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 | from org.apache.hadoop.fs import Path |
---|
20 | from org.apache.hadoop.io import * |
---|
21 | from org.apache.hadoop.mapred import * |
---|
22 | |
---|
23 | from org.apache.hadoop.abacus import *; |
---|
24 | |
---|
25 | from java.util import *; |
---|
26 | |
---|
27 | import sys |
---|
28 | |
---|
29 | class AbacusWordCount(ValueAggregatorBaseDescriptor): |
---|
30 | def generateKeyValPairs(self, key, val): |
---|
31 | retv = ArrayList(); |
---|
32 | for w in val.toString().split(): |
---|
33 | en = ValueAggregatorBaseDescriptor.generateEntry(ValueAggregatorBaseDescriptor.LONG_VALUE_SUM, w, ValueAggregatorBaseDescriptor.ONE); |
---|
34 | retv.add(en); |
---|
35 | return retv; |
---|
36 | |
---|