命令行编译打包运行自己的MapReduce程序
Hadoop 2.8.2
java version “1.8.0_151″
编译、打包 Hadoop MapReduce 程序
将hadoop的classpath信息添加到CLASSPATH变量中，在~/.bashrc中增加如下几行：
|
1 2 |
export HADOOP_HOME=/usr/local/hadoop export CLASSPATH=$($HADOOP_HOME/bin/hadoop classpath):$CLASSPATH |
执行使变量生效
|
1 |
source ~/.bashrc |
javac命令编译WordCount.java(文末有)
|
1 |
javac WordCount.java |
接着把 .class 文件打包成 jar，才能在 Hadoop 中运行：
|
1 |
jar -cvf WordCount.jar ./WordCount*.class |
创建1.txt文件
|
1 |
vim 1.txt |
把文件放入hdfs中
|
1 |
./bin/hdfs dfs -put ./1.txt /user/hdfs/input/ |
运行
|
1 |
/usr/local/hadoop/bin/hadoop jar WordCount.jar org.apache.hadoop.examples.WordCount /user/hdfs/input/ /user/hdfs/output/ |
查看结果(后面的值为出现结果)
|
1 |
../bin/hdfs dfs -cat /user/hdfs/output/part-r-00000 |
WordCount.java 源码
文件位于 hadoop-2.6.0-src\hadoop-mapreduce-project\hadoop-mapreduce-examples\src\main\java\org\apache\hadoop\examples 中
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
/** * 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.examples; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2); } Job job = new Job(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } } |
请尊重我们的辛苦付出，未经允许，请不要转载 本站 的文章，鄙视各种无耻的采集行为！