use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.
the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindMultiMaps.
/**
* Tests join program with replicated data source behind multiple map ops.
*/
@Test
public void checkJoinWithReplicatedSourceInputBehindMultiMaps() {
ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
env.setParallelism(DEFAULT_PARALLELISM);
TupleTypeInfo<Tuple1<String>> typeInfo = TupleTypeInfo.getBasicTupleTypeInfo(String.class);
ReplicatingInputFormat<Tuple1<String>, FileInputSplit> rif = new ReplicatingInputFormat<Tuple1<String>, FileInputSplit>(new TupleCsvInputFormat<Tuple1<String>>(new Path("/some/path"), typeInfo));
DataSet<Tuple1<String>> source1 = env.createInput(rif, new TupleTypeInfo<Tuple1<String>>(BasicTypeInfo.STRING_TYPE_INFO));
DataSet<Tuple1<String>> source2 = env.readCsvFile("/some/otherpath").types(String.class);
DataSink<Tuple2<Tuple1<String>, Tuple1<String>>> out = source1.filter(new NoFilter()).mapPartition(new IdPMap()).flatMap(new IdFlatMap()).map(new IdMap()).join(source2).where("*").equalTo("*").writeAsText("/some/newpath");
Plan plan = env.createProgramPlan();
// submit the plan to the compiler
OptimizedPlan oPlan = compileNoStats(plan);
// check the optimized Plan
// when join should have forward strategy on both sides
SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
DualInputPlanNode joinNode = (DualInputPlanNode) sinkNode.getPredecessor();
ShipStrategyType joinIn1 = joinNode.getInput1().getShipStrategy();
ShipStrategyType joinIn2 = joinNode.getInput2().getShipStrategy();
Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn1);
Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, joinIn2);
}
use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.
the class SemanticPropertiesAPIToPlanTest method forwardFieldsTestJoin.
@Test
public void forwardFieldsTestJoin() {
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Tuple3<Integer, Integer, Integer>> in1 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
DataSet<Tuple3<Integer, Integer, Integer>> in2 = env.readCsvFile(IN_FILE).types(Integer.class, Integer.class, Integer.class);
in1 = in1.map(new MockMapper()).withForwardedFields("*").groupBy(0).reduce(new MockReducer()).withForwardedFields("f0->f1");
in2 = in2.map(new MockMapper()).withForwardedFields("*").groupBy(1).reduce(new MockReducer()).withForwardedFields("f1->f2");
DataSet<Tuple3<Integer, Integer, Integer>> out = in1.join(in2).where(1).equalTo(2).with(new MockJoin());
out.output(new DiscardingOutputFormat<Tuple3<Integer, Integer, Integer>>());
Plan plan = env.createProgramPlan();
OptimizedPlan oPlan = compileWithStats(plan);
oPlan.accept(new Visitor<PlanNode>() {
@Override
public boolean preVisit(PlanNode visitable) {
if (visitable instanceof DualInputPlanNode && visitable.getProgramOperator() instanceof InnerJoinOperatorBase) {
DualInputPlanNode node = ((DualInputPlanNode) visitable);
final Channel inConn1 = node.getInput1();
final Channel inConn2 = node.getInput2();
Assert.assertTrue("Join should just forward the input if it is already partitioned", inConn1.getShipStrategy() == ShipStrategyType.FORWARD);
Assert.assertTrue("Join should just forward the input if it is already partitioned", inConn2.getShipStrategy() == ShipStrategyType.FORWARD);
return false;
}
return true;
}
@Override
public void postVisit(PlanNode visitable) {
}
});
}
use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.
the class BinaryCustomPartitioningCompatibilityTest method testCompatiblePartitioningJoin.
@Test
public void testCompatiblePartitioningJoin() {
try {
final Partitioner<Long> partitioner = new Partitioner<Long>() {
@Override
public int partition(Long key, int numPartitions) {
return 0;
}
};
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Tuple2<Long, Long>> input1 = env.fromElements(new Tuple2<Long, Long>(0L, 0L));
DataSet<Tuple3<Long, Long, Long>> input2 = env.fromElements(new Tuple3<Long, Long, Long>(0L, 0L, 0L));
input1.partitionCustom(partitioner, 1).join(input2.partitionCustom(partitioner, 0)).where(1).equalTo(0).output(new DiscardingOutputFormat<Tuple2<Tuple2<Long, Long>, Tuple3<Long, Long, Long>>>());
Plan p = env.createProgramPlan();
OptimizedPlan op = compileNoStats(p);
SinkPlanNode sink = op.getDataSinks().iterator().next();
DualInputPlanNode join = (DualInputPlanNode) sink.getInput().getSource();
SingleInputPlanNode partitioner1 = (SingleInputPlanNode) join.getInput1().getSource();
SingleInputPlanNode partitioner2 = (SingleInputPlanNode) join.getInput2().getSource();
assertEquals(ShipStrategyType.FORWARD, join.getInput1().getShipStrategy());
assertEquals(ShipStrategyType.FORWARD, join.getInput2().getShipStrategy());
assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitioner1.getInput().getShipStrategy());
assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitioner2.getInput().getShipStrategy());
assertEquals(partitioner, partitioner1.getInput().getPartitioner());
assertEquals(partitioner, partitioner2.getInput().getPartitioner());
new JobGraphGenerator().compileJobGraph(op);
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
}
use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.
the class BinaryCustomPartitioningCompatibilityTest method testCompatiblePartitioningCoGroup.
@Test
public void testCompatiblePartitioningCoGroup() {
try {
final Partitioner<Long> partitioner = new Partitioner<Long>() {
@Override
public int partition(Long key, int numPartitions) {
return 0;
}
};
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Tuple2<Long, Long>> input1 = env.fromElements(new Tuple2<Long, Long>(0L, 0L));
DataSet<Tuple3<Long, Long, Long>> input2 = env.fromElements(new Tuple3<Long, Long, Long>(0L, 0L, 0L));
input1.partitionCustom(partitioner, 1).coGroup(input2.partitionCustom(partitioner, 0)).where(1).equalTo(0).with(new DummyCoGroupFunction<Tuple2<Long, Long>, Tuple3<Long, Long, Long>>()).output(new DiscardingOutputFormat<Tuple2<Tuple2<Long, Long>, Tuple3<Long, Long, Long>>>());
Plan p = env.createProgramPlan();
OptimizedPlan op = compileNoStats(p);
SinkPlanNode sink = op.getDataSinks().iterator().next();
DualInputPlanNode coGroup = (DualInputPlanNode) sink.getInput().getSource();
SingleInputPlanNode partitioner1 = (SingleInputPlanNode) coGroup.getInput1().getSource();
SingleInputPlanNode partitioner2 = (SingleInputPlanNode) coGroup.getInput2().getSource();
assertEquals(ShipStrategyType.FORWARD, coGroup.getInput1().getShipStrategy());
assertEquals(ShipStrategyType.FORWARD, coGroup.getInput2().getShipStrategy());
assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitioner1.getInput().getShipStrategy());
assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitioner2.getInput().getShipStrategy());
assertEquals(partitioner, partitioner1.getInput().getPartitioner());
assertEquals(partitioner, partitioner2.getInput().getPartitioner());
new JobGraphGenerator().compileJobGraph(op);
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
}
use of org.apache.flink.optimizer.plan.DualInputPlanNode in project flink by apache.
the class CoGroupCustomPartitioningTest method testCoGroupWithKeySelectors.
@Test
public void testCoGroupWithKeySelectors() {
try {
final Partitioner<Integer> partitioner = new TestPartitionerInt();
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
DataSet<Pojo2> input1 = env.fromElements(new Pojo2());
DataSet<Pojo3> input2 = env.fromElements(new Pojo3());
input1.coGroup(input2).where(new Pojo2KeySelector()).equalTo(new Pojo3KeySelector()).withPartitioner(partitioner).with(new DummyCoGroupFunction<Pojo2, Pojo3>()).output(new DiscardingOutputFormat<Tuple2<Pojo2, Pojo3>>());
Plan p = env.createProgramPlan();
OptimizedPlan op = compileNoStats(p);
SinkPlanNode sink = op.getDataSinks().iterator().next();
DualInputPlanNode join = (DualInputPlanNode) sink.getInput().getSource();
assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput1().getShipStrategy());
assertEquals(ShipStrategyType.PARTITION_CUSTOM, join.getInput2().getShipStrategy());
assertEquals(partitioner, join.getInput1().getPartitioner());
assertEquals(partitioner, join.getInput2().getPartitioner());
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
}
Aggregations