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.mapred.lib.aggregate; 020 021 import java.util.Map.Entry; 022 023 import org.apache.hadoop.classification.InterfaceAudience; 024 import org.apache.hadoop.classification.InterfaceStability; 025 import org.apache.hadoop.io.Text; 026 import org.apache.hadoop.mapred.JobConf; 027 028 /** 029 * This class implements the common functionalities of 030 * the subclasses of ValueAggregatorDescriptor class. 031 * 032 * @deprecated Use 033 * {@link org.apache.hadoop.mapreduce.lib.aggregate.ValueAggregatorBaseDescriptor} 034 * instead 035 */ 036 @Deprecated 037 @InterfaceAudience.Public 038 @InterfaceStability.Stable 039 public class ValueAggregatorBaseDescriptor extends org.apache.hadoop.mapreduce. 040 lib.aggregate.ValueAggregatorBaseDescriptor 041 implements ValueAggregatorDescriptor { 042 043 static public final String UNIQ_VALUE_COUNT = org.apache.hadoop.mapreduce. 044 lib.aggregate.ValueAggregatorBaseDescriptor.UNIQ_VALUE_COUNT; 045 046 static public final String LONG_VALUE_SUM = org.apache.hadoop.mapreduce. 047 lib.aggregate.ValueAggregatorBaseDescriptor.LONG_VALUE_SUM; 048 049 static public final String DOUBLE_VALUE_SUM = org.apache.hadoop.mapreduce. 050 lib.aggregate.ValueAggregatorBaseDescriptor.DOUBLE_VALUE_SUM; 051 052 static public final String VALUE_HISTOGRAM = org.apache.hadoop.mapreduce. 053 lib.aggregate.ValueAggregatorBaseDescriptor.VALUE_HISTOGRAM; 054 055 static public final String LONG_VALUE_MAX = org.apache.hadoop.mapreduce. 056 lib.aggregate.ValueAggregatorBaseDescriptor.LONG_VALUE_MAX; 057 058 static public final String LONG_VALUE_MIN = org.apache.hadoop.mapreduce. 059 lib.aggregate.ValueAggregatorBaseDescriptor.LONG_VALUE_MIN; 060 061 static public final String STRING_VALUE_MAX = org.apache.hadoop.mapreduce. 062 lib.aggregate.ValueAggregatorBaseDescriptor.STRING_VALUE_MAX; 063 064 static public final String STRING_VALUE_MIN = org.apache.hadoop.mapreduce. 065 lib.aggregate.ValueAggregatorBaseDescriptor.STRING_VALUE_MIN; 066 067 private static long maxNumItems = Long.MAX_VALUE; 068 069 /** 070 * 071 * @param type the aggregation type 072 * @param id the aggregation id 073 * @param val the val associated with the id to be aggregated 074 * @return an Entry whose key is the aggregation id prefixed with 075 * the aggregation type. 076 */ 077 public static Entry<Text, Text> generateEntry(String type, String id, Text val) { 078 return org.apache.hadoop.mapreduce.lib.aggregate. 079 ValueAggregatorBaseDescriptor.generateEntry(type, id, val); 080 } 081 082 /** 083 * 084 * @param type the aggregation type 085 * @return a value aggregator of the given type. 086 */ 087 static public ValueAggregator generateValueAggregator(String type) { 088 ValueAggregator retv = null; 089 if (type.compareToIgnoreCase(LONG_VALUE_SUM) == 0) { 090 retv = new LongValueSum(); 091 } if (type.compareToIgnoreCase(LONG_VALUE_MAX) == 0) { 092 retv = new LongValueMax(); 093 } else if (type.compareToIgnoreCase(LONG_VALUE_MIN) == 0) { 094 retv = new LongValueMin(); 095 } else if (type.compareToIgnoreCase(STRING_VALUE_MAX) == 0) { 096 retv = new StringValueMax(); 097 } else if (type.compareToIgnoreCase(STRING_VALUE_MIN) == 0) { 098 retv = new StringValueMin(); 099 } else if (type.compareToIgnoreCase(DOUBLE_VALUE_SUM) == 0) { 100 retv = new DoubleValueSum(); 101 } else if (type.compareToIgnoreCase(UNIQ_VALUE_COUNT) == 0) { 102 retv = new UniqValueCount(maxNumItems); 103 } else if (type.compareToIgnoreCase(VALUE_HISTOGRAM) == 0) { 104 retv = new ValueHistogram(); 105 } 106 return retv; 107 } 108 109 /** 110 * get the input file name. 111 * 112 * @param job a job configuration object 113 */ 114 public void configure(JobConf job) { 115 super.configure(job); 116 maxNumItems = job.getLong("aggregate.max.num.unique.values", 117 Long.MAX_VALUE); 118 } 119 }