org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorCombiner Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of hadoop-apache2 Show documentation
Shaded version of Apache Hadoop 2.x for Presto
The newest version!
/**
 * 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.hadoop.mapreduce.lib.aggregate;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapreduce.Reducer;

/**
 * This class implements the generic combiner of Aggregate.
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public class ValueAggregatorCombiner,
                                     V1 extends Writable>
  extends Reducer {

  /** Combines values for a given key.  
   * @param key the key is expected to be a Text object, whose prefix indicates
   * the type of aggregation to aggregate the values. 
   * @param values the values to combine
   * @param context to collect combined values
   */
  public void reduce(Text key, Iterable values, Context context) 
      throws IOException, InterruptedException {
    String keyStr = key.toString();
    int pos = keyStr.indexOf(ValueAggregatorDescriptor.TYPE_SEPARATOR);
    String type = keyStr.substring(0, pos);
    long uniqCount = context.getConfiguration().
      getLong(UniqValueCount.MAX_NUM_UNIQUE_VALUES, Long.MAX_VALUE);
    ValueAggregator aggregator = ValueAggregatorBaseDescriptor
      .generateValueAggregator(type, uniqCount);
    for (Text val : values) {
      aggregator.addNextValue(val);
    }
    Iterator outputs = aggregator.getCombinerOutput().iterator();

    while (outputs.hasNext()) {
      Object v = outputs.next();
      if (v instanceof Text) {
        context.write(key, (Text)v);
      } else {
        context.write(key, new Text(v.toString()));
      }
    }
  }
}