Examples with ReplicatingInputFormat org.apache.flink.api.common.io.ReplicatingInputFormat used on opensource projects

Example 6 with ReplicatingInputFormat

use of org.apache.flink.api.common.io.ReplicatingInputFormat in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInput.

/**
 * Tests join program with replicated data source.
 */
@Test
public void checkJoinWithReplicatedSourceInput() {
    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.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);
}

Example 7 with ReplicatingInputFormat

use of org.apache.flink.api.common.io.ReplicatingInputFormat in project flink by apache.

the class ReplicatingDataSourceITCase method testReplicatedSourceToCross.

@Test
public void testReplicatedSourceToCross() throws Exception {
    /*
		 * Test replicated source going into cross
		 */
    final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple1<Long>> source1 = env.createInput(new ReplicatingInputFormat<Long, GenericInputSplit>(new ParallelIteratorInputFormat<Long>(new NumberSequenceIterator(0l, 1000l))), BasicTypeInfo.LONG_TYPE_INFO).map(new ToTuple());
    DataSet<Tuple1<Long>> source2 = env.generateSequence(0l, 1000l).map(new ToTuple());
    DataSet<Tuple1<Long>> pairs = source1.cross(source2).filter(new FilterFunction<Tuple2<Tuple1<Long>, Tuple1<Long>>>() {

        @Override
        public boolean filter(Tuple2<Tuple1<Long>, Tuple1<Long>> value) throws Exception {
            return value.f0.f0.equals(value.f1.f0);
        }
    }).map(new MapFunction<Tuple2<Tuple1<Long>, Tuple1<Long>>, Tuple1<Long>>() {

        @Override
        public Tuple1<Long> map(Tuple2<Tuple1<Long>, Tuple1<Long>> value) throws Exception {
            return value.f0;
        }
    }).sum(0);
    List<Tuple1<Long>> result = pairs.collect();
    String expectedResult = "(500500)";
    compareResultAsText(result, expectedResult);
}

Example 8 with ReplicatingInputFormat

use of org.apache.flink.api.common.io.ReplicatingInputFormat in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindRebalance.

/**
 * Tests compiler fail for join program with replicated data source behind rebalance.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputBehindRebalance() {
    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.rebalance().join(source2).where("*").equalTo("*").writeAsText("/some/newpath");
    Plan plan = env.createProgramPlan();
    // submit the plan to the compiler
    OptimizedPlan oPlan = compileNoStats(plan);
}

Example 9 with ReplicatingInputFormat

use of org.apache.flink.api.common.io.ReplicatingInputFormat in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindMap.

/**
 * Tests join program with replicated data source behind map.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindMap() {
    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.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);
}

Example 10 with ReplicatingInputFormat

use of org.apache.flink.api.common.io.ReplicatingInputFormat in project flink by apache.

the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindMapChangingparallelism.

/**
 * Tests compiler fail for join program with replicated data source behind map and changing
 * parallelism.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputBehindMapChangingparallelism() {
    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.map(new IdMap()).setParallelism(DEFAULT_PARALLELISM + 1).join(source2).where("*").equalTo("*").writeAsText("/some/newpath");
    Plan plan = env.createProgramPlan();
    // submit the plan to the compiler
    OptimizedPlan oPlan = compileNoStats(plan);
}