Search in sources :

Example 51 with OptimizedPlan

use of org.apache.flink.optimizer.plan.OptimizedPlan in project flink by apache.

the class PropertyDataSourceTest method checkSinglePartitionedOrderedSource4.

@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);
}
Also used : ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) FieldSet(org.apache.flink.api.common.operators.util.FieldSet) GlobalProperties(org.apache.flink.optimizer.dataproperties.GlobalProperties) Tuple2(org.apache.flink.api.java.tuple.Tuple2) SinkPlanNode(org.apache.flink.optimizer.plan.SinkPlanNode) SourcePlanNode(org.apache.flink.optimizer.plan.SourcePlanNode) Plan(org.apache.flink.api.common.Plan) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) LocalProperties(org.apache.flink.optimizer.dataproperties.LocalProperties) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) Test(org.junit.Test)

Example 52 with OptimizedPlan

use of org.apache.flink.optimizer.plan.OptimizedPlan in project flink by apache.

the class PropertyDataSourceTest method checkSinglePartitionedGroupedSource2.

@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);
}
Also used : ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) FieldSet(org.apache.flink.api.common.operators.util.FieldSet) GlobalProperties(org.apache.flink.optimizer.dataproperties.GlobalProperties) Tuple2(org.apache.flink.api.java.tuple.Tuple2) SinkPlanNode(org.apache.flink.optimizer.plan.SinkPlanNode) SourcePlanNode(org.apache.flink.optimizer.plan.SourcePlanNode) Plan(org.apache.flink.api.common.Plan) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) LocalProperties(org.apache.flink.optimizer.dataproperties.LocalProperties) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) Test(org.junit.Test)

Example 53 with OptimizedPlan

use of org.apache.flink.optimizer.plan.OptimizedPlan in project flink by apache.

the class PropertyDataSourceTest method checkSinglePartitionedSource3.

@Test
public void checkSinglePartitionedSource3() {
    ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
    env.setParallelism(DEFAULT_PARALLELISM);
    DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);
    data.getSplitDataProperties().splitsPartitionedBy("*");
    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(0, 1, 2, 3, 4)));
    Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
    Assert.assertTrue(lprops.getGroupedFields() == null);
    Assert.assertTrue(lprops.getOrdering() == null);
}
Also used : ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) FieldSet(org.apache.flink.api.common.operators.util.FieldSet) GlobalProperties(org.apache.flink.optimizer.dataproperties.GlobalProperties) Tuple3(org.apache.flink.api.java.tuple.Tuple3) SinkPlanNode(org.apache.flink.optimizer.plan.SinkPlanNode) SourcePlanNode(org.apache.flink.optimizer.plan.SourcePlanNode) Plan(org.apache.flink.api.common.Plan) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) LocalProperties(org.apache.flink.optimizer.dataproperties.LocalProperties) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) Test(org.junit.Test)

Example 54 with OptimizedPlan

use of org.apache.flink.optimizer.plan.OptimizedPlan in project flink by apache.

the class PropertyDataSourceTest method checkCoPartitionedSources2.

@Test
public void checkCoPartitionedSources2() {
    ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
    env.setParallelism(DEFAULT_PARALLELISM);
    DataSource<Tuple2<Long, String>> data1 = env.readCsvFile("/some/path").types(Long.class, String.class);
    data1.getSplitDataProperties().splitsPartitionedBy("byCountry", 0);
    DataSource<Tuple2<Long, String>> data2 = env.readCsvFile("/some/path").types(Long.class, String.class);
    data2.getSplitDataProperties().splitsPartitionedBy("byDate", 0);
    data1.union(data2).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 sourceNode1 = (SourcePlanNode) ((NAryUnionPlanNode) sinkNode.getPredecessor()).getListOfInputs().get(0).getSource();
    SourcePlanNode sourceNode2 = (SourcePlanNode) ((NAryUnionPlanNode) sinkNode.getPredecessor()).getListOfInputs().get(1).getSource();
    GlobalProperties gprops1 = sourceNode1.getGlobalProperties();
    LocalProperties lprops1 = sourceNode1.getLocalProperties();
    GlobalProperties gprops2 = sourceNode2.getGlobalProperties();
    LocalProperties lprops2 = sourceNode2.getLocalProperties();
    Assert.assertTrue((new FieldSet(gprops1.getPartitioningFields().toArray())).equals(new FieldSet(0)));
    Assert.assertTrue(gprops1.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING);
    Assert.assertTrue(lprops1.getGroupedFields() == null);
    Assert.assertTrue(lprops1.getOrdering() == null);
    Assert.assertTrue((new FieldSet(gprops2.getPartitioningFields().toArray())).equals(new FieldSet(0)));
    Assert.assertTrue(gprops2.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING);
    Assert.assertTrue(lprops2.getGroupedFields() == null);
    Assert.assertTrue(lprops2.getOrdering() == null);
    Assert.assertTrue(!gprops1.getCustomPartitioner().equals(gprops2.getCustomPartitioner()));
}
Also used : ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) FieldSet(org.apache.flink.api.common.operators.util.FieldSet) GlobalProperties(org.apache.flink.optimizer.dataproperties.GlobalProperties) Tuple2(org.apache.flink.api.java.tuple.Tuple2) SinkPlanNode(org.apache.flink.optimizer.plan.SinkPlanNode) SourcePlanNode(org.apache.flink.optimizer.plan.SourcePlanNode) Plan(org.apache.flink.api.common.Plan) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) LocalProperties(org.apache.flink.optimizer.dataproperties.LocalProperties) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) Test(org.junit.Test)

Example 55 with OptimizedPlan

use of org.apache.flink.optimizer.plan.OptimizedPlan in project flink by apache.

the class PropertyDataSourceTest method checkSinglePartitionedGroupedSource3.

@Test
public void checkSinglePartitionedGroupedSource3() {
    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).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(1)));
    Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
    Assert.assertTrue(lprops.getGroupedFields() == null);
    Assert.assertTrue(lprops.getOrdering() == null);
}
Also used : ExecutionEnvironment(org.apache.flink.api.java.ExecutionEnvironment) FieldSet(org.apache.flink.api.common.operators.util.FieldSet) GlobalProperties(org.apache.flink.optimizer.dataproperties.GlobalProperties) Tuple2(org.apache.flink.api.java.tuple.Tuple2) SinkPlanNode(org.apache.flink.optimizer.plan.SinkPlanNode) SourcePlanNode(org.apache.flink.optimizer.plan.SourcePlanNode) Plan(org.apache.flink.api.common.Plan) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) LocalProperties(org.apache.flink.optimizer.dataproperties.LocalProperties) OptimizedPlan(org.apache.flink.optimizer.plan.OptimizedPlan) Test(org.junit.Test)

Aggregations

OptimizedPlan (org.apache.flink.optimizer.plan.OptimizedPlan)221 Test (org.junit.Test)197 Plan (org.apache.flink.api.common.Plan)192 ExecutionEnvironment (org.apache.flink.api.java.ExecutionEnvironment)183 SinkPlanNode (org.apache.flink.optimizer.plan.SinkPlanNode)146 Tuple2 (org.apache.flink.api.java.tuple.Tuple2)91 SingleInputPlanNode (org.apache.flink.optimizer.plan.SingleInputPlanNode)83 DualInputPlanNode (org.apache.flink.optimizer.plan.DualInputPlanNode)82 JobGraphGenerator (org.apache.flink.optimizer.plantranslate.JobGraphGenerator)55 Tuple3 (org.apache.flink.api.java.tuple.Tuple3)54 SourcePlanNode (org.apache.flink.optimizer.plan.SourcePlanNode)48 DiscardingOutputFormat (org.apache.flink.api.java.io.DiscardingOutputFormat)33 InvalidProgramException (org.apache.flink.api.common.InvalidProgramException)27 FieldList (org.apache.flink.api.common.operators.util.FieldList)27 Channel (org.apache.flink.optimizer.plan.Channel)26 FieldSet (org.apache.flink.api.common.operators.util.FieldSet)25 GlobalProperties (org.apache.flink.optimizer.dataproperties.GlobalProperties)25 LocalProperties (org.apache.flink.optimizer.dataproperties.LocalProperties)25 IdentityMapper (org.apache.flink.optimizer.testfunctions.IdentityMapper)20 WorksetIterationPlanNode (org.apache.flink.optimizer.plan.WorksetIterationPlanNode)16