org.apache.flink.optimizer.dataproperties.PartitioningProperty Java Examples

The following examples show how to use org.apache.flink.optimizer.dataproperties.PartitioningProperty. 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: GroupCombineProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED) {
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #2
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 #3
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 #4
Source File: AllGroupCombineProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #5
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource7() {

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

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

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

	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 #6
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 #7
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 #8
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 #9
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 #10
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 #11
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource2() {

	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, 0}, new Order[]{Order.ASCENDING, 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(1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue((new FieldSet(lprops.getGroupedFields().toArray())).equals(new FieldSet(1, 0)));
	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 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 #13
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 #14
Source File: CoGroupDescriptor.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties in1, GlobalProperties in2) {
	GlobalProperties gp = GlobalProperties.combine(in1, in2);
	if (gp.getUniqueFieldCombination() != null && gp.getUniqueFieldCombination().size() > 0 &&
				gp.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gp.setAnyPartitioning(gp.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gp.clearUniqueFieldCombinations();
	return gp;
}
Example #15
Source File: CoGroupDescriptor.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public boolean areCompatible(RequestedGlobalProperties requested1, RequestedGlobalProperties requested2,
		GlobalProperties produced1, GlobalProperties produced2)
{

	if(produced1.getPartitioning() == PartitioningProperty.HASH_PARTITIONED &&
			produced2.getPartitioning() == PartitioningProperty.HASH_PARTITIONED) {

		// both are hash partitioned, check that partitioning fields are equivalently chosen
		return checkEquivalentFieldPositionsInKeyFields(
				produced1.getPartitioningFields(), produced2.getPartitioningFields());

	}
	else if(produced1.getPartitioning() == PartitioningProperty.RANGE_PARTITIONED &&
			produced2.getPartitioning() == PartitioningProperty.RANGE_PARTITIONED &&
			produced1.getDataDistribution() != null && produced2.getDataDistribution() != null) {

		return produced1.getPartitioningFields().size() == produced2.getPartitioningFields().size() &&
				checkSameOrdering(produced1, produced2, produced1.getPartitioningFields().size()) &&
				produced1.getDataDistribution().equals(produced2.getDataDistribution());
		
	}
	else if(produced1.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING &&
			produced2.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING) {

		// both use a custom partitioner. Check that both keys are exactly as specified and that both the same partitioner
		return produced1.getPartitioningFields().isExactMatch(this.keys1) &&
				produced2.getPartitioningFields().isExactMatch(this.keys2) &&
				produced1.getCustomPartitioner() != null && produced2.getCustomPartitioner() != null &&
				produced1.getCustomPartitioner().equals(produced2.getCustomPartitioner());

	}
	else {

		// no other partitioning valid, incl. ANY_PARTITIONING.
		//   For co-groups we must ensure that both sides are exactly identically partitioned, ANY is not good enough.
		return false;
	}

}
Example #16
Source File: PropertyDataSourceTest.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource3() {

	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)
			.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(0)));
	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 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 #18
Source File: AllGroupWithPartialPreGroupProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #19
Source File: FlatMapDescriptor.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #20
Source File: ReduceProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #21
Source File: PropertyDataSourceTest.java    From flink 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 #22
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 #23
Source File: GroupReduceWithCombineProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #24
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 #25
Source File: GroupReduceProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #26
Source File: PropertyDataSourceTest.java    From Flink-CEPplus 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 #27
Source File: PropertyDataSourceTest.java    From Flink-CEPplus 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 #28
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 #29
Source File: AllGroupCombineProperties.java    From flink with Apache License 2.0 5 votes vote down vote up 
@Override
public GlobalProperties computeGlobalProperties(GlobalProperties gProps) {
	if (gProps.getUniqueFieldCombination() != null && gProps.getUniqueFieldCombination().size() > 0 &&
			gProps.getPartitioning() == PartitioningProperty.RANDOM_PARTITIONED)
	{
		gProps.setAnyPartitioning(gProps.getUniqueFieldCombination().iterator().next().toFieldList());
	}
	gProps.clearUniqueFieldCombinations();
	return gProps;
}
Example #30
Source File: PropertyDataSourceTest.java    From Flink-CEPplus with Apache License 2.0 5 votes vote down vote up 
@Test
public void checkSinglePartitionedOrderedSource2() {

	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, 0}, new Order[]{Order.ASCENDING, 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(1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue((new FieldSet(lprops.getGroupedFields().toArray())).equals(new FieldSet(1, 0)));
	Assert.assertTrue(lprops.getOrdering() == null);

}