fullstack/hyracks/hyracks-dataflow-std/src/main/java/edu/uci/ics/hyracks/dataflow/std/map/SamplerDeserializedMapperFactory.java

/*
 * Copyright 2009-2010 by The Regents of the University of California
 * Licensed 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 from
 * 
 *     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 edu.uci.ics.hyracks.dataflow.std.map;

import java.util.Random;

import edu.uci.ics.hyracks.api.dataflow.IDataWriter;
import edu.uci.ics.hyracks.api.exceptions.HyracksDataException;

public class SamplerDeserializedMapperFactory implements IDeserializedMapperFactory {
    private static final long serialVersionUID = 1L;
    private final float sampleRatio;

    public SamplerDeserializedMapperFactory(float sampleRatio) {
        this.sampleRatio = sampleRatio;
    }

    @Override
    public IDeserializedMapper createMapper() throws HyracksDataException {
        return new IDeserializedMapper() {
            private Random random = new Random();

            @Override
            public void map(Object[] data, IDataWriter<Object[]> writer) throws HyracksDataException {
                if (random.nextFloat() <= sampleRatio) {
                    writer.writeData(data);
                }
            }
        };
    }
}