当前位置: 首页>>代码示例>>Java>>正文


Java ExecutionEnvironment.createLocalEnvironment方法代码示例

本文整理汇总了Java中org.apache.flink.api.java.ExecutionEnvironment.createLocalEnvironment方法的典型用法代码示例。如果您正苦于以下问题:Java ExecutionEnvironment.createLocalEnvironment方法的具体用法?Java ExecutionEnvironment.createLocalEnvironment怎么用?Java ExecutionEnvironment.createLocalEnvironment使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在org.apache.flink.api.java.ExecutionEnvironment的用法示例。


在下文中一共展示了ExecutionEnvironment.createLocalEnvironment方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。

示例1: checkJoinWithReplicatedSourceInputBehindReduce

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
/**
 * 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);
}
 
开发者ID:axbaretto,项目名称:flink,代码行数:26,代码来源:ReplicatingDataSourceTest.java

示例2: checkJoinWithReplicatedSourceInputBehindRebalance

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
/**
 * 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);
}
 
开发者ID:axbaretto,项目名称:flink,代码行数:26,代码来源:ReplicatingDataSourceTest.java

示例3: main

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
public static void main(String[] argv) throws Exception {

		// BasicConfigurator.configure(new ConsoleAppender(new
		// PatternLayout()));

		ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();

		OSMPBFWayInputFormat iformat = new OSMPBFWayInputFormat();

		iformat.setFilePath("C:/projets/OSMImport/france-latest.osm.pbf");

		// iformat.setFilePath("C:/projets/OSMImport/rhone-alpes-latest.osm.pbf");

		FileInputSplit[] s = iformat.createInputSplits(4);

		DataSource<WayEntity> r = env.createInput(iformat, new GenericTypeInfo<WayEntity>(WayEntity.class));
		r.flatMap(new FlatMapFunction<WayEntity, Tuple2<Long, String>>() {
			@Override
			public void flatMap(WayEntity value, Collector<Tuple2<Long, String>> out)
					throws Exception {
				if (value.fields != null) {
					if (value.fields.containsKey("type")) {
						out.collect(new Tuple2<>(value.id, (String) value.fields.get("type")));
					}
				}
			}
		}).writeAsCsv("test.csv");

		env.execute();

	}
 
开发者ID:frett27,项目名称:osm-flink-tools,代码行数:32,代码来源:TestPBFWayInputStream.java

示例4: checkSinglePartitionedOrderedSource3

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedOrderedSource3() {

	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)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.ASCENDING});

	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(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:34,代码来源:PropertyDataSourceTest.java

示例5: checkSinglePartitionedSource7

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedSource7() {

	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("byDate", 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, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.CUSTOM_PARTITIONING);
	Assert.assertTrue(gprops.getCustomPartitioner() != null);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:34,代码来源:PropertyDataSourceTest.java

示例6: checkSinglePartitionedOrderedSource7

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedOrderedSource7() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1")
			.splitsOrderedBy("f1.stringField", new Order[]{Order.ASCENDING});

	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(1,2,3)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:33,代码来源:PropertyDataSourceTest.java

示例7: checkSinglePartitionedGroupedSource7

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedGroupedSource7() {

	ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();
	env.setParallelism(DEFAULT_PARALLELISM);

	DataSource<Tuple3<Long, SomePojo, String>> data = env.fromCollection(tuple3PojoData, tuple3PojoType);

	data.getSplitDataProperties()
			.splitsPartitionedBy("f1.intField")
			.splitsGroupedBy("f1");

	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(2)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(new FieldSet(lprops.getGroupedFields().toArray()).equals(new FieldSet(1,2,3)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:33,代码来源:PropertyDataSourceTest.java

示例8: checkSinglePartitionedGroupedSource1

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedGroupedSource1() {

	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(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)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:34,代码来源:PropertyDataSourceTest.java

示例9: checkSinglePartitionedOrderedSource1

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedOrderedSource1() {

	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)
			.splitsOrderedBy(new int[]{1}, new Order[]{Order.ASCENDING});

	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((new FieldSet(lprops.getGroupedFields().toArray())).equals(new FieldSet(1)));
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:34,代码来源:PropertyDataSourceTest.java

示例10: checkSinglePartitionedSource1

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedSource1() {

	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);

	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(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:33,代码来源:PropertyDataSourceTest.java

示例11: main

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
public static void main(String[] argv) throws Exception {

		// BasicConfigurator.configure(new ConsoleAppender(new
		// PatternLayout()));

		ExecutionEnvironment env = ExecutionEnvironment.createLocalEnvironment();

		OSMPBFRelationInputFormat iformat = new OSMPBFRelationInputFormat();

		//iformat.setFilePath("C:/projets/OSMImport/france-latest.osm.pbf");

		iformat.setFilePath("C:/projets/OSMImport/rhone-alpes-latest.osm.pbf");

		FileInputSplit[] s = iformat.createInputSplits(4);

		DataSource<Relation> r = env.createInput(iformat, new GenericTypeInfo<Relation>(Relation.class));
		r.flatMap(new FlatMapFunction<Relation, Tuple2<Long, String>>() {
			@Override
			public void flatMap(Relation value, Collector<Tuple2<Long, String>> out)
					throws Exception {
				if (value.fields != null) {
					if (value.fields.containsKey("type")) {
						out.collect(new Tuple2<>(value.id, (String) value.fields.get("type")));
					}
				}
			}
		}).writeAsCsv("test.csv");

		env.execute();

	}
 
开发者ID:frett27,项目名称:osm-flink-tools,代码行数:32,代码来源:TestPBFRelationInputStream.java

示例12: checkSinglePartitionedGroupedSource4

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
@Test
public void checkSinglePartitionedGroupedSource4() {

	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)
			.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(0, 1)));
	Assert.assertTrue(gprops.getPartitioning() == PartitioningProperty.ANY_PARTITIONING);
	Assert.assertTrue(lprops.getGroupedFields() == null);
	Assert.assertTrue(lprops.getOrdering() == null);

}
 
开发者ID:axbaretto,项目名称:flink,代码行数:34,代码来源:PropertyDataSourceTest.java

示例13: checkJoinWithReplicatedSourceInputBehindFilter

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
/**
 * 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);
}
 
开发者ID:axbaretto,项目名称:flink,代码行数:38,代码来源:ReplicatingDataSourceTest.java

示例14: checkJoinWithReplicatedSourceInputBehindFlatMap

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
/**
 * 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);
}
 
开发者ID:axbaretto,项目名称:flink,代码行数:38,代码来源:ReplicatingDataSourceTest.java

示例15: checkJoinWithReplicatedSourceInputBehindMapPartition

import org.apache.flink.api.java.ExecutionEnvironment; //导入方法依赖的package包/类
/**
 * 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);
}
 
开发者ID:axbaretto,项目名称:flink,代码行数:38,代码来源:ReplicatingDataSourceTest.java


注:本文中的org.apache.flink.api.java.ExecutionEnvironment.createLocalEnvironment方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。