Package org.getalp.dbnary.languages.eng
Class WiktionaryDataHandler
- java.lang.Object
-
- org.getalp.dbnary.model.DbnaryModel
-
- org.getalp.dbnary.languages.OntolexBasedRDFDataHandler
-
- org.getalp.dbnary.languages.eng.WiktionaryDataHandler
-
- All Implemented Interfaces:
IWiktionaryDataHandler
public class WiktionaryDataHandler extends OntolexBasedRDFDataHandler
Created by serasset on 17/09/14, pantaleo
-
-
Nested Class Summary
-
Nested classes/interfaces inherited from class org.getalp.dbnary.languages.OntolexBasedRDFDataHandler
OntolexBasedRDFDataHandler.PosAndType
-
-
Field Summary
Fields Modifier and Type Field Description protected static HashSet<org.apache.jena.rdf.model.Resource>
affixTypes
ArrayList<org.apache.jena.rdf.model.Resource>
ancestors
Resources containing Etymology Entries.org.apache.jena.rdf.model.Resource
currentEtymologyEntry
protected int
currentEtymologyNumber
An integer counting the number of alternative etymologies for the same entry.org.apache.jena.rdf.model.Resource
currentGlobalEtymologyEntry
protected static HashSet<org.apache.jena.rdf.model.Resource>
multiWordTypes
protected static HashMap<org.apache.jena.rdf.model.Resource,org.apache.jena.rdf.model.Resource>
wordToMutiWordPOSTypes
protected static HashSet<org.apache.jena.rdf.model.Resource>
wordTypes
-
Fields inherited from class org.getalp.dbnary.languages.OntolexBasedRDFDataHandler
aBox, currentCanonicalForm, currentEncodedLexicalEntryName, currentLexEntry, currentLexicalEntry, currentLexieCount, currentMainLexEntry, currentPage, currentSense, currentSenseNumber, currentSharedPronunciations, glossFilter, lexvoExtractedLanguage, lexvoSectionLanguage, longEditionLanguageCode, longSectionLanguageCode, nbEntries, posAndTypeValueMap, reifiedNymCount, shortEditionLanguageCode, shortSectionLanguageCode, translationCount, WIKT
-
Fields inherited from class org.getalp.dbnary.model.DbnaryModel
DBNARY_NS_PREFIX, LEXVO, tBox
-
-
Constructor Summary
Constructors Constructor Description WiktionaryDataHandler(String lang, String tdbDir)
-
Method Summary
All Methods Static Methods Instance Methods Concrete Methods Modifier and Type Method Description void
addAncestorsAndRegisterDescendants(Etymology etymology)
void
addInflectionOnCanonicalForm(EnglishInflectionData infl)
protected void
addOtherFormPropertiesToLexicalEntry(org.apache.jena.rdf.model.Resource lexEntry, HashSet<PropertyObjectPair> properties)
void
addWrittenRep(String word)
void
comparable()
void
countable()
org.apache.jena.rdf.model.Resource
createEtymologyEntryResource(org.apache.jena.rdf.model.Model eBox, String e, String lang)
void
finalizeAncestors()
String
getDerivationStatementId(String derived)
org.apache.jena.rdf.model.Resource
getGlossForWikisaurus(String id)
String
getGlossURI(String id)
String
getPrefix(String lang)
void
initializeAncestors()
void
initializeLanguageSection(String lang)
protected org.apache.jena.rdf.model.Resource
initializeLexicalEntry(String pos, org.apache.jena.rdf.model.Resource lexinfoPOS, org.apache.jena.rdf.model.Resource type)
void
initializeNewEtymology()
static boolean
isValidPOS(String pos)
void
notComparable()
void
postProcessEtymology()
void
registerCurrentEtymologyEntry(String lang)
void
registerDerivation(String derived)
void
registerDerivation(String derived, String note)
void
registerDerived(Etymology etymology)
void
registerEtymology(Etymology etymology)
void
registerEtymologyPos(String wiktionaryPageName)
void
registerEtymologyPos(String lang, String languageName, String wiktionaryPageName)
void
registerInflection(String languageCode, String pos, String inflection, String canonicalForm, int defNumber, HashSet<PropertyObjectPair> props)
void
registerInflection(String languageCode, String pos, String inflection, String canonicalForm, int defNumber, HashSet<PropertyObjectPair> props, HashSet<PronunciationPair> pronunciations)
void
registerInflection(String inflection, String note, HashSet<PropertyObjectPair> props)
void
registerNymRelationToEntity(String target, String nymRelation, org.apache.jena.rdf.model.Resource entity, org.apache.jena.rdf.model.Resource gloss, String usage)
void
registerWikisaurusNym(String currentPOS, String currentWS, String currentNym, String s)
void
uncountable()
-
Methods inherited from class org.getalp.dbnary.languages.OntolexBasedRDFDataHandler
addTo, addToCurrentWordSense, buildDatacubeObservations, closeDataset, computeNymId, computeNymId, computeOtherFormResourceName, computeSenseNum, computeStatistics, createGeneralStatisticsObservation, createGlossResource, createGlossResource, createGlossResource, createGlossResource, createNymRelationObservation, createTranslationObservation, currentLexinfoPos, currentPagename, currentWiktionaryPos, decodePartOfSpeech, dump, dumpAllFeaturesAsHDT, enableEndolexFeatures, enableExolexFeatures, finalizeLanguageSection, finalizePageExtraction, getCurrentEntryLanguage, getEncodedPageName, getEndolexFeatureBox, getExolexFeatureBox, getExtractedLanguage, getFeatureBox, getGlossFilter, getGlossResourceName, getLexEntry, getLexEntry, getPageResource, getPageResource, getPageResourceIRI, getPrefix, initializeLexicalEntry, initializeLexicalEntry__noModel, initializePageExtraction, isDisabled, isResourceCompatible, mergePropertiesIntoResource, nbEntries, populateMetadata, posResource, posResource, registerAlternateSpelling, registerExample, registerExample, registerInflection, registerNewDefinition, registerNewDefinition, registerNewDefinition, registerNymRelation, registerNymRelation, registerNymRelationOnCurrentSense, registerNymRelationToEntity, registerPronunciation, registerPronunciation, registerPropertyOnCanonicalForm, registerPropertyOnLexicalEntry, registerTranslation, registerTranslationToEntity, typeResource, typeResource
-
Methods inherited from class org.getalp.dbnary.model.DbnaryModel
setGlobalDbnaryPrefix, uriEncode, uriEncode, uriEncode
-
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
-
Methods inherited from interface org.getalp.dbnary.api.IWiktionaryDataHandler
registerNymRelationOnCurrentSense
-
-
-
-
Field Detail
-
ancestors
public ArrayList<org.apache.jena.rdf.model.Resource> ancestors
Resources containing Etymology Entries.
-
currentEtymologyEntry
public org.apache.jena.rdf.model.Resource currentEtymologyEntry
-
currentGlobalEtymologyEntry
public org.apache.jena.rdf.model.Resource currentGlobalEtymologyEntry
-
currentEtymologyNumber
protected int currentEtymologyNumber
An integer counting the number of alternative etymologies for the same entry.
-
wordToMutiWordPOSTypes
protected static final HashMap<org.apache.jena.rdf.model.Resource,org.apache.jena.rdf.model.Resource> wordToMutiWordPOSTypes
-
multiWordTypes
protected static final HashSet<org.apache.jena.rdf.model.Resource> multiWordTypes
-
affixTypes
protected static final HashSet<org.apache.jena.rdf.model.Resource> affixTypes
-
wordTypes
protected static final HashSet<org.apache.jena.rdf.model.Resource> wordTypes
-
-
Method Detail
-
initializeLanguageSection
public void initializeLanguageSection(String lang)
- Specified by:
initializeLanguageSection
in interfaceIWiktionaryDataHandler
- Overrides:
initializeLanguageSection
in classOntolexBasedRDFDataHandler
-
initializeLexicalEntry
protected org.apache.jena.rdf.model.Resource initializeLexicalEntry(String pos, org.apache.jena.rdf.model.Resource lexinfoPOS, org.apache.jena.rdf.model.Resource type)
- Overrides:
initializeLexicalEntry
in classOntolexBasedRDFDataHandler
-
registerDerivation
public void registerDerivation(String derived)
-
isValidPOS
public static boolean isValidPOS(String pos)
-
registerEtymologyPos
public void registerEtymologyPos(String wiktionaryPageName)
-
registerEtymologyPos
public void registerEtymologyPos(String lang, String languageName, String wiktionaryPageName)
-
postProcessEtymology
public void postProcessEtymology()
-
registerDerived
public void registerDerived(Etymology etymology)
-
registerCurrentEtymologyEntry
public void registerCurrentEtymologyEntry(String lang)
-
createEtymologyEntryResource
public org.apache.jena.rdf.model.Resource createEtymologyEntryResource(org.apache.jena.rdf.model.Model eBox, String e, String lang)
-
registerEtymology
public void registerEtymology(Etymology etymology)
-
initializeAncestors
public void initializeAncestors()
-
finalizeAncestors
public void finalizeAncestors()
-
addAncestorsAndRegisterDescendants
public void addAncestorsAndRegisterDescendants(Etymology etymology)
-
registerInflection
public void registerInflection(String languageCode, String pos, String inflection, String canonicalForm, int defNumber, HashSet<PropertyObjectPair> props, HashSet<PronunciationPair> pronunciations)
- Specified by:
registerInflection
in interfaceIWiktionaryDataHandler
- Overrides:
registerInflection
in classOntolexBasedRDFDataHandler
-
addOtherFormPropertiesToLexicalEntry
protected void addOtherFormPropertiesToLexicalEntry(org.apache.jena.rdf.model.Resource lexEntry, HashSet<PropertyObjectPair> properties)
- Overrides:
addOtherFormPropertiesToLexicalEntry
in classOntolexBasedRDFDataHandler
-
registerInflection
public void registerInflection(String inflection, String note, HashSet<PropertyObjectPair> props)
-
registerInflection
public void registerInflection(String languageCode, String pos, String inflection, String canonicalForm, int defNumber, HashSet<PropertyObjectPair> props)
- Specified by:
registerInflection
in interfaceIWiktionaryDataHandler
- Overrides:
registerInflection
in classOntolexBasedRDFDataHandler
- Parameters:
languageCode
- the language code of the inflectionpos
- the part of speech of the inflected forminflection
- inflected formcanonicalForm
- canonical formdefNumber
- definition number of the word sense associated to the formprops
- morpho syntactic properties to be registered with the inflected form
-
addWrittenRep
public void addWrittenRep(String word)
-
uncountable
public void uncountable()
-
countable
public void countable()
-
comparable
public void comparable()
-
notComparable
public void notComparable()
-
addInflectionOnCanonicalForm
public void addInflectionOnCanonicalForm(EnglishInflectionData infl)
-
getGlossForWikisaurus
public org.apache.jena.rdf.model.Resource getGlossForWikisaurus(String id)
-
registerWikisaurusNym
public void registerWikisaurusNym(String currentPOS, String currentWS, String currentNym, String s)
-
registerNymRelationToEntity
public void registerNymRelationToEntity(String target, String nymRelation, org.apache.jena.rdf.model.Resource entity, org.apache.jena.rdf.model.Resource gloss, String usage)
- Overrides:
registerNymRelationToEntity
in classOntolexBasedRDFDataHandler
-
initializeNewEtymology
public void initializeNewEtymology()
-
-