[120] | 1 | /** |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
---|
| 3 | * or more contributor license agreements. See the NOTICE file |
---|
| 4 | * distributed with this work for additional information |
---|
| 5 | * regarding copyright ownership. The ASF licenses this file |
---|
| 6 | * to you under the Apache License, Version 2.0 (the |
---|
| 7 | * "License"); you may not use this file except in compliance |
---|
| 8 | * with the License. You may obtain a copy of the License at |
---|
| 9 | * |
---|
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 11 | * |
---|
| 12 | * Unless required by applicable law or agreed to in writing, software |
---|
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 15 | * See the License for the specific language governing permissions and |
---|
| 16 | * limitations under the License. |
---|
| 17 | */ |
---|
| 18 | |
---|
| 19 | package org.apache.hadoop.mapred.lib.aggregate; |
---|
| 20 | |
---|
| 21 | import org.apache.hadoop.io.Text; |
---|
| 22 | import java.util.ArrayList; |
---|
| 23 | import java.util.Map.Entry; |
---|
| 24 | |
---|
| 25 | public class AggregatorTests extends ValueAggregatorBaseDescriptor { |
---|
| 26 | |
---|
| 27 | public ArrayList<Entry<Text, Text>> generateKeyValPairs(Object key, Object val) { |
---|
| 28 | ArrayList<Entry<Text, Text>> retv = new ArrayList<Entry<Text, Text>>(); |
---|
| 29 | String [] words = val.toString().split(" "); |
---|
| 30 | |
---|
| 31 | String countType; |
---|
| 32 | String id; |
---|
| 33 | Entry<Text, Text> e; |
---|
| 34 | |
---|
| 35 | for (String word: words) { |
---|
| 36 | long numVal = Long.parseLong(word); |
---|
| 37 | countType = LONG_VALUE_SUM; |
---|
| 38 | id = "count_" + word; |
---|
| 39 | e = generateEntry(countType, id, ONE); |
---|
| 40 | if (e != null) { |
---|
| 41 | retv.add(e); |
---|
| 42 | } |
---|
| 43 | countType = LONG_VALUE_MAX; |
---|
| 44 | id = "max"; |
---|
| 45 | e = generateEntry(countType, id, new Text(word)); |
---|
| 46 | if (e != null) { |
---|
| 47 | retv.add(e); |
---|
| 48 | } |
---|
| 49 | |
---|
| 50 | countType = LONG_VALUE_MIN; |
---|
| 51 | id = "min"; |
---|
| 52 | e = generateEntry(countType, id, new Text(word)); |
---|
| 53 | if (e != null) { |
---|
| 54 | retv.add(e); |
---|
| 55 | } |
---|
| 56 | |
---|
| 57 | countType = STRING_VALUE_MAX; |
---|
| 58 | id = "value_as_string_max"; |
---|
| 59 | e = generateEntry(countType, id, new Text(""+numVal)); |
---|
| 60 | if (e != null) { |
---|
| 61 | retv.add(e); |
---|
| 62 | } |
---|
| 63 | |
---|
| 64 | countType = STRING_VALUE_MIN; |
---|
| 65 | id = "value_as_string_min"; |
---|
| 66 | e = generateEntry(countType, id, new Text(""+numVal)); |
---|
| 67 | if (e != null) { |
---|
| 68 | retv.add(e); |
---|
| 69 | } |
---|
| 70 | |
---|
| 71 | countType = UNIQ_VALUE_COUNT; |
---|
| 72 | id = "uniq_count"; |
---|
| 73 | e = generateEntry(countType, id, new Text(word)); |
---|
| 74 | if (e != null) { |
---|
| 75 | retv.add(e); |
---|
| 76 | } |
---|
| 77 | |
---|
| 78 | countType = VALUE_HISTOGRAM; |
---|
| 79 | id = "histogram"; |
---|
| 80 | e = generateEntry(countType, id, new Text(word)); |
---|
| 81 | if (e != null) { |
---|
| 82 | retv.add(e); |
---|
| 83 | } |
---|
| 84 | } |
---|
| 85 | return retv; |
---|
| 86 | } |
---|
| 87 | |
---|
| 88 | } |
---|