blob: a5a3f22dcc3f7ea574df2e34258d56ae521b06ea [file] [log] [blame]
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.wayang.spark.operators;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.wayang.basic.data.Tuple2;
import org.apache.wayang.basic.operators.MapOperator;
import org.apache.wayang.basic.operators.ZipWithIdOperator;
import org.apache.wayang.core.optimizer.OptimizationContext;
import org.apache.wayang.core.plan.wayangplan.ExecutionOperator;
import org.apache.wayang.core.platform.ChannelDescriptor;
import org.apache.wayang.core.platform.ChannelInstance;
import org.apache.wayang.core.platform.lineage.ExecutionLineageNode;
import org.apache.wayang.core.types.DataSetType;
import org.apache.wayang.core.util.Tuple;
import org.apache.wayang.spark.channels.BroadcastChannel;
import org.apache.wayang.spark.channels.RddChannel;
import org.apache.wayang.spark.execution.SparkExecutor;
import java.util.Arrays;
import java.util.Collection;
import java.util.Collections;
import java.util.List;
/**
* Spark implementation of the {@link MapOperator}.
*/
public class SparkZipWithIdOperator<InputType>
extends ZipWithIdOperator<InputType>
implements SparkExecutionOperator {
/**
* Creates a new instance.
*/
public SparkZipWithIdOperator(DataSetType<InputType> inputType) {
super(inputType);
}
/**
* Creates a new instance.
*/
public SparkZipWithIdOperator(Class<InputType> inputTypeClass) {
super(inputTypeClass);
}
/**
* Copies an instance (exclusive of broadcasts).
*
* @param that that should be copied
*/
public SparkZipWithIdOperator(ZipWithIdOperator<InputType> that) {
super(that);
}
@Override
public Tuple<Collection<ExecutionLineageNode>, Collection<ChannelInstance>> evaluate(
ChannelInstance[] inputs,
ChannelInstance[] outputs,
SparkExecutor sparkExecutor,
OptimizationContext.OperatorContext operatorContext) {
assert inputs.length == this.getNumInputs();
assert outputs.length == this.getNumOutputs();
RddChannel.Instance input = (RddChannel.Instance) inputs[0];
RddChannel.Instance output = (RddChannel.Instance) outputs[0];
final JavaRDD<InputType> inputRdd = input.provideRdd();
final JavaPairRDD<InputType, Long> zippedRdd = inputRdd.zipWithUniqueId();
this.name(zippedRdd);
final JavaRDD<Tuple2<Long, InputType>> outputRdd = zippedRdd.map(pair -> new Tuple2<>(pair._2, pair._1));
this.name(outputRdd);
output.accept(outputRdd, sparkExecutor);
return ExecutionOperator.modelLazyExecution(inputs, outputs, operatorContext);
}
@Override
protected ExecutionOperator createCopy() {
return new SparkZipWithIdOperator<>(this.getInputType());
}
@Override
public String getLoadProfileEstimatorConfigurationKey() {
return "wayang.spark.zipwithid.load";
}
@Override
public List<ChannelDescriptor> getSupportedInputChannels(int index) {
if (index == 0) {
return Arrays.asList(RddChannel.UNCACHED_DESCRIPTOR, RddChannel.CACHED_DESCRIPTOR);
} else {
return Collections.singletonList(BroadcastChannel.DESCRIPTOR);
}
}
@Override
public List<ChannelDescriptor> getSupportedOutputChannels(int index) {
return Collections.singletonList(RddChannel.UNCACHED_DESCRIPTOR);
}
@Override
public boolean containsAction() {
return false;
}
}