Package net.sansa_stack.spark.rdd.op.rdf
Class JavaRddOfBindingsOps
java.lang.Object
net.sansa_stack.spark.rdd.op.rdf.JavaRddOfBindingsOps
-
Field Summary
Modifier and TypeFieldDescriptionstatic final org.apache.jena.sparql.core.Var
The special ?ROWNUM variable supported by tarql -
Constructor Summary
-
Method Summary
Modifier and TypeMethodDescriptionstatic <A2,
I, O> Function<I, O> bindSecondArgument
(A2 arg2, BiFunction<I, A2, O> fn) Create a Function from a BiFunction by binding the second argument to a given valuestatic <I,
O> Function<I, O> bindToExecCxt
(org.apache.jena.sparql.engine.ExecutionContext execCxt, BiFunction<I, org.apache.jena.sparql.engine.ExecutionContext, O> fn) static <T> BiFunction<org.apache.jena.sparql.engine.binding.Binding,
org.apache.jena.sparql.engine.ExecutionContext, Stream<T>> compileNodeTupleMapper
(org.apache.jena.query.Query query, Function<org.apache.jena.sparql.syntax.Template, Function<org.apache.jena.sparql.engine.binding.Binding, Stream<T>>> templateMapperFactory) Compile a construct query into a function that can efficiently produce triples/quads from a given binding.static Function<org.apache.jena.sparql.engine.binding.Binding,
Stream<org.apache.jena.sparql.core.Quad>> compileTarqlMapper
(List<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean constructMode) static Function<org.apache.jena.sparql.engine.binding.Binding,
org.apache.jena.sparql.core.DatasetGraph> compileTarqlMapperGeneral
(Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode) static org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding>
enrichRddWithRowNum
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd) static boolean
mayProduceQuads
(Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts) static boolean
mayProduceQuads
(org.aksw.jenax.stmt.core.SparqlStmt stmt) static boolean
mentionesRowNum
(Collection<org.aksw.jenax.stmt.core.SparqlStmt> sparqlStmts) static boolean
mentionesRowNum
(org.aksw.jenax.stmt.core.SparqlStmt sparqlStmt) static org.aksw.commons.util.stream.StreamFunction<org.apache.jena.sparql.engine.binding.Binding,
org.apache.jena.sparql.core.Quad> quadMapper
(Collection<org.apache.jena.query.Query> queries, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) static <T> org.apache.spark.api.java.JavaRDD<T>
tarqlDatasets
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, org.aksw.commons.lambda.serializable.SerializableFunction<org.apache.jena.sparql.core.DatasetGraph, Stream<T>> finisher) Turns each row into a dataset based on SPARQL update statements.static org.apache.spark.api.java.JavaRDD<org.apache.jena.query.Dataset>
tarqlDatasets
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, org.apache.jena.query.Query query) Method for the typical case of mapping an RDD of bindings via a construct query to an RDD of datasets.static org.apache.jena.sparql.algebra.Op
tarqlOptimize
(org.apache.jena.sparql.algebra.Op op) Apply default optimizations for algebra expressions meant for tarql Combines EXTENDSstatic org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.core.Quad>
tarqlQuads
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) static org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.core.Quad>
tarqlQuads
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, org.apache.jena.query.Query query, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) static org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple>
tarqlTriples
(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) static Function<org.apache.jena.sparql.engine.binding.Binding,
Stream<org.apache.jena.sparql.core.Quad>> templateMapperQuads
(org.apache.jena.sparql.syntax.Template template) templateMapperTriples
(org.apache.jena.sparql.syntax.Template template) static org.aksw.commons.util.stream.StreamFunction<org.apache.jena.sparql.engine.binding.Binding,
org.apache.jena.graph.Triple> tripleMapper
(Collection<org.apache.jena.query.Query> queries, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier)
-
Field Details
-
ROWNUM
public static final org.apache.jena.sparql.core.Var ROWNUMThe special ?ROWNUM variable supported by tarql
-
-
Constructor Details
-
JavaRddOfBindingsOps
public JavaRddOfBindingsOps()
-
-
Method Details
-
compileNodeTupleMapper
public static <T> BiFunction<org.apache.jena.sparql.engine.binding.Binding,org.apache.jena.sparql.engine.ExecutionContext, compileNodeTupleMapperStream<T>> (org.apache.jena.query.Query query, Function<org.apache.jena.sparql.syntax.Template, Function<org.apache.jena.sparql.engine.binding.Binding, Stream<T>>> templateMapperFactory) Compile a construct query into a function that can efficiently produce triples/quads from a given binding. The query is internally stored in algebra form to allow for fast execution. -
bindToExecCxt
public static <I,O> Function<I,O> bindToExecCxt(org.apache.jena.sparql.engine.ExecutionContext execCxt, BiFunction<I, org.apache.jena.sparql.engine.ExecutionContext, O> fn) -
bindSecondArgument
Create a Function from a BiFunction by binding the second argument to a given value -
templateMapperTriples
-
templateMapperQuads
-
compileTarqlMapper
-
compileTarqlMapperGeneral
public static Function<org.apache.jena.sparql.engine.binding.Binding,org.apache.jena.sparql.core.DatasetGraph> compileTarqlMapperGeneral(Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode) -
mayProduceQuads
-
mayProduceQuads
public static boolean mayProduceQuads(org.aksw.jenax.stmt.core.SparqlStmt stmt) -
tarqlDatasets
public static org.apache.spark.api.java.JavaRDD<org.apache.jena.query.Dataset> tarqlDatasets(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, org.apache.jena.query.Query query) Method for the typical case of mapping an RDD of bindings via a construct query to an RDD of datasets. -
tarqlDatasets
public static <T> org.apache.spark.api.java.JavaRDD<T> tarqlDatasets(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, org.aksw.commons.lambda.serializable.SerializableFunction<org.apache.jena.sparql.core.DatasetGraph, Stream<T>> finisher) Turns each row into a dataset based on SPARQL update statements. Construct queries and select queries are print out to STDERR. UseUpdateUtils.constructToInsert
to convert construct queries. -
tarqlTriples
public static org.apache.spark.api.java.JavaRDD<org.apache.jena.graph.Triple> tarqlTriples(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) -
tarqlQuads
public static org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.core.Quad> tarqlQuads(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, org.apache.jena.query.Query query, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) -
tarqlQuads
public static org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.core.Quad> tarqlQuads(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd, Collection<org.aksw.jenax.stmt.core.SparqlStmt> stmts, boolean accumulationMode, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) -
tripleMapper
public static org.aksw.commons.util.stream.StreamFunction<org.apache.jena.sparql.engine.binding.Binding,org.apache.jena.graph.Triple> tripleMapper(Collection<org.apache.jena.query.Query> queries, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) -
quadMapper
public static org.aksw.commons.util.stream.StreamFunction<org.apache.jena.sparql.engine.binding.Binding,org.apache.jena.sparql.core.Quad> quadMapper(Collection<org.apache.jena.query.Query> queries, Supplier<org.apache.jena.sparql.engine.ExecutionContext> execCxtSupplier) -
tarqlOptimize
public static org.apache.jena.sparql.algebra.Op tarqlOptimize(org.apache.jena.sparql.algebra.Op op) Apply default optimizations for algebra expressions meant for tarql Combines EXTENDS -
mentionesRowNum
public static boolean mentionesRowNum(org.aksw.jenax.stmt.core.SparqlStmt sparqlStmt) -
mentionesRowNum
-
enrichRddWithRowNum
public static org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> enrichRddWithRowNum(org.apache.spark.api.java.JavaRDD<org.apache.jena.sparql.engine.binding.Binding> rdd)
-