Search in sources :

Example 1 with ImportKeyValueJavaPairRDDToAccumulo

use of uk.gov.gchq.gaffer.sparkaccumulo.operation.javardd.ImportKeyValueJavaPairRDDToAccumulo in project Gaffer by gchq.

the class ImportKeyValueJavaPairRDDToAccumuloHandlerTest method checkImportKeyValueJavaPairRDD.

@Test
public void checkImportKeyValueJavaPairRDD() throws OperationException, IOException, InterruptedException {
    final Graph graph1 = new Graph.Builder().addSchema(getClass().getResourceAsStream("/schema/dataSchema.json")).addSchema(getClass().getResourceAsStream("/schema/dataTypes.json")).addSchema(getClass().getResourceAsStream("/schema/storeSchema.json")).addSchema(getClass().getResourceAsStream("/schema/storeTypes.json")).storeProperties(getClass().getResourceAsStream("/store.properties")).build();
    final List<Element> elements = new ArrayList<>();
    for (int i = 0; i < 10; i++) {
        final Entity entity = new Entity(TestGroups.ENTITY);
        entity.setVertex("" + i);
        final Edge edge1 = new Edge(TestGroups.EDGE);
        edge1.setSource("" + i);
        edge1.setDestination("B");
        edge1.setDirected(false);
        edge1.putProperty(TestPropertyNames.COUNT, 2);
        final Edge edge2 = new Edge(TestGroups.EDGE);
        edge2.setSource("" + i);
        edge2.setDestination("C");
        edge2.setDirected(false);
        edge2.putProperty(TestPropertyNames.COUNT, 4);
        elements.add(edge1);
        elements.add(edge2);
        elements.add(entity);
    }
    final User user = new User();
    final SparkConf sparkConf = new SparkConf().setMaster("local").setAppName("testCheckGetCorrectElementsInJavaRDDForEntitySeed").set("spark.serializer", "org.apache.spark.serializer.KryoSerializer").set("spark.kryo.registrator", "uk.gov.gchq.gaffer.spark.serialisation.kryo.Registrator").set("spark.driver.allowMultipleContexts", "true");
    final JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);
    // Create Hadoop configuration and serialise to a string
    final Configuration configuration = new Configuration();
    final ByteArrayOutputStream baos = new ByteArrayOutputStream();
    configuration.write(new DataOutputStream(baos));
    final String configurationString = new String(baos.toByteArray(), CommonConstants.UTF_8);
    final String outputPath = this.getClass().getResource("/").getPath().toString() + "load";
    final String failurePath = this.getClass().getResource("/").getPath().toString() + "failure";
    final File file = new File(outputPath);
    if (file.exists()) {
        FileUtils.forceDelete(file);
    }
    final ElementConverterFunction func = new ElementConverterFunction(sparkContext.broadcast(new ByteEntityAccumuloElementConverter(graph1.getSchema())));
    final JavaPairRDD<Key, Value> elementJavaRDD = sparkContext.parallelize(elements).flatMapToPair(func);
    final ImportKeyValueJavaPairRDDToAccumulo addRdd = new ImportKeyValueJavaPairRDDToAccumulo.Builder().input(elementJavaRDD).outputPath(outputPath).failurePath(failurePath).build();
    graph1.execute(addRdd, user);
    FileUtils.forceDelete(file);
    // Check all elements were added
    final GetJavaRDDOfAllElements rddQuery = new GetJavaRDDOfAllElements.Builder().javaSparkContext(sparkContext).option(AbstractGetRDDHandler.HADOOP_CONFIGURATION_KEY, configurationString).build();
    final JavaRDD<Element> rdd = graph1.execute(rddQuery, user);
    if (rdd == null) {
        fail("No RDD returned");
    }
    final Set<Element> results = new HashSet<>(rdd.collect());
    assertEquals(elements.size(), results.size());
    sparkContext.stop();
}
Also used : Entity(uk.gov.gchq.gaffer.data.element.Entity) User(uk.gov.gchq.gaffer.user.User) Configuration(org.apache.hadoop.conf.Configuration) DataOutputStream(java.io.DataOutputStream) Element(uk.gov.gchq.gaffer.data.element.Element) ArrayList(java.util.ArrayList) GetJavaRDDOfAllElements(uk.gov.gchq.gaffer.spark.operation.javardd.GetJavaRDDOfAllElements) JavaSparkContext(org.apache.spark.api.java.JavaSparkContext) HashSet(java.util.HashSet) ByteArrayOutputStream(org.apache.commons.io.output.ByteArrayOutputStream) ImportKeyValueJavaPairRDDToAccumulo(uk.gov.gchq.gaffer.sparkaccumulo.operation.javardd.ImportKeyValueJavaPairRDDToAccumulo) Graph(uk.gov.gchq.gaffer.graph.Graph) Value(org.apache.accumulo.core.data.Value) ByteEntityAccumuloElementConverter(uk.gov.gchq.gaffer.accumulostore.key.core.impl.byteEntity.ByteEntityAccumuloElementConverter) ElementConverterFunction(uk.gov.gchq.gaffer.sparkaccumulo.operation.utils.java.ElementConverterFunction) Edge(uk.gov.gchq.gaffer.data.element.Edge) SparkConf(org.apache.spark.SparkConf) File(java.io.File) Key(org.apache.accumulo.core.data.Key) Test(org.junit.Test)

Example 2 with ImportKeyValueJavaPairRDDToAccumulo

use of uk.gov.gchq.gaffer.sparkaccumulo.operation.javardd.ImportKeyValueJavaPairRDDToAccumulo in project Gaffer by gchq.

the class ImportJavaRDDOfElementsHandler method doOperation.

public void doOperation(final ImportJavaRDDOfElements operation, final Context context, final AccumuloStore store) throws OperationException {
    final String outputPath = operation.getOption(OUTPUT_PATH);
    if (null == outputPath || outputPath.isEmpty()) {
        throw new OperationException("Option outputPath must be set for this option to be run against the accumulostore");
    }
    final String failurePath = operation.getOption(FAILURE_PATH);
    if (null == failurePath || failurePath.isEmpty()) {
        throw new OperationException("Option failurePath must be set for this option to be run against the accumulostore");
    }
    final Broadcast<AccumuloElementConverter> broadcast = operation.getJavaSparkContext().broadcast(store.getKeyPackage().getKeyConverter());
    final ElementConverterFunction func = new ElementConverterFunction(broadcast);
    final JavaPairRDD<Key, Value> rdd = operation.getInput().flatMapToPair(func);
    final ImportKeyValueJavaPairRDDToAccumulo op = new ImportKeyValueJavaPairRDDToAccumulo.Builder().input(rdd).failurePath(failurePath).outputPath(outputPath).build();
    store._execute(new OperationChain<>(op), context);
}
Also used : ImportKeyValueJavaPairRDDToAccumulo(uk.gov.gchq.gaffer.sparkaccumulo.operation.javardd.ImportKeyValueJavaPairRDDToAccumulo) AccumuloElementConverter(uk.gov.gchq.gaffer.accumulostore.key.AccumuloElementConverter) Value(org.apache.accumulo.core.data.Value) ElementConverterFunction(uk.gov.gchq.gaffer.sparkaccumulo.operation.utils.java.ElementConverterFunction) OperationException(uk.gov.gchq.gaffer.operation.OperationException) Key(org.apache.accumulo.core.data.Key)

Aggregations

Key (org.apache.accumulo.core.data.Key)2 Value (org.apache.accumulo.core.data.Value)2 ImportKeyValueJavaPairRDDToAccumulo (uk.gov.gchq.gaffer.sparkaccumulo.operation.javardd.ImportKeyValueJavaPairRDDToAccumulo)2 ElementConverterFunction (uk.gov.gchq.gaffer.sparkaccumulo.operation.utils.java.ElementConverterFunction)2 DataOutputStream (java.io.DataOutputStream)1 File (java.io.File)1 ArrayList (java.util.ArrayList)1 HashSet (java.util.HashSet)1 ByteArrayOutputStream (org.apache.commons.io.output.ByteArrayOutputStream)1 Configuration (org.apache.hadoop.conf.Configuration)1 SparkConf (org.apache.spark.SparkConf)1 JavaSparkContext (org.apache.spark.api.java.JavaSparkContext)1 Test (org.junit.Test)1 AccumuloElementConverter (uk.gov.gchq.gaffer.accumulostore.key.AccumuloElementConverter)1 ByteEntityAccumuloElementConverter (uk.gov.gchq.gaffer.accumulostore.key.core.impl.byteEntity.ByteEntityAccumuloElementConverter)1 Edge (uk.gov.gchq.gaffer.data.element.Edge)1 Element (uk.gov.gchq.gaffer.data.element.Element)1 Entity (uk.gov.gchq.gaffer.data.element.Entity)1 Graph (uk.gov.gchq.gaffer.graph.Graph)1 OperationException (uk.gov.gchq.gaffer.operation.OperationException)1