use of org.apache.flink.core.fs.FileInputSplit in project flink by apache.
the class ReplicatingDataSourceTest method checkCrossWithReplicatedSourceInput.
/**
* 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);
}
use of org.apache.flink.core.fs.FileInputSplit in project flink by apache.
the class ReplicatingDataSourceTest method checkJoinWithReplicatedSourceInputBehindMapPartition.
/**
* 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);
}
use of org.apache.flink.core.fs.FileInputSplit 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);
}
use of org.apache.flink.core.fs.FileInputSplit in project flink by apache.
the class ReplicatingDataSourceTest method checkCrossWithReplicatedSourceInputBehindMap.
/**
* 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);
}
use of org.apache.flink.core.fs.FileInputSplit in project flink by apache.
the class MockInputSplitProvider method addInputSplits.
/**
* Generates a set of input splits from an input path
*
* @param path
* the path of the local file to generate the input splits from
* @param noSplits
* the number of input splits to be generated from the given input file
*/
public void addInputSplits(final String path, final int noSplits) {
final InputSplit[] tmp = new InputSplit[noSplits];
final String[] hosts = { "localhost" };
final String localPath;
try {
localPath = new URI(path).getPath();
} catch (URISyntaxException e) {
throw new IllegalArgumentException("Path URI can not be transformed to local path.");
}
final File inFile = new File(localPath);
final long splitLength = inFile.length() / noSplits;
long pos = 0;
for (int i = 0; i < noSplits - 1; i++) {
tmp[i] = new FileInputSplit(i, new Path(path), pos, splitLength, hosts);
pos += splitLength;
}
tmp[noSplits - 1] = new FileInputSplit(noSplits - 1, new Path(path), pos, inFile.length() - pos, hosts);
this.inputSplits = tmp;
}
Aggregations