001 /** 002 * Licensed to the Apache Software Foundation (ASF) under one 003 * or more contributor license agreements. See the NOTICE file 004 * distributed with this work for additional information 005 * regarding copyright ownership. The ASF licenses this file 006 * to you under the Apache License, Version 2.0 (the 007 * "License"); you may not use this file except in compliance 008 * with the License. You may obtain a copy of the License at 009 * 010 * http://www.apache.org/licenses/LICENSE-2.0 011 * 012 * Unless required by applicable law or agreed to in writing, software 013 * distributed under the License is distributed on an "AS IS" BASIS, 014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 015 * See the License for the specific language governing permissions and 016 * limitations under the License. 017 */ 018 019 package org.apache.hadoop.mapreduce.lib.aggregate; 020 021 import java.io.IOException; 022 import java.util.Iterator; 023 024 import org.apache.hadoop.classification.InterfaceAudience; 025 import org.apache.hadoop.classification.InterfaceStability; 026 import org.apache.hadoop.io.Text; 027 import org.apache.hadoop.io.Writable; 028 import org.apache.hadoop.io.WritableComparable; 029 import org.apache.hadoop.mapreduce.Reducer; 030 031 /** 032 * This class implements the generic combiner of Aggregate. 033 */ 034 @InterfaceAudience.Public 035 @InterfaceStability.Stable 036 public class ValueAggregatorCombiner<K1 extends WritableComparable<?>, 037 V1 extends Writable> 038 extends Reducer<Text, Text, Text, Text> { 039 040 /** Combines values for a given key. 041 * @param key the key is expected to be a Text object, whose prefix indicates 042 * the type of aggregation to aggregate the values. 043 * @param values the values to combine 044 * @param context to collect combined values 045 */ 046 public void reduce(Text key, Iterable<Text> values, Context context) 047 throws IOException, InterruptedException { 048 String keyStr = key.toString(); 049 int pos = keyStr.indexOf(ValueAggregatorDescriptor.TYPE_SEPARATOR); 050 String type = keyStr.substring(0, pos); 051 long uniqCount = context.getConfiguration(). 052 getLong(UniqValueCount.MAX_NUM_UNIQUE_VALUES, Long.MAX_VALUE); 053 ValueAggregator aggregator = ValueAggregatorBaseDescriptor 054 .generateValueAggregator(type, uniqCount); 055 for (Text val : values) { 056 aggregator.addNextValue(val); 057 } 058 Iterator<?> outputs = aggregator.getCombinerOutput().iterator(); 059 060 while (outputs.hasNext()) { 061 Object v = outputs.next(); 062 if (v instanceof Text) { 063 context.write(key, (Text)v); 064 } else { 065 context.write(key, new Text(v.toString())); 066 } 067 } 068 } 069 }