Package net.sansa_stack.spark.rdd.op.rdf

Class JavaRddOfTriplesOps

java.lang.Object
net.sansa_stack.spark.rdd.op.rdf.JavaRddOfTriplesOps
public class JavaRddOfTriplesOps extends Object

  • Constructor Summary

    Constructors
    Constructor
    Description
    JavaRddOfTriplesOps()
     

  • Method Summary

    Modifier and Type
    Method
    Description
    static <K> org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.rdf.model.Model>
    groupBy(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd, org.aksw.commons.lambda.serializable.SerializableFunction<? super org.apache.jena.graph.Triple,K> tripleToKey)
     
    static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model>
    groupByObjectNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
     
    static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model>
    groupByObjects(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
     
    static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model>
    groupByPredicateNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
    This function mainly exists for completeness
    static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model>
    groupByPredicates(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
    This function mainly exists for completeness
    static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model>
    groupBySubjectNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
     
    static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model>
    groupBySubjects(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
     
    static <K> org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.rdf.model.Model>
    groupTriplesIntoModels(org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.graph.Triple> rdd)
     
    static JavaRddFunction<org.apache.jena.graph.Triple,org.apache.jena.sparql.core.Quad>
    mapIntoGraph(org.apache.jena.graph.Node graphNode)
     
    static org.apache.spark.api.java.JavaRDD<org.apache.jena.rdf.model.Model>
    mapToModel(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
     
    static org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple>
    postProcess(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd, boolean sort, boolean ascending, boolean distinct, int numPartitions)
    Sort quads by their string representation (relies on NodeFmtLib.str(org.apache.jena.graph.Triple))
    static String
    toGraphName(org.apache.jena.graph.Node node)
    Map a node losslessly to an IRI suitable for use as a graph name This is needed to e.g.

    Methods inherited from class java.lang.Object

    clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

  • Constructor Details

    • JavaRddOfTriplesOps

      public JavaRddOfTriplesOps()

  • Method Details

    • groupTriplesIntoModels

      public static <K> org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.rdf.model.Model> groupTriplesIntoModels(org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.graph.Triple> rdd)

    • groupBy

      public static <K> org.apache.spark.api.java.JavaPairRDD<K,org.apache.jena.rdf.model.Model> groupBy(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd, org.aksw.commons.lambda.serializable.SerializableFunction<? super org.apache.jena.graph.Triple,K> tripleToKey)

    • groupBySubjectNodes

      public static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model> groupBySubjectNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)

    • groupByObjectNodes

      public static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model> groupByObjectNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)

    • groupByPredicateNodes

      public static org.apache.spark.api.java.JavaPairRDD<org.apache.jena.graph.Node,org.apache.jena.rdf.model.Model> groupByPredicateNodes(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
      This function mainly exists for completeness

    • groupBySubjects

      public static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model> groupBySubjects(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)

    • groupByObjects

      public static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model> groupByObjects(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)

    • groupByPredicates

      public static org.apache.spark.api.java.JavaPairRDD<String,org.apache.jena.rdf.model.Model> groupByPredicates(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)
      This function mainly exists for completeness

    • toGraphName

      public static String toGraphName(org.apache.jena.graph.Node node)
      Map a node losslessly to an IRI suitable for use as a graph name This is needed to e.g. group triples by objects into named graphs in order to use all the RDF machinery - named graphs need to be IRIs. This mapping is used in the 'RddOfDatasetOps.naturalResource' TODO Add a reverse mapping

    • mapToModel

      public static org.apache.spark.api.java.JavaRDD<org.apache.jena.rdf.model.Model> mapToModel(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd)

    • mapIntoGraph

      public static JavaRddFunction<org.apache.jena.graph.Triple,org.apache.jena.sparql.core.Quad> mapIntoGraph(org.apache.jena.graph.Node graphNode)

    • postProcess

      public static org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> postProcess(org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> rdd, boolean sort, boolean ascending, boolean distinct, int numPartitions)
      Sort quads by their string representation (relies on NodeFmtLib.str(org.apache.jena.graph.Triple))