blob: d1e2aad4d7c11dc8c0b19df075d6d90377573c9d [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 java.util.Arrays;
import java.util.Collection;
import java.util.Collections;
import java.util.List;
import java.util.Optional;
import org.apache.commons.lang3.Validate;
import org.apache.wayang.core.api.Configuration;
import org.apache.wayang.core.optimizer.OptimizationContext;
import org.apache.wayang.core.optimizer.cardinality.CardinalityEstimator;
import org.apache.wayang.core.optimizer.cardinality.DefaultCardinalityEstimator;
import org.apache.wayang.core.plan.wayangplan.ExecutionOperator;
import org.apache.wayang.core.plan.wayangplan.UnaryToUnaryOperator;
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.java.channels.CollectionChannel;
import org.apache.wayang.java.platform.JavaPlatform;
import org.apache.wayang.spark.channels.RddChannel;
import org.apache.wayang.spark.execution.SparkExecutor;
/**
* Converts a {@link RddChannel} into a {@link CollectionChannel} of the {@link JavaPlatform}.
*/
public class SparkCollectOperator<Type>
extends UnaryToUnaryOperator<Type, Type>
implements SparkExecutionOperator {
public SparkCollectOperator(DataSetType<Type> type) {
super(type, type, false);
}
@Override
public Tuple<Collection<ExecutionLineageNode>, Collection<ChannelInstance>> evaluate(
ChannelInstance[] inputs,
ChannelInstance[] outputs,
SparkExecutor sparkExecutor,
OptimizationContext.OperatorContext operatorContext) {
RddChannel.Instance input = (RddChannel.Instance) inputs[0];
CollectionChannel.Instance output = (CollectionChannel.Instance) outputs[0];
@SuppressWarnings("unchecked")
final List<Type> collectedRdd = (List<Type>) input.provideRdd().collect();
output.accept(collectedRdd);
return ExecutionOperator.modelEagerExecution(inputs, outputs, operatorContext);
}
@Override
public List<ChannelDescriptor> getSupportedInputChannels(int index) {
return Arrays.asList(RddChannel.UNCACHED_DESCRIPTOR, RddChannel.CACHED_DESCRIPTOR);
}
@Override
public List<ChannelDescriptor> getSupportedOutputChannels(int index) {
return Collections.singletonList(CollectionChannel.DESCRIPTOR);
}
@Override
public boolean containsAction() {
return true;
}
@Override
public Optional<CardinalityEstimator> createCardinalityEstimator(
final int outputIndex,
final Configuration configuration) {
Validate.inclusiveBetween(0, 0, outputIndex);
return Optional.of(new DefaultCardinalityEstimator(1d, 1, this.isSupportingBroadcastInputs(),
inputCards -> inputCards[0]));
}
@Override
public String getLoadProfileEstimatorConfigurationKey() {
return "wayang.spark.collect.load";
}
}