@Test
public void shouldWriteToArbitraryRDD() throws Exception {
final Configuration configuration = new BaseConfiguration();
configuration.setProperty("spark.master", "local[4]");
configuration.setProperty("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
configuration.setProperty(Graph.GRAPH, HadoopGraph.class.getName());
configuration.setProperty(
Constants.GREMLIN_HADOOP_INPUT_LOCATION,
HadoopGraphProvider.PATHS.get("tinkerpop-modern.kryo"));
configuration.setProperty(
Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT, GryoInputFormat.class.getCanonicalName());
configuration.setProperty(
Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_RDD, ExampleOutputRDD.class.getCanonicalName());
configuration.setProperty(
Constants.GREMLIN_HADOOP_OUTPUT_LOCATION, "hadoop-gremlin/target/test-output");
configuration.setProperty(Constants.GREMLIN_HADOOP_JARS_IN_DISTRIBUTED_CACHE, false);
////////
Graph graph = GraphFactory.open(configuration);
graph
.compute(SparkGraphComputer.class)
.result(GraphComputer.ResultGraph.NEW)
.persist(GraphComputer.Persist.EDGES)
.program(
TraversalVertexProgram.build()
.traversal(
GraphTraversalSource.build()
.engine(ComputerTraversalEngine.build().computer(SparkGraphComputer.class)),
"gremlin-groovy",
"g.V()")
.create(graph))
.submit()
.get();
}
