Question

如何在hadoop2.5.2使用命令行编译打包运行自己的mapreduce程序

Answer 1

网上的 MapReduce WordCount 教程对于如何编译 WordCount.Java 几乎是一笔带过… 而有写到的，大多又是 0.20 等旧版本版本的做法，即 javac -classpath /usr/local/Hadoop/hadoop-1.0.1/hadoop-core-1.0.1.jar WordCount.java，但较新的 2.X 版本中，已经没有 hadoop-core*.jar 这个文件，因此编辑和打包自己的 MapReduce 程序与旧版本有所不同。
本文以 Hadoop 2.7.2 环境下的 WordCount 实例来介绍 2.x 版本中如何编辑自己的 MapReduce 程序。

编译、打包 Hadoop MapReduce 程序
我们将 Hadoop 的 classhpath 信息添加到 CLASSPATH 变量中，在 ~/.bashrc 中增加如下几行：

[html] view plain copy
export HADOOP_HOME=/usr/local/hadoop
export CLASSPATH=$($HADOOP_HOME/bin/hadoop classpath):$CLASSPATH

别忘了执行 source ~/.bashrc 使变量生效，接着就可以通过 javac 命令编译 WordCount.java 了（使用的是 Hadoop 源码中的 WordCount.java，源码在文本最后面）：javac WordCount.java

编译时会有警告，可以忽略。编译后可以看到生成了几个 .class 文件。

接着把 .class 文件打包成 jar，才能在 Hadoop 中运行：

[html] view plain copy
jar -cvf WordCount.jar ./WordCount*.class

开始运行：
[html] view plain copy
hadoop jar WordCount.jar WordCount input output//hdfs上的input文件夹，命令执行所在位置为WordCount.jar同一目录

因为程序中声明了
package ，所以在命令中也要 org.apache.hadoop.examples 写完整：

[html] view plain copy
hadoop jar WordCount.jar org.apache.hadoop.examples.WordCount input output

查看：
[html] view plain copy
hadoop fs -cat /output/part-r-00000
WordCount.java 源码

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);
}
}