日志

如何根据安装包自带wordcount例子，写相关mapredcue

已有 1783 次阅读2015-7-6 14:45

问题导读

1.如何查看hadoop带自带例子源码？
2.本文使用的什么工具进行反编译？
3.hadoop2.7如何实例化job的？

原文连接：

如何反编译hadoop2.x(2.7为例)安装包自带wordcount

我们在自己写wordcount的过程中，最烦恼的一个问题，api兼容问题。
从别的地方直接copy过来不能直接使用，那么如何变成我们自己的，该如何与当前版本兼容，我们是该使用job类，还是jobconf类；是使用new job(,);还是使用job.getInstane（）。
这里交给大家一个方法，就是反编译安装包自带的例子。
例子的路径：

[Bash shell] 纯文本查看复制代码

1	`/usr/hadoop-2.7.0/share/hadoop/mapreduce`

hadoop-2.7.0.tar.gz
链接：http://pan.baidu.com/s/1eQ1sUjS 密码：0h97

jar包下载：
hadoop-mapreduce-examples-2.7.0
链接：http://pan.baidu.com/s/1qWOdiEC 密码：qfrx

直接解压，看到下面内容：

上面是编译的文件。我们该如何看到源码

我们下载jad

jad.rar (160.1 KB, 下载次数: 0)

下载，解压会看到jad.exe

将jad.exe放到jdk的bin目录下

然后进入
通过cmd进入C:\Program Files\Java\jdk1.7.0_67\bin

执行命令：

C:\Program Files\Java\jdk1.7.0_67\bin>Jad -d D:\ -s wordcount.java -8 C:\Users\A
dministrator\Desktop\hadoop-mapreduce-examples-2.7.0\org\apache\hadoop\examples\
WordCount.class

上面命令有些复杂，简化：
Jad -d c:\test -s .java -8 HelloWorld.class

Jad -d 输出目录 -s 输出文件名 -8 被反翻译文件

最后文件在D：\找到

文件内容：

[Bash shell] 纯文本查看复制代码

// Decompiled by Jad v1.5.8e2. Copyright 2001 Pavel Kouznetsov.
// Jad home page: [url=http://kpdus.tripod.com/jad.html]http://kpdus.tripod.com/jad.html[/url]
// Decompiler options: packimports(3) ansi 
// Source File Name:   WordCount.java
 
package org.apache.hadoop.examples;
 
import java.io.IOException;
import java.io.PrintStream;
import java.util.Iterator;
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.*;
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 IntSumReducer extends Reducer
    {
 
        public void reduce(Text key, Iterable values, org.apache.hadoop.mapreduce.Reducer.Context context)
            throws IOException, InterruptedException
        {
            int sum = 0;
            for(Iterator i$ = values.iterator(); i$.hasNext();)
            {
                IntWritable val = (IntWritable)i$.next();
                sum += val.get();
            }
 
            result.set(sum);
            context.write(key, result);
        }
 
        public volatile void reduce(Object x0, Iterable x1, org.apache.hadoop.mapreduce.Reducer.Context x2)
            throws IOException, InterruptedException
        {
            reduce((Text)x0, x1, x2);
        }
 
        private IntWritable result;
 
        public IntSumReducer()
        {
            result = new IntWritable();
        }
    }
 
    public static class TokenizerMapper extends Mapper
    {
 
        public void map(Object key, Text value, org.apache.hadoop.mapreduce.Mapper.Context context)
            throws IOException, InterruptedException
        {
            for(StringTokenizer itr = new StringTokenizer(value.toString()); itr.hasMoreTokens(); context.write(word, one))
                word.set(itr.nextToken());
 
        }
 
        public volatile void map(Object x0, Object x1, org.apache.hadoop.mapreduce.Mapper.Context x2)
            throws IOException, InterruptedException
        {
            map(x0, (Text)x1, x2);
        }
 
        private static final IntWritable one = new IntWritable(1);
        private Text word;
 
 
        public TokenizerMapper()
        {
            word = new Text();
        }
    }
 
 
    public WordCount()
    {
    }
 
    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> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(org/apache/hadoop/examples/WordCount);
        job.setMapperClass(org/apache/hadoop/examples/WordCount$TokenizerMapper);
        job.setCombinerClass(org/apache/hadoop/examples/WordCount$IntSumReducer);
        job.setReducerClass(org/apache/hadoop/examples/WordCount$IntSumReducer);
        job.setOutputKeyClass(org/apache/hadoop/io/Text);
        job.setOutputValueClass(org/apache/hadoop/io/IntWritable);
        for(int i = 0; i < otherArgs.length - 1; i++)
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));[/i]
 
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}