blob: f3d4559e71fad7177d248ca9bf14828215221c7a [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.List;
import java.util.Optional;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.wayang.basic.operators.TextFileSink;
import org.apache.wayang.core.api.Configuration;
import org.apache.wayang.core.function.TransformationDescriptor;
import org.apache.wayang.core.optimizer.OptimizationContext;
import org.apache.wayang.core.optimizer.costs.LoadProfileEstimator;
import org.apache.wayang.core.optimizer.costs.LoadProfileEstimators;
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.util.Tuple;
import org.apache.wayang.spark.channels.RddChannel;
import org.apache.wayang.spark.execution.SparkExecutor;
/**
* Implementation of the {@link TextFileSink} operator for the Spark platform.
*/
public class SparkTextFileSink<T> extends TextFileSink<T> implements SparkExecutionOperator {
public SparkTextFileSink(String textFileUrl, TransformationDescriptor<T, String> formattingDescriptor) {
super(textFileUrl, formattingDescriptor);
}
public SparkTextFileSink(TextFileSink<T> that) {
super(that);
}
@Override
public Tuple<Collection<ExecutionLineageNode>, Collection<ChannelInstance>> evaluate(
ChannelInstance[] inputs,
ChannelInstance[] outputs,
SparkExecutor sparkExecutor,
OptimizationContext.OperatorContext operatorContext) {
assert inputs.length == 1;
assert outputs.length == 0;
JavaRDD<T> inputRdd = ((RddChannel.Instance) inputs[0]).provideRdd();
final Function<T, String> formattingFunction =
sparkExecutor.getCompiler().compile(this.formattingDescriptor, this, operatorContext, inputs);
inputRdd.map(formattingFunction).saveAsTextFile(this.textFileUrl);
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) {
throw new UnsupportedOperationException("This operator has no outputs.");
}
@Override
public boolean containsAction() {
return true;
}
@Override
public String getLoadProfileEstimatorConfigurationKey() {
return "wayang.spark.textfilesink.load";
}
@Override
public Optional<LoadProfileEstimator> createLoadProfileEstimator(Configuration configuration) {
final Optional<LoadProfileEstimator> optEstimator =
SparkExecutionOperator.super.createLoadProfileEstimator(configuration);
LoadProfileEstimators.nestUdfEstimator(optEstimator, this.formattingDescriptor, configuration);
return optEstimator;
}
}