Examples with MapTask com.google.api.services.dataflow.model.MapTask used on opensource projects

Example 16 with MapTask

use of com.google.api.services.dataflow.model.MapTask in project beam by apache.

the class MapTaskToNetworkFunctionTest method testParDo.

@Test
public void testParDo() {
    InstructionOutput readOutput = createInstructionOutput("Read.out");
    ParallelInstruction read = createParallelInstruction("Read", readOutput);
    read.setRead(new ReadInstruction());
    MultiOutputInfo parDoMultiOutput = createMultiOutputInfo("output");
    ParDoInstruction parDoInstruction = new ParDoInstruction();
    // Read.out
    parDoInstruction.setInput(createInstructionInput(0, 0));
    parDoInstruction.setMultiOutputInfos(ImmutableList.of(parDoMultiOutput));
    InstructionOutput parDoOutput = createInstructionOutput("ParDo.out");
    ParallelInstruction parDo = createParallelInstruction("ParDo", parDoOutput);
    parDo.setParDo(parDoInstruction);
    MapTask mapTask = new MapTask();
    mapTask.setInstructions(ImmutableList.of(read, parDo));
    mapTask.setFactory(Transport.getJsonFactory());
    Network<Node, Edge> network = new MapTaskToNetworkFunction(IdGenerators.decrementingLongs()).apply(mapTask);
    assertNetworkProperties(network);
    assertEquals(4, network.nodes().size());
    assertEquals(3, network.edges().size());
    ParallelInstructionNode readNode = get(network, read);
    InstructionOutputNode readOutputNode = getOnlySuccessor(network, readNode);
    assertEquals(readOutput, readOutputNode.getInstructionOutput());
    ParallelInstructionNode parDoNode = getOnlySuccessor(network, readOutputNode);
    InstructionOutputNode parDoOutputNode = getOnlySuccessor(network, parDoNode);
    assertEquals(parDoOutput, parDoOutputNode.getInstructionOutput());
    assertEquals(parDoMultiOutput, ((MultiOutputInfoEdge) Iterables.getOnlyElement(network.edgesConnecting(parDoNode, parDoOutputNode))).getMultiOutputInfo());
}

Example 17 with MapTask

use of com.google.api.services.dataflow.model.MapTask in project beam by apache.

the class MapTaskToNetworkFunctionTest method testFlatten.

@Test
public void testFlatten() {
    // ReadA --\
    // |--> Flatten
    // ReadB --/
    InstructionOutput readOutputA = createInstructionOutput("ReadA.out");
    ParallelInstruction readA = createParallelInstruction("ReadA", readOutputA);
    readA.setRead(new ReadInstruction());
    InstructionOutput readOutputB = createInstructionOutput("ReadB.out");
    ParallelInstruction readB = createParallelInstruction("ReadB", readOutputB);
    readB.setRead(new ReadInstruction());
    FlattenInstruction flattenInstruction = new FlattenInstruction();
    flattenInstruction.setInputs(ImmutableList.of(// ReadA.out
    createInstructionInput(0, 0), // ReadB.out
    createInstructionInput(1, 0)));
    InstructionOutput flattenOutput = createInstructionOutput("Flatten.out");
    ParallelInstruction flatten = createParallelInstruction("Flatten", flattenOutput);
    flatten.setFlatten(flattenInstruction);
    MapTask mapTask = new MapTask();
    mapTask.setInstructions(ImmutableList.of(readA, readB, flatten));
    mapTask.setFactory(Transport.getJsonFactory());
    Network<Node, Edge> network = new MapTaskToNetworkFunction(IdGenerators.decrementingLongs()).apply(mapTask);
    assertNetworkProperties(network);
    assertEquals(6, network.nodes().size());
    assertEquals(5, network.edges().size());
    ParallelInstructionNode readANode = get(network, readA);
    InstructionOutputNode readOutputANode = getOnlySuccessor(network, readANode);
    assertEquals(readOutputA, readOutputANode.getInstructionOutput());
    ParallelInstructionNode readBNode = get(network, readB);
    InstructionOutputNode readOutputBNode = getOnlySuccessor(network, readBNode);
    assertEquals(readOutputB, readOutputBNode.getInstructionOutput());
    // Make sure the successors for both ReadA and ReadB output PCollections are the same
    assertEquals(network.successors(readOutputANode), network.successors(readOutputBNode));
    ParallelInstructionNode flattenNode = getOnlySuccessor(network, readOutputANode);
    InstructionOutputNode flattenOutputNode = getOnlySuccessor(network, flattenNode);
    assertEquals(flattenOutput, flattenOutputNode.getInstructionOutput());
}

Example 18 with MapTask

use of com.google.api.services.dataflow.model.MapTask in project beam by apache.

the class MapTaskToNetworkFunctionTest method testPartialGroupByKey.

@Test
public void testPartialGroupByKey() {
    // Read --> PGBK --> Write
    InstructionOutput readOutput = createInstructionOutput("Read.out");
    ParallelInstruction read = createParallelInstruction("Read", readOutput);
    read.setRead(new ReadInstruction());
    PartialGroupByKeyInstruction pgbkInstruction = new PartialGroupByKeyInstruction();
    // Read.out
    pgbkInstruction.setInput(createInstructionInput(0, 0));
    InstructionOutput pgbkOutput = createInstructionOutput("PGBK.out");
    ParallelInstruction pgbk = createParallelInstruction("PGBK", pgbkOutput);
    pgbk.setPartialGroupByKey(pgbkInstruction);
    WriteInstruction writeInstruction = new WriteInstruction();
    // PGBK.out
    writeInstruction.setInput(createInstructionInput(1, 0));
    ParallelInstruction write = createParallelInstruction("Write");
    write.setWrite(writeInstruction);
    MapTask mapTask = new MapTask();
    mapTask.setInstructions(ImmutableList.of(read, pgbk, write));
    mapTask.setFactory(Transport.getJsonFactory());
    Network<Node, Edge> network = new MapTaskToNetworkFunction(IdGenerators.decrementingLongs()).apply(mapTask);
    assertNetworkProperties(network);
    assertEquals(5, network.nodes().size());
    assertEquals(4, network.edges().size());
    ParallelInstructionNode readNode = get(network, read);
    InstructionOutputNode readOutputNode = getOnlySuccessor(network, readNode);
    assertEquals(readOutput, readOutputNode.getInstructionOutput());
    ParallelInstructionNode pgbkNode = getOnlySuccessor(network, readOutputNode);
    InstructionOutputNode pgbkOutputNode = getOnlySuccessor(network, pgbkNode);
    assertEquals(pgbkOutput, pgbkOutputNode.getInstructionOutput());
    getOnlySuccessor(network, pgbkOutputNode);
    assertNotNull(write);
}

Example 19 with MapTask

use of com.google.api.services.dataflow.model.MapTask in project beam by apache.

the class MapTaskToNetworkFunctionTest method testWrite.

@Test
public void testWrite() {
    InstructionOutput readOutput = createInstructionOutput("Read.out");
    ParallelInstruction read = createParallelInstruction("Read", readOutput);
    read.setRead(new ReadInstruction());
    WriteInstruction writeInstruction = new WriteInstruction();
    // Read.out
    writeInstruction.setInput(createInstructionInput(0, 0));
    ParallelInstruction write = createParallelInstruction("Write");
    write.setWrite(writeInstruction);
    MapTask mapTask = new MapTask();
    mapTask.setInstructions(ImmutableList.of(read, write));
    mapTask.setFactory(Transport.getJsonFactory());
    Network<Node, Edge> network = new MapTaskToNetworkFunction(IdGenerators.decrementingLongs()).apply(mapTask);
    assertNetworkProperties(network);
    assertEquals(3, network.nodes().size());
    assertEquals(2, network.edges().size());
    ParallelInstructionNode readNode = get(network, read);
    InstructionOutputNode readOutputNode = getOnlySuccessor(network, readNode);
    assertEquals(readOutput, readOutputNode.getInstructionOutput());
    ParallelInstructionNode writeNode = getOnlySuccessor(network, readOutputNode);
    assertNotNull(writeNode);
}

Example 20 with MapTask

use of com.google.api.services.dataflow.model.MapTask in project beam by apache.

the class FixMultiOutputInfosOnParDoInstructionsTest method testExistingMultiOutputInfosAreUnmodified.

@Test
public void testExistingMultiOutputInfosAreUnmodified() {
    FixMultiOutputInfosOnParDoInstructions function = new FixMultiOutputInfosOnParDoInstructions(IdGenerators.decrementingLongs());
    MapTask output = function.apply(createMapTaskWithParDo(2, "5", "6"));
    assertEquals(createMapTaskWithParDo(2, "5", "6"), output);
}