blob: 931fc1b86dc05774df94a55ff27ef4cce7df11ce [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.JavaRDD;
import org.apache.wayang.basic.operators.IntersectOperator;
import org.apache.wayang.basic.operators.JoinOperator;
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.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 JoinOperator}.
*/
public class SparkIntersectOperator<Type> extends IntersectOperator<Type> implements SparkExecutionOperator {
public SparkIntersectOperator(DataSetType<Type> dataSetType) {
super(dataSetType);
}
public SparkIntersectOperator(Class<Type> typeClass) {
super(typeClass);
}
/**
* Copies an instance (exclusive of broadcasts).
*
* @param that that should be copied
*/
public SparkIntersectOperator(IntersectOperator<Type> 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();
final RddChannel.Instance input0 = (RddChannel.Instance) inputs[0];
final RddChannel.Instance input1 = (RddChannel.Instance) inputs[1];
final RddChannel.Instance output = (RddChannel.Instance) outputs[0];
final JavaRDD<Object> outputRdd = input0.provideRdd().intersection(input1.provideRdd());
this.name(outputRdd);
output.accept(outputRdd, sparkExecutor);
return ExecutionOperator.modelLazyExecution(inputs, outputs, operatorContext);
}
@Override
protected ExecutionOperator createCopy() {
return new SparkIntersectOperator<>(this.getType());
}
@Override
public String getLoadProfileEstimatorConfigurationKey() {
return "wayang.spark.intersect.load";
}
@Override
public List<ChannelDescriptor> getSupportedInputChannels(int index) {
assert index <= this.getNumInputs() || (index == 0 && this.getNumInputs() == 0);
return Arrays.asList(RddChannel.UNCACHED_DESCRIPTOR, RddChannel.CACHED_DESCRIPTOR);
}
@Override
public List<ChannelDescriptor> getSupportedOutputChannels(int index) {
assert index <= this.getNumOutputs() || (index == 0 && this.getNumOutputs() == 0);
return Collections.singletonList(RddChannel.UNCACHED_DESCRIPTOR);
}
@Override
public boolean containsAction() {
return false;
}
}