use of com.google.api.services.dataflow.model.WriteInstruction in project beam by apache.
the class BeamFnMapTaskExecutorFactory method createWriteOperation.
OperationNode createWriteOperation(ParallelInstructionNode node, PipelineOptions options, SinkFactory sinkFactory, DataflowExecutionContext executionContext, DataflowOperationContext context) throws Exception {
ParallelInstruction instruction = node.getParallelInstruction();
WriteInstruction write = instruction.getWrite();
Coder<?> coder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(write.getSink().getCodec()));
CloudObject cloudSink = CloudObject.fromSpec(write.getSink().getSpec());
Sink<?> sink = sinkFactory.create(cloudSink, coder, options, executionContext, context);
return OperationNode.create(WriteOperation.create(sink, EMPTY_OUTPUT_RECEIVER_ARRAY, context));
}
use of com.google.api.services.dataflow.model.WriteInstruction in project beam by apache.
the class LengthPrefixUnknownCodersTest method testLengthPrefixWriteInstructionCoder.
@Test
public void testLengthPrefixWriteInstructionCoder() throws Exception {
WriteInstruction writeInstruction = new WriteInstruction();
writeInstruction.setSink(new Sink().setCodec(CloudObjects.asCloudObject(windowedValueCoder, /*sdkComponents=*/
null)));
instruction.setWrite(writeInstruction);
ParallelInstruction prefixedInstruction = forParallelInstruction(instruction, false);
assertEqualsAsJson(CloudObjects.asCloudObject(prefixedWindowedValueCoder, /*sdkComponents=*/
null), prefixedInstruction.getWrite().getSink().getCodec());
// Should not mutate the instruction.
assertEqualsAsJson(CloudObjects.asCloudObject(windowedValueCoder, /*sdkComponents=*/
null), writeInstruction.getSink().getCodec());
}
use of com.google.api.services.dataflow.model.WriteInstruction in project beam by apache.
the class IntrinsicMapTaskExecutorFactoryTest method createWriteInstruction.
static ParallelInstruction createWriteInstruction(int producerIndex, int producerOutputNum, String systemName) {
InstructionInput cloudInput = new InstructionInput();
cloudInput.setProducerInstructionIndex(producerIndex);
cloudInput.setOutputNum(producerOutputNum);
CloudObject spec = CloudObject.forClass(IntrinsicMapTaskExecutorFactoryTest.TestSinkFactory.class);
com.google.api.services.dataflow.model.Sink cloudSink = new com.google.api.services.dataflow.model.Sink();
cloudSink.setSpec(spec);
cloudSink.setCodec(windowedStringCoder);
WriteInstruction writeInstruction = new WriteInstruction();
writeInstruction.setInput(cloudInput);
writeInstruction.setSink(cloudSink);
ParallelInstruction instruction = new ParallelInstruction();
instruction.setWrite(writeInstruction);
instruction.setSystemName(systemName);
instruction.setOriginalName(systemName + "OriginalName");
return instruction;
}
use of com.google.api.services.dataflow.model.WriteInstruction in project beam by apache.
the class IntrinsicMapTaskExecutorFactory method createWriteOperation.
OperationNode createWriteOperation(ParallelInstructionNode node, PipelineOptions options, SinkFactory sinkFactory, DataflowExecutionContext executionContext, DataflowOperationContext context) throws Exception {
ParallelInstruction instruction = node.getParallelInstruction();
WriteInstruction write = instruction.getWrite();
Coder<?> coder = CloudObjects.coderFromCloudObject(CloudObject.fromSpec(write.getSink().getCodec()));
CloudObject cloudSink = CloudObject.fromSpec(write.getSink().getSpec());
Sink<?> sink = sinkFactory.create(cloudSink, coder, options, executionContext, context);
return OperationNode.create(WriteOperation.create(sink, EMPTY_OUTPUT_RECEIVER_ARRAY, context));
}
use of com.google.api.services.dataflow.model.WriteInstruction in project beam by apache.
the class MapTaskToNetworkFunctionTest method testMultipleOutput.
@Test
public void testMultipleOutput() {
// /---> WriteA
// Read ---> ParDo
// \---> WriteB
InstructionOutput readOutput = createInstructionOutput("Read.out");
ParallelInstruction read = createParallelInstruction("Read", readOutput);
read.setRead(new ReadInstruction());
MultiOutputInfo parDoMultiOutput1 = createMultiOutputInfo("output1");
MultiOutputInfo parDoMultiOutput2 = createMultiOutputInfo("output2");
ParDoInstruction parDoInstruction = new ParDoInstruction();
// Read.out
parDoInstruction.setInput(createInstructionInput(0, 0));
parDoInstruction.setMultiOutputInfos(ImmutableList.of(parDoMultiOutput1, parDoMultiOutput2));
InstructionOutput parDoOutput1 = createInstructionOutput("ParDo.out1");
InstructionOutput parDoOutput2 = createInstructionOutput("ParDo.out2");
ParallelInstruction parDo = createParallelInstruction("ParDo", parDoOutput1, parDoOutput2);
parDo.setParDo(parDoInstruction);
WriteInstruction writeAInstruction = new WriteInstruction();
// ParDo.out1
writeAInstruction.setInput(createInstructionInput(1, 0));
ParallelInstruction writeA = createParallelInstruction("WriteA");
writeA.setWrite(writeAInstruction);
WriteInstruction writeBInstruction = new WriteInstruction();
// ParDo.out2
writeBInstruction.setInput(createInstructionInput(1, 1));
ParallelInstruction writeB = createParallelInstruction("WriteB");
writeB.setWrite(writeBInstruction);
MapTask mapTask = new MapTask();
mapTask.setInstructions(ImmutableList.of(read, parDo, writeA, writeB));
mapTask.setFactory(Transport.getJsonFactory());
Network<Node, Edge> network = new MapTaskToNetworkFunction(IdGenerators.decrementingLongs()).apply(mapTask);
assertNetworkProperties(network);
assertEquals(7, network.nodes().size());
assertEquals(6, network.edges().size());
ParallelInstructionNode parDoNode = get(network, parDo);
ParallelInstructionNode writeANode = get(network, writeA);
ParallelInstructionNode writeBNode = get(network, writeB);
InstructionOutputNode parDoOutput1Node = getOnlyPredecessor(network, writeANode);
assertEquals(parDoOutput1, parDoOutput1Node.getInstructionOutput());
InstructionOutputNode parDoOutput2Node = getOnlyPredecessor(network, writeBNode);
assertEquals(parDoOutput2, parDoOutput2Node.getInstructionOutput());
assertThat(network.successors(parDoNode), Matchers.<Node>containsInAnyOrder(parDoOutput1Node, parDoOutput2Node));
assertEquals(parDoMultiOutput1, ((MultiOutputInfoEdge) Iterables.getOnlyElement(network.edgesConnecting(parDoNode, parDoOutput1Node))).getMultiOutputInfo());
assertEquals(parDoMultiOutput2, ((MultiOutputInfoEdge) Iterables.getOnlyElement(network.edgesConnecting(parDoNode, parDoOutput2Node))).getMultiOutputInfo());
}
Aggregations