShipStart = basionymMatcher.end(1) + 1;
|
1193 |
|
|
|
1194 |
|
|
TeamOrPersonBase<?>[] basAuthors = new TeamOrPersonBase[2];
|
1195 |
|
|
Integer[] basYears = new Integer[2];
|
1196 |
|
|
authorsAndEx(basString, basAuthors, basYears);
|
1197 |
|
|
authors[2]= basAuthors[0];
|
1198 |
|
|
years[2] = basYears[0];
|
1199 |
|
|
authors[3]= basAuthors[1];
|
1200 |
|
|
years[3] = basYears[1];
|
1201 |
|
|
}
|
1202 |
|
|
if (fullAuthorString.length() >= authorShipStart){
|
1203 |
|
|
TeamOrPersonBase<?>[] combinationAuthors = new TeamOrPersonBase[2];;
|
1204 |
|
|
Integer[] combinationYears = new Integer[2];
|
1205 |
|
|
authorsAndEx(fullAuthorString.substring(authorShipStart), combinationAuthors, combinationYears);
|
1206 |
|
|
authors[0]= combinationAuthors[0] ;
|
1207 |
|
|
years[0] = combinationYears[0];
|
1208 |
|
|
authors[1]= combinationAuthors[1];
|
1209 |
|
|
years[1] = combinationYears[1];
|
1210 |
|
|
}
|
1211 |
|
|
}
|
1212 |
|
|
|
1213 |
|
|
|
1214 |
|
|
/**
|
1215 |
|
|
* Parses the author and ex-author String
|
1216 |
|
|
* @param authorShipStringOrig String representing the author and the ex-author team
|
1217 |
|
|
* @return array of Teams containing the Team[0] and the ExTeam[1]
|
1218 |
|
|
*/
|
1219 |
|
|
protected void authorsAndEx (String authorShipStringOrig, TeamOrPersonBase<?>[] authors, Integer[] years){
|
1220 |
|
|
//TODO noch allgemeiner am anfang durch Replace etc.
|
1221 |
|
|
String authorShipString = authorShipStringOrig.trim();
|
1222 |
|
|
authorShipString = authorShipString.replaceFirst(oWs + "ex" + oWs, " ex. " );
|
1223 |
|
|
|
1224 |
|
|
//int authorEnd = authorTeamString.length();
|
1225 |
|
|
int authorBegin = 0;
|
1226 |
|
|
|
1227 |
|
|
Matcher exAuthorMatcher = exAuthorPattern.matcher(authorShipString);
|
1228 |
|
|
if (exAuthorMatcher.find(0)){
|
1229 |
|
|
authorBegin = exAuthorMatcher.end(0);
|
1230 |
|
|
int exAuthorEnd = exAuthorMatcher.start(0);
|
1231 |
|
|
String exString = authorShipString.substring(0, exAuthorEnd).trim();
|
1232 |
|
|
authors [1] = author(exString);
|
1233 |
|
|
}
|
1234 |
|
|
zooOrBotanicAuthor(authorShipString.substring(authorBegin), authors, years );
|
1235 |
|
|
}
|
1236 |
|
|
|
1237 |
|
|
/**
|
1238 |
|
|
* Parses the authorString and if it matches an botanical or zoological authorTeam it fills
|
1239 |
|
|
* the computes the AuthorTeam and fills it into the first field of the team array. Same applies
|
1240 |
|
|
* to the year in case of an zoological name.
|
1241 |
|
|
* @param authorString
|
1242 |
|
|
* @param team
|
1243 |
|
|
* @param year
|
1244 |
|
|
*/
|
1245 |
|
|
protected void zooOrBotanicAuthor(String authorString, TeamOrPersonBase<?>[] team, Integer[] year){
|
1246 |
|
|
if (authorString == null){
|
1247 |
|
|
return;
|
1248 |
|
|
}else if ((authorString = authorString.trim()).length() == 0){
|
1249 |
|
|
return;
|
1250 |
|
|
}
|
1251 |
|
|
Matcher zooAuthorAddidtionMatcher = zooAuthorAddidtionPattern.matcher(authorString);
|
1252 |
|
|
if (zooAuthorAddidtionMatcher.find()){
|
1253 |
|
|
int index = zooAuthorAddidtionMatcher.start(0);
|
1254 |
|
|
String strYear = authorString.substring(index);
|
1255 |
|
|
strYear = strYear.replaceAll(zooAuthorYearSeperator, "").trim();
|
1256 |
|
|
year[0] = Integer.valueOf(strYear);
|
1257 |
|
|
authorString = authorString.substring(0, index).trim();
|
1258 |
|
|
}
|
1259 |
|
|
team[0] = author(authorString);
|
1260 |
|
|
}
|
1261 |
|
|
|
1262 |
|
|
|
1263 |
|
|
/**
|
1264 |
|
|
* Parses an authorTeam String and returns the Team
|
1265 |
|
|
* !!! TODO (atomization not yet implemented)
|
1266 |
|
|
* @param authorTeamString String representing the author team
|
1267 |
|
|
* @return an Team
|
1268 |
|
|
*/
|
1269 |
|
|
protected TeamOrPersonBase<?> author (String authorString){
|
1270 |
|
|
if (authorString == null){
|
1271 |
|
|
return null;
|
1272 |
|
|
}else if ((authorString = authorString.trim()).length() == 0){
|
1273 |
|
|
return null;
|
1274 |
|
|
}else if (! finalTeamSplitterPattern.matcher(authorString).find() && ! authorIsAlwaysTeam){
|
1275 |
|
|
//1 Person
|
1276 |
|
|
Person result = Person.NewInstance();
|
1277 |
|
|
result.setNomenclaturalTitle(authorString);
|
1278 |
|
|
return result;
|
1279 |
|
|
}else{
|
1280 |
|
|
return parsedTeam(authorString);
|
1281 |
|
|
}
|
1282 |
|
|
|
1283 |
|
|
}
|
1284 |
|
|
|
1285 |
|
|
/**
|
1286 |
|
|
* Parses an authorString (reprsenting a team into the single authors and add
|
1287 |
|
|
* them to the return Team.
|
1288 |
|
|
* @param authorString
|
1289 |
|
|
* @return Team
|
1290 |
|
|
*/
|
1291 |
|
|
protected Team parsedTeam(String authorString){
|
1292 |
|
|
Team result = Team.NewInstance();
|
1293 |
|
|
String[] authors = authorString.split(notFinalTeamSplitter);
|
1294 |
|
|
for (int i = 0; i < authors.length; i++){
|
1295 |
|
|
String author = authors[i];
|
1296 |
|
|
if ("al.".equals(author.trim()) && i == authors.length - 1){ //final al. is handled as hasMoreMembers
|
1297 |
|
|
result.setHasMoreMembers(true);
|
1298 |
|
|
}else{
|
1299 |
|
|
Person person = Person.NewInstance();
|
1300 |
|
|
person.setNomenclaturalTitle(author);
|
1301 |
|
|
result.addTeamMember(person);
|
1302 |
|
|
}
|
1303 |
|
|
}
|
1304 |
|
|
return result;
|
1305 |
|
|
}
|
1306 |
|
|
|
1307 |
|
|
|
1308 |
|
|
//Parsing of the given full name that has been identified as hybrid already somewhere else.
|
1309 |
|
|
private void parseHybrid(NonViralName nameToBeFilled, String fullNameString, Rank rank, boolean makeEmpty){
|
1310 |
|
|
logger.warn("parseHybrid --> function not yet implemented");
|
1311 |
|
|
|
1312 |
|
|
// String nonHybridName = fullNameString;
|
1313 |
|
|
// boolean isMonomHybrid = isMonomHybrid(fullNameString);
|
1314 |
|
|
// if (isMonomHybrid){
|
1315 |
|
|
// nonHybridName.replaceAll(hybrid, "");
|
1316 |
|
|
// }
|
1317 |
|
|
//
|
1318 |
|
|
// String[] split = nonHybridName.split("\\s");
|
1319 |
|
|
// parseFullName(nameToBeFilled, nonHybridName, rank, makeEmpty);
|
1320 |
|
|
//
|
1321 |
|
|
// nonHybridName = nonHybridName.replaceAll(hybrid, " ");
|
1322 |
|
|
//
|
1323 |
|
|
// boolean isBinomHybrid = isBinomHybrid(split);
|
1324 |
|
|
//// boolean isTrinomHybrid = isTrinomHybrid(split);
|
1325 |
|
|
//
|
1326 |
|
|
// nonHybridName = nonHybridName.replaceAll(hybrid, " ");
|
1327 |
|
|
//
|
1328 |
|
|
// parseFullName(nameToBeFilled, nonHybridName, rank, makeEmpty);
|
1329 |
|
|
// nameToBeFilled.getTitleCache();
|
1330 |
|
|
// nameToBeFilled.setMonomHybrid(isMonomHybrid);
|
1331 |
|
|
// nameToBeFilled.setBinomHybrid(isBinomHybrid);
|
1332 |
|
|
// nameToBeFilled.setBinomHybrid(isTrinomHybrid);
|
1333 |
|
|
|
1334 |
|
|
nameToBeFilled.setTitleCache(fullNameString,true);
|
1335 |
|
|
return;
|
1336 |
|
|
}
|
1337 |
|
|
|
1338 |
|
|
// private boolean isBinomHybrid(String[] split) {
|
1339 |
|
|
// if (){
|
1340 |
|
|
//
|
1341 |
|
|
// }
|
1342 |
|
|
// return false;
|
1343 |
|
|
// }
|
1344 |
|
|
|
1345 |
|
|
private boolean isMonomHybrid(String fullNameString) {
|
1346 |
|
|
Matcher matcher = hybridPattern.matcher(fullNameString);
|
1347 |
|
|
boolean find = matcher.find();
|
1348 |
|
|
int start = matcher.start();
|
1349 |
|
|
if (find == true && start == 0){
|
1350 |
|
|
return true;
|
1351 |
|
|
}else{
|
1352 |
|
|
return false;
|
1353 |
|
|
}
|
1354 |
|
|
}
|
1355 |
|
|
|
1356 |
|
|
// // Parsing of the given full name that has been identified as a cultivar already somwhere else.
|
1357 |
|
|
// // The ... cv. ... syntax is not covered here as it is not according the rules for naming cultivars.
|
1358 |
|
|
public BotanicalName parseCultivar(String fullName) throws StringNotParsableException{
|
1359 |
|
|
CultivarPlantName result = null;
|
1360 |
|
|
String[] words = oWsPattern.split(fullName);
|
1361 |
|
|
|
1362 |
|
|
/* ---------------------------------------------------------------------------------
|
1363 |
|
|
* cultivar
|
1364 |
|
|
* ---------------------------------------------------------------------------------*/
|
1365 |
|
|
if (fullName.indexOf(" '") != 0){
|
1366 |
|
|
//TODO location of 'xx' is probably not arbitrary
|
1367 |
|
|
Matcher cultivarMatcher = cultivarPattern.matcher(fullName);
|
1368 |
|
|
if (cultivarMatcher.find()){
|
1369 |
|
|
String namePart = fullName.replaceFirst(cultivar, "");
|
1370 |
|
|
|
1371 |
|
|
String cultivarPart = cultivarMatcher.group(0).replace("'","").trim();
|
1372 |
|
|
//OLD: String cultivarPart = cultivarRE.getParen(0).replace("'","").trim();
|
1373 |
|
|
|
1374 |
|
|
result = (CultivarPlantName)parseFullName(namePart);
|
1375 |
|
|
result.setCultivarName(cultivarPart);
|
1376 |
|
|
}
|
1377 |
|
|
}else if (fullName.indexOf(" cv.") != 0){
|
1378 |
|
|
// cv. is old form (not official)
|
1379 |
|
|
throw new StringNotParsableException("Cultivars with only cv. not yet implemented in name parser!");
|
1380 |
|
|
}
|
1381 |
|
|
|
1382 |
|
|
/* ---------------------------------------------------------------------------------
|
1383 |
|
|
* cultivar group
|
1384 |
|
|
* ---------------------------------------------------------------------------------
|
1385 |
|
|
*/
|
1386 |
|
|
// TODO in work
|
1387 |
|
|
//Ann. this is not the official way of noting cultivar groups
|
1388 |
|
|
String group = oWs + "Group" + oWs + capitalEpiWord + end;
|
1389 |
|
|
Pattern groupRE = Pattern.compile(group);
|
1390 |
|
|
Matcher groupMatcher = groupRE.matcher(fullName);
|
1391 |
|
|
if (groupMatcher.find()){
|
1392 |
|
|
if (! words[words.length - 2].equals("group")){
|
1393 |
|
|
throw new StringNotParsableException ("fct ParseHybrid --> term before cultivar group name in " + fullName + " should be 'group'");
|
1394 |
|
|
}else{
|
1395 |
|
|
|
1396 |
|
|
String namePart = fullName.substring(0, groupMatcher.start(0) - 0);
|
1397 |
|
|
//OLD: String namePart = fullName.substring(0, groupRE.getParenStart(0) - 0);
|
1398 |
|
|
|
1399 |
|
|
String cultivarPart = words[words.length -1];
|
1400 |
|
|
result = (CultivarPlantName)parseFullName(namePart);
|
1401 |
|
|
if (result != null){
|
1402 |
|
|
result.setCultivarName(cultivarPart);
|
1403 |
|
|
|
1404 |
|
|
//OLD: result.setCultivarGroupName(cultivarPart);
|
1405 |
|
|
}
|
1406 |
|
|
}
|
1407 |
|
|
|
1408 |
|
|
}
|
1409 |
|
|
// // ---------------------------------------------------------------------------------
|
1410 |
|
|
// if ( result = "" ){
|
1411 |
|
|
// return "I: fct ParseCultivar: --> could not parse cultivar " + fullName;
|
1412 |
|
|
// }else{
|
1413 |
|
|
// return result;
|
1414 |
|
|
// }
|
1415 |
|
|
return result; //TODO
|
1416 |
|
|
}
|
1417 |
|
|
|
1418 |
|
|
|
1419 |
|
|
private void makeEmpty(NonViralName<?> nameToBeFilled){
|
1420 |
|
|
nameToBeFilled.setRank(null);
|
1421 |
|
|
nameToBeFilled.setTitleCache(null, false);
|
1422 |
|
|
nameToBeFilled.setFullTitleCache(null, false);
|
1423 |
|
|
nameToBeFilled.setNameCache(null, false);
|
1424 |
|
|
|
1425 |
|
|
nameToBeFilled.setAppendedPhrase(null);
|
1426 |
|
|
nameToBeFilled.setBasionymAuthorship(null);
|
1427 |
|
|
nameToBeFilled.setCombinationAuthorship(null);
|
1428 |
|
|
nameToBeFilled.setExBasionymAuthorship(null);
|
1429 |
|
|
nameToBeFilled.setExCombinationAuthorship(null);
|
1430 |
|
|
nameToBeFilled.setAuthorshipCache(null, false);
|
1431 |
|
|
|
1432 |
|
|
|
1433 |
|
|
//delete problems except check rank
|
1434 |
|
|
makeProblemEmpty(nameToBeFilled);
|
1435 |
|
|
|
1436 |
|
|
// TODO ?
|
1437 |
|
|
//nameToBeFilled.setHomotypicalGroup(newHomotypicalGroup);
|
1438 |
|
|
|
1439 |
|
|
|
1440 |
|
|
nameToBeFilled.setGenusOrUninomial(null);
|
1441 |
|
|
nameToBeFilled.setInfraGenericEpithet(null);
|
1442 |
|
|
nameToBeFilled.setSpecificEpithet(null);
|
1443 |
|
|
nameToBeFilled.setInfraSpecificEpithet(null);
|
1444 |
|
|
|
1445 |
|
|
nameToBeFilled.setNomenclaturalMicroReference(null);
|
1446 |
|
|
nameToBeFilled.setNomenclaturalReference(null);
|
1447 |
|
|
|
1448 |
|
|
nameToBeFilled.setHybridFormula(false);
|
1449 |
|
|
nameToBeFilled.setMonomHybrid(false);
|
1450 |
|
|
nameToBeFilled.setBinomHybrid(false);
|
1451 |
|
|
nameToBeFilled.setTrinomHybrid(false);
|
1452 |
|
|
|
1453 |
|
|
if (nameToBeFilled.isInstanceOf(BotanicalName.class)){
|
1454 |
|
|
BotanicalName botanicalName = (BotanicalName)nameToBeFilled;
|
1455 |
|
|
botanicalName.setAnamorphic(false);
|
1456 |
|
|
}
|
1457 |
|
|
|
1458 |
|
|
if (nameToBeFilled.isInstanceOf(ZoologicalName.class)){
|
1459 |
|
|
ZoologicalName zoologicalName = (ZoologicalName)nameToBeFilled;
|
1460 |
|
|
zoologicalName.setBreed(null);
|
1461 |
|
|
zoologicalName.setOriginalPublicationYear(null);
|
1462 |
|
|
}
|
1463 |
|
|
|
1464 |
|
|
//nom status handled in nom status parser, otherwise we loose additional information like reference etc.
|
1465 |
|
|
//hybrid relationships handled in hybrid formula and at end of fullNameParser
|
1466 |
|
|
}
|
1467 |
|
|
|
1468 |
|
|
|
1469 |
|
|
|
1470 |
|
|
}
|