Class TextExtractorResourceDescriptionInRDF

java.lang.Object
de.uni_mannheim.informatik.dws.melt.matching_jena_matchers.util.textExtractors.TextExtractorRDFBase
de.uni_mannheim.informatik.dws.melt.matching_jena_matchers.util.textExtractors.TextExtractorResourceDescriptionInRDF
All Implemented Interfaces:
TextExtractor

public class TextExtractorResourceDescriptionInRDF extends TextExtractorRDFBase
  • Field Details

    • LOGGER

      private static final org.slf4j.Logger LOGGER
    • MULTIPLE_WHITESPACE

      private static final Pattern MULTIPLE_WHITESPACE
    • removeNewlines

      protected boolean removeNewlines
    • removeMultipleSpaces

      protected boolean removeMultipleSpaces
    • useLabelInsteadOfResource

      protected boolean useLabelInsteadOfResource
    • includePrefixesInModel

      protected boolean includePrefixesInModel
    • removePrefixDefition

      protected boolean removePrefixDefition
    • serializationFormat

      protected org.apache.jena.riot.RDFFormat serializationFormat
      The serialization format to use - more info at the corresponding jena page.
    • LABEL_PROP

      private static final Set<org.apache.jena.rdf.model.Property> LABEL_PROP
    • labelExtractor

      private static final TextExtractorOnlyLabel labelExtractor
    • noPrefixLang

      private static Set<org.apache.jena.riot.Lang> noPrefixLang
  • Constructor Details

    • TextExtractorResourceDescriptionInRDF

      public TextExtractorResourceDescriptionInRDF(boolean useLabelInsteadOfResource, org.apache.jena.riot.RDFFormat serializationFormat)
    • TextExtractorResourceDescriptionInRDF

      public TextExtractorResourceDescriptionInRDF(boolean useLabelInsteadOfResource)
    • TextExtractorResourceDescriptionInRDF

      public TextExtractorResourceDescriptionInRDF()
  • Method Details

    • extract

      public Set<String> extract(org.apache.jena.rdf.model.Resource r)
      Description copied from interface: TextExtractor
      Given a Jena resource this method extracts textual/string representations from it.
      Parameters:
      r - the jena resource which also allows to traverse the whole rdf graph
      Returns:
      a set of textual representations of the given resource.
    • getModelWithResource

      protected org.apache.jena.rdf.model.Model getModelWithResource(org.apache.jena.rdf.model.Resource r)
    • getModelWithLabel

      protected org.apache.jena.rdf.model.Model getModelWithLabel(org.apache.jena.rdf.model.Resource r)
    • removeUnusedPrefixes

      private org.apache.jena.rdf.model.Model removeUnusedPrefixes(org.apache.jena.rdf.model.Model m)
    • getPrefix

      private String getPrefix(Map<String,String> map, String uri)
    • createEmptyModel

      private org.apache.jena.rdf.model.Model createEmptyModel(org.apache.jena.rdf.model.Resource r)
    • isRemoveNewlines

      public boolean isRemoveNewlines()
    • setRemoveNewlines

      public TextExtractorResourceDescriptionInRDF setRemoveNewlines(boolean removeNewlines)
    • isUseLabelInsteadOfResource

      public boolean isUseLabelInsteadOfResource()
    • setUseLabelInsteadOfResource

      public TextExtractorResourceDescriptionInRDF setUseLabelInsteadOfResource(boolean useLabelInsteadOfResource)
    • isIncludePrefixesInModel

      public boolean isIncludePrefixesInModel()
    • setIncludePrefixesInModel

      public TextExtractorResourceDescriptionInRDF setIncludePrefixesInModel(boolean includePrefixesInModel)
    • isRemovePrefixDefition

      public boolean isRemovePrefixDefition()
    • setRemovePrefixDefition

      public TextExtractorResourceDescriptionInRDF setRemovePrefixDefition(boolean removePrefixDefition)
    • getSerializationFormat

      public org.apache.jena.riot.RDFFormat getSerializationFormat()
    • setSerializationFormat

      public TextExtractorResourceDescriptionInRDF setSerializationFormat(org.apache.jena.riot.RDFFormat serializationFormat)
    • isRemoveMultipleSpaces

      public boolean isRemoveMultipleSpaces()
    • setRemoveMultipleSpaces

      public TextExtractorResourceDescriptionInRDF setRemoveMultipleSpaces(boolean removeMultipleSpaces)