org.apache.flink.api.java.operators.DataSink Java Examples

/**
 * Tests compiler fail for join program with replicated data source behind reduce.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputBehindReduce() {
	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
			.reduce(new LastReduce())
			.join(source2).where("*").equalTo("*")
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

@Override
public DataSink<?> consumeDataSet(DataSet<Row> dataSet) {
	MapOperator<Row, String> csvRows =
		dataSet.map(new CsvFormatter(fieldDelim == null ? "," : fieldDelim));

	DataSink<String> sink;
	if (writeMode != null) {
		sink = csvRows.writeAsText(path, writeMode);
	} else {
		sink = csvRows.writeAsText(path);
	}

	if (numFiles > 0) {
		csvRows.setParallelism(numFiles);
		sink.setParallelism(numFiles);
	}

	return sink.name(TableConnectorUtils.generateRuntimeName(CsvTableSink.class, fieldNames));
}
 

/**
 * Tests compiler fail for join program with replicated data source and changing parallelism.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputChangingparallelism() {

	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("*").setParallelism(DEFAULT_PARALLELISM+2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

/**
 * 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);
}
 

/**
 * Tests compiler fail for join program with replicated data source and changing parallelism.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputChangingparallelism() {

	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("*").setParallelism(DEFAULT_PARALLELISM+2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

/**
 * 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);

}
 

/**
 * Tests compiler fail for join program with replicated data source behind reduce.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputBehindReduce() {
	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
			.reduce(new LastReduce())
			.join(source2).where("*").equalTo("*")
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

/**
 * 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);
}
 

/**
 * Tests compiler fail for join program with replicated data source and changing parallelism.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputChangingparallelism() {

	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("*").setParallelism(DEFAULT_PARALLELISM+2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

/**
 * 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);

}
 

/**
 * Tests compiler fail for join program with replicated data source behind reduce.
 */
@Test(expected = CompilerException.class)
public void checkJoinWithReplicatedSourceInputBehindReduce() {
	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
			.reduce(new LastReduce())
			.join(source2).where("*").equalTo("*")
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);
}
 

/**
 * 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);

}
 

/**
 * 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);
}
 

@Override
public void emitDataSet(DataSet<Row> dataSet) {
	MapOperator<Row, String> csvRows =
		dataSet.map(new CsvFormatter(fieldDelim == null ? "," : fieldDelim));

	DataSink<String> sink;
	if (writeMode != null) {
		sink = csvRows.writeAsText(path, writeMode);
	} else {
		sink = csvRows.writeAsText(path);
	}

	if (numFiles > 0) {
		csvRows.setParallelism(numFiles);
		sink.setParallelism(numFiles);
	}

	sink.name(TableConnectorUtils.generateRuntimeName(CsvTableSink.class, fieldNames));
}
 

/**
 * 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);
}
 

@Override
public DataSink<?> consumeDataSet(DataSet<Row> dataSet) {
	return dataSet.output(
			new Utils.CollectHelper<>(accumulatorName, typeSerializer))
			.name("Batch select table sink")
			.setParallelism(1);
}
 

/**
 * 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);
}
 

/**
 * Tests join program with replicated data source behind flatMap.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindFlatMap() {

	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
			.flatMap(new IdFlatMap())
			.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);
}
 

/**
 * Tests join program with replicated data source behind flatMap.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindFlatMap() {

	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
			.flatMap(new IdFlatMap())
			.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);
}
 

/**
 * Tests join program with replicated data source behind filter.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindFilter() {

	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
			.filter(new NoFilter())
			.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);
}
 

/**
 * Tests cross program with replicated data source.
 */
@Test
public void checkCrossWithReplicatedSourceInput() {

	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
			.cross(source2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	// when cross should have forward strategy on both sides
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	DualInputPlanNode crossNode = (DualInputPlanNode) sinkNode.getPredecessor();

	ShipStrategyType crossIn1 = crossNode.getInput1().getShipStrategy();
	ShipStrategyType crossIn2 = crossNode.getInput2().getShipStrategy();

	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn1);
	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn2);
}
 

/**
 * Tests cross program with replicated data source.
 */
@Test
public void checkCrossWithReplicatedSourceInput() {

	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
			.cross(source2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	// when cross should have forward strategy on both sides
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	DualInputPlanNode crossNode = (DualInputPlanNode) sinkNode.getPredecessor();

	ShipStrategyType crossIn1 = crossNode.getInput1().getShipStrategy();
	ShipStrategyType crossIn2 = crossNode.getInput2().getShipStrategy();

	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn1);
	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn2);
}
 

/**
 * Tests cross program with replicated data source behind map and filter.
 */
@Test
public void checkCrossWithReplicatedSourceInputBehindMap() {

	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())
			.filter(new NoFilter())
			.cross(source2)
			.writeAsText("/some/newpath");

	Plan plan = env.createProgramPlan();

	// submit the plan to the compiler
	OptimizedPlan oPlan = compileNoStats(plan);

	// check the optimized Plan
	// when cross should have forward strategy on both sides
	SinkPlanNode sinkNode = oPlan.getDataSinks().iterator().next();
	DualInputPlanNode crossNode = (DualInputPlanNode) sinkNode.getPredecessor();

	ShipStrategyType crossIn1 = crossNode.getInput1().getShipStrategy();
	ShipStrategyType crossIn2 = crossNode.getInput2().getShipStrategy();

	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn1);
	Assert.assertEquals("Invalid ship strategy for an operator.", ShipStrategyType.FORWARD, crossIn2);
}
 

@Override
public void translateNode(AvroIO.Write.Bound<T> transform, FlinkBatchTranslationContext context) {
	DataSet<T> inputDataSet = context.getInputDataSet(context.getInput(transform));
	String filenamePrefix = transform.getFilenamePrefix();
	String filenameSuffix = transform.getFilenameSuffix();
	int numShards = transform.getNumShards();
	String shardNameTemplate = transform.getShardNameTemplate();

	// TODO: Implement these. We need Flink support for this.
	LOG.warn("Translation of TextIO.Write.filenameSuffix not yet supported. Is: {}.",
			filenameSuffix);
	LOG.warn("Translation of TextIO.Write.shardNameTemplate not yet supported. Is: {}.", shardNameTemplate);

	// This is super hacky, but unfortunately we cannot get the type otherwise
	Class<T> extractedAvroType;
	try {
		Field typeField = transform.getClass().getDeclaredField("type");
		typeField.setAccessible(true);
		@SuppressWarnings("unchecked")
		Class<T> avroType = (Class<T>) typeField.get(transform);
		extractedAvroType = avroType;
	} catch (NoSuchFieldException | IllegalAccessException e) {
		// we know that the field is there and it is accessible
		throw new RuntimeException("Could not access type from AvroIO.Bound", e);
	}

	DataSink<T> dataSink = inputDataSet.output(new AvroOutputFormat<>(new Path
			(filenamePrefix), extractedAvroType));

	if (numShards > 0) {
		dataSink.setParallelism(numShards);
	}
}
 

/**
 * Tests join program with replicated data source behind map partition.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindMapPartition() {

	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
			.mapPartition(new IdPMap())
			.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);
}
 

/**
 * Tests join program with replicated data source behind map partition.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindMapPartition() {

	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
			.mapPartition(new IdPMap())
			.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);
}
 

/**
 * 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);
}
 

@SuppressWarnings("unchecked")
private <X extends Tuple> DataSink<T> internalWriteAsCsv(Path filePath, String rowDelimiter, String fieldDelimiter, WriteMode wm) {
	Preconditions.checkArgument(getType().isTupleType(), "The writeAsCsv() method can only be used on data sets of tuples.");
	CsvOutputFormat<X> of = new CsvOutputFormat<>(filePath, rowDelimiter, fieldDelimiter);
	if (wm != null) {
		of.setWriteMode(wm);
	}
	return output((OutputFormat<T>) of);
}
 

/**
 * Tests join program with replicated data source behind filter.
 */
@Test
public void checkJoinWithReplicatedSourceInputBehindFilter() {

	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
			.filter(new NoFilter())
			.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);
}
 

public PlanGenerator(
		List<DataSink<?>> sinks,
		ExecutionConfig config,
		int defaultParallelism,
		List<Tuple2<String, DistributedCache.DistributedCacheEntry>> cacheFile,
		String jobName) {
	this.sinks = checkNotNull(sinks);
	this.config = checkNotNull(config);
	this.cacheFile = checkNotNull(cacheFile);
	this.jobName = checkNotNull(jobName);
	this.defaultParallelism = defaultParallelism;
}