org.apache.flink.optimizer.plan.SourcePlanNode Java Examples

The following examples show how to use org.apache.flink.optimizer.plan.SourcePlanNode. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: JobGraphGenerator.java    From flink with Apache License 2.0 6 votes vote down vote up 
private JobVertex createDataSourceVertex(SourcePlanNode node) throws CompilerException {
	final InputOutputFormatVertex vertex = new InputOutputFormatVertex(node.getNodeName());
	final TaskConfig config = new TaskConfig(vertex.getConfiguration());

	final OperatorID operatorID = new OperatorID();

	vertex.setResources(node.getMinResources(), node.getPreferredResources());
	vertex.setInvokableClass(DataSourceTask.class);
	vertex.setFormatDescription(operatorID, getDescriptionForUserCode(node.getProgramOperator().getUserCodeWrapper()));

	// set user code
	new InputOutputFormatContainer(Thread.currentThread().getContextClassLoader())
		.addInputFormat(operatorID, (UserCodeWrapper<? extends InputFormat<?, ?>>) node.getProgramOperator().getUserCodeWrapper())
		.addParameters(operatorID, node.getProgramOperator().getParameters())
		.write(config);

	config.setOutputSerializer(node.getSerializer());
	return vertex;
}
Example #2
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource4() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0, 1)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.DESCENDING});

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #3
Source File: PartitionOperatorTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void testRangePartitionOperatorPreservesFields() {
	try {
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		DataSet<Tuple2<Long, Long>> data = env.fromCollection(Collections.singleton(new Tuple2<>(0L, 0L)));

		data.partitionByRange(1)
			.groupBy(1)
			.reduceGroup(new IdentityGroupReducerCombinable<Tuple2<Long,Long>>())
			.output(new DiscardingOutputFormat<Tuple2<Long, Long>>());

		Plan p = env.createProgramPlan();
		OptimizedPlan op = compileNoStats(p);

		SinkPlanNode sink = op.getDataSinks().iterator().next();
		SingleInputPlanNode reducer = (SingleInputPlanNode) sink.getInput().getSource();
		SingleInputPlanNode partitionNode = (SingleInputPlanNode)reducer.getInput().getSource();
		SingleInputPlanNode partitionIDRemover = (SingleInputPlanNode) partitionNode.getInput().getSource();

		assertEquals(ShipStrategyType.FORWARD, reducer.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, partitionNode.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitionIDRemover.getInput().getShipStrategy());

		SourcePlanNode sourcePlanNode = op.getDataSources().iterator().next();
		List<Channel> sourceOutgoingChannels = sourcePlanNode.getOutgoingChannels();
		assertEquals(2, sourceOutgoingChannels.size());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(0).getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(1).getShipStrategy());
		assertEquals(DataExchangeMode.PIPELINED, sourceOutgoingChannels.get(0).getDataExchangeMode());
		assertEquals(DataExchangeMode.BATCH, sourceOutgoingChannels.get(1).getDataExchangeMode());
	}
	catch (Exception e) {
		e.printStackTrace();
		fail(e.getMessage());
	}
}
Example #4
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource8() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1")
			.splitsGroupedBy("f1.stringField");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #5
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource4() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0, 1)
			.splitsGroupedBy(0);

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #6
Source File: PlanFinalizer.java    From flink with Apache License 2.0 5 votes vote down vote up 
/**
 * Creates a new plan finalizer.
 */
public PlanFinalizer() {
	this.allNodes = new HashSet<PlanNode>();
	this.sources = new ArrayList<SourcePlanNode>();
	this.sinks = new ArrayList<SinkPlanNode>();
	this.stackOfIterationNodes = new ArrayDeque<IterationPlanNode>();
}
Example #7
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource5() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
		.splitsPartitionedBy("f1.intField")
		.splitsOrderedBy("f0; f1.intField", new Order[]{Order.ASCENDING, Order.DESCENDING});

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(0,2)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #8
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedSource1() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0);

	data.output(new DiscardingOutputFormat<Tuple2<Long,String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #9
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource1() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0)
			.splitsGroupedBy(0);

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(0)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #10
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedSource7() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy("byDate", 1, 0);

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING);
	Assert.assertTrue(gprops.getCustomPartitioner() != null);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #11
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource2() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0)
			.splitsGroupedBy(1, 0);

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(0, 1)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #12
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource1() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(1)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.ASCENDING});

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue((new FieldSet(lprops.getGroupedFields().toArray())).equals(new FieldSet(1)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #13
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource5() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f2")
			.splitsGroupedBy("f2");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(4)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(4)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #14
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource6() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1.intField")
			.splitsGroupedBy("f0; f1.intField");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(0,2)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #15
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource7() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1.intField")
			.splitsGroupedBy("f1");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #16
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource8() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1")
			.splitsGroupedBy("f1.stringField");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #17
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource1() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(1)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.ASCENDING});

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue((new FieldSet(lprops.getGroupedFields().toArray())).equals(new FieldSet(1)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #18
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource7() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1.intField")
			.splitsGroupedBy("f1");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #19
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource4() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0, 1)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.DESCENDING});

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #20
Source File: FeedbackPropertiesMatchTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testNoPartialSolutionFoundTwoInputOperator() {
	try {
		SourcePlanNode target = new SourcePlanNode(getSourceNode(), "Partial Solution");

		SourcePlanNode source1 = new SourcePlanNode(getSourceNode(), "Source 1");
		SourcePlanNode source2 = new SourcePlanNode(getSourceNode(), "Source 2");
		
		Channel toMap1 = new Channel(source1);
		toMap1.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toMap1.setLocalStrategy(LocalStrategy.NONE);
		SingleInputPlanNode map1 = new SingleInputPlanNode(getMapNode(), "Mapper 1", toMap1, DriverStrategy.MAP);
		
		Channel toMap2 = new Channel(source2);
		toMap2.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toMap2.setLocalStrategy(LocalStrategy.NONE);
		SingleInputPlanNode map2 = new SingleInputPlanNode(getMapNode(), "Mapper 2", toMap2, DriverStrategy.MAP);
		
		Channel toJoin1 = new Channel(map1);
		Channel toJoin2 = new Channel(map2);
		
		toJoin1.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toJoin1.setLocalStrategy(LocalStrategy.NONE);
		toJoin2.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toJoin2.setLocalStrategy(LocalStrategy.NONE);
		
		DualInputPlanNode join = new DualInputPlanNode(getJoinNode(), "Join", toJoin1, toJoin2, DriverStrategy.HYBRIDHASH_BUILD_FIRST);
		
		FeedbackPropertiesMeetRequirementsReport report = join.checkPartialSolutionPropertiesMet(target, new GlobalProperties(), new LocalProperties());
		assertEquals(NO_PARTIAL_SOLUTION, report);
	}
	catch (Exception e) {
		e.printStackTrace();
		fail(e.getMessage());
	}
}
Example #21
Source File: JavaApiPostPass.java    From flink with Apache License 2.0 5 votes vote down vote up 
@SuppressWarnings("unchecked")
private static <T> TypeInformation<T> getTypeInfoFromSource(SourcePlanNode node) {
	Operator<?> op = node.getOptimizerNode().getOperator();
	
	if (op instanceof GenericDataSourceBase) {
		return ((GenericDataSourceBase<T, ?>) op).getOperatorInfo().getOutputType();
	} else {
		throw new RuntimeException("Wrong operator type found in post pass.");
	}
}
Example #22
Source File: PlanFinalizer.java    From flink with Apache License 2.0 5 votes vote down vote up 
/**
 * Creates a new plan finalizer.
 */
public PlanFinalizer() {
	this.allNodes = new HashSet<PlanNode>();
	this.sources = new ArrayList<SourcePlanNode>();
	this.sinks = new ArrayList<SinkPlanNode>();
	this.stackOfIterationNodes = new ArrayDeque<IterationPlanNode>();
}
Example #23
Source File: PartitionOperatorTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testRangePartitionOperatorPreservesFields() {
	try {
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		DataSet<Tuple2<Long, Long>> data = env.fromCollection(Collections.singleton(new Tuple2<>(0L, 0L)));

		data.partitionByRange(1)
			.groupBy(1)
			.reduceGroup(new IdentityGroupReducerCombinable<Tuple2<Long,Long>>())
			.output(new DiscardingOutputFormat<Tuple2<Long, Long>>());

		Plan p = env.createProgramPlan();
		OptimizedPlan op = compileNoStats(p);

		SinkPlanNode sink = op.getDataSinks().iterator().next();
		SingleInputPlanNode reducer = (SingleInputPlanNode) sink.getInput().getSource();
		SingleInputPlanNode partitionNode = (SingleInputPlanNode)reducer.getInput().getSource();
		SingleInputPlanNode partitionIDRemover = (SingleInputPlanNode) partitionNode.getInput().getSource();

		assertEquals(ShipStrategyType.FORWARD, reducer.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, partitionNode.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitionIDRemover.getInput().getShipStrategy());

		SourcePlanNode sourcePlanNode = op.getDataSources().iterator().next();
		List<Channel> sourceOutgoingChannels = sourcePlanNode.getOutgoingChannels();
		assertEquals(2, sourceOutgoingChannels.size());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(0).getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(1).getShipStrategy());
		assertEquals(DataExchangeMode.PIPELINED, sourceOutgoingChannels.get(0).getDataExchangeMode());
		assertEquals(DataExchangeMode.BATCH, sourceOutgoingChannels.get(1).getDataExchangeMode());
	}
	catch (Exception e) {
		e.printStackTrace();
		fail(e.getMessage());
	}
}
Example #24
Source File: PartitionOperatorTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testRangePartitionOperatorPreservesFields() {
	try {
		ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

		DataSet<Tuple2<Long, Long>> data = env.fromCollection(Collections.singleton(new Tuple2<>(0L, 0L)));

		data.partitionByRange(1)
			.groupBy(1)
			.reduceGroup(new IdentityGroupReducerCombinable<Tuple2<Long,Long>>())
			.output(new DiscardingOutputFormat<Tuple2<Long, Long>>());

		Plan p = env.createProgramPlan();
		OptimizedPlan op = compileNoStats(p);

		SinkPlanNode sink = op.getDataSinks().iterator().next();
		SingleInputPlanNode reducer = (SingleInputPlanNode) sink.getInput().getSource();
		SingleInputPlanNode partitionNode = (SingleInputPlanNode)reducer.getInput().getSource();
		SingleInputPlanNode partitionIDRemover = (SingleInputPlanNode) partitionNode.getInput().getSource();

		assertEquals(ShipStrategyType.FORWARD, reducer.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, partitionNode.getInput().getShipStrategy());
		assertEquals(ShipStrategyType.PARTITION_CUSTOM, partitionIDRemover.getInput().getShipStrategy());

		SourcePlanNode sourcePlanNode = op.getDataSources().iterator().next();
		List<Channel> sourceOutgoingChannels = sourcePlanNode.getOutgoingChannels();
		assertEquals(2, sourceOutgoingChannels.size());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(0).getShipStrategy());
		assertEquals(ShipStrategyType.FORWARD, sourceOutgoingChannels.get(1).getShipStrategy());
		assertEquals(DataExchangeMode.PIPELINED, sourceOutgoingChannels.get(0).getDataExchangeMode());
		assertEquals(DataExchangeMode.BATCH, sourceOutgoingChannels.get(1).getDataExchangeMode());
	}
	catch (Exception e) {
		e.printStackTrace();
		fail(e.getMessage());
	}
}
Example #25
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource5() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f2")
			.splitsGroupedBy("f2");

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(4)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(4)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #26
Source File: JavaApiPostPass.java    From flink with Apache License 2.0 5 votes vote down vote up 
@SuppressWarnings("unchecked")
private static <T> TypeInformation<T> getTypeInfoFromSource(SourcePlanNode node) {
	Operator<?> op = node.getOptimizerNode().getOperator();
	
	if (op instanceof GenericDataSourceBase) {
		return ((GenericDataSourceBase<T, ?>) op).getOperatorInfo().getOutputType();
	} else {
		throw new RuntimeException("Wrong operator type found in post pass.");
	}
}
Example #27
Source File: FeedbackPropertiesMatchTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void testNoPartialSolutionFoundTwoInputOperator() {
	try {
		SourcePlanNode target = new SourcePlanNode(getSourceNode(), "Partial Solution");

		SourcePlanNode source1 = new SourcePlanNode(getSourceNode(), "Source 1");
		SourcePlanNode source2 = new SourcePlanNode(getSourceNode(), "Source 2");
		
		Channel toMap1 = new Channel(source1);
		toMap1.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toMap1.setLocalStrategy(LocalStrategy.NONE);
		SingleInputPlanNode map1 = new SingleInputPlanNode(getMapNode(), "Mapper 1", toMap1, DriverStrategy.MAP);
		
		Channel toMap2 = new Channel(source2);
		toMap2.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toMap2.setLocalStrategy(LocalStrategy.NONE);
		SingleInputPlanNode map2 = new SingleInputPlanNode(getMapNode(), "Mapper 2", toMap2, DriverStrategy.MAP);
		
		Channel toJoin1 = new Channel(map1);
		Channel toJoin2 = new Channel(map2);
		
		toJoin1.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toJoin1.setLocalStrategy(LocalStrategy.NONE);
		toJoin2.setShipStrategy(ShipStrategyType.FORWARD, DataExchangeMode.PIPELINED);
		toJoin2.setLocalStrategy(LocalStrategy.NONE);
		
		DualInputPlanNode join = new DualInputPlanNode(getJoinNode(), "Join", toJoin1, toJoin2, DriverStrategy.HYBRIDHASH_BUILD_FIRST);
		
		FeedbackPropertiesMeetRequirementsReport report = join.checkPartialSolutionPropertiesMet(target, new GlobalProperties(), new LocalProperties());
		assertEquals(NO_PARTIAL_SOLUTION, report);
	}
	catch (Exception e) {
		e.printStackTrace();
		fail(e.getMessage());
	}
}
Example #28
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource6() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1.intField")
			.splitsOrderedBy("f1", new Order[]{Order.DESCENDING});

	data.output(new DiscardingOutputFormat<Tuple3<Long, SomePojo, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #29
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedSource2() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(1, 0);

	data.output(new DiscardingOutputFormat<Tuple2<Long,String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
Example #30
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedGroupedSource1() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple2<Long, String>> data =
			env.readCsvFile("/some/path").types(Long.class, String.class);

	data.getSplitDataProperties()
			.splitsPartitionedBy(0)
			.splitsGroupedBy(0);

	data.output(new DiscardingOutputFormat<Tuple2<Long, String>>());

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	SourcePlanNode sourceNode = (SourcePlanNode) sinkNode.getPredecessor();

	GlobalProperties gprops = sourceNode.getGlobalProperties();
	LocalProperties lprops = sourceNode.getLocalProperties();

	Assert.assertTrue((new FieldSet(gprops.getPartitioningFields().toArray())).equals(new FieldSet(0)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(0)));
	Assert.assertTrue(lprops.getOrdering() == null);

}