Hadoop之MR简单例子（WordCount）

一、Map/Reduce

package com.mrtest.hadoop;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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 java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;


/**
 * 单词计数
 * @author xuyao
 */
public class WordCount {

    public static class WordCountMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable ONE = new IntWritable(1);
        private Text word = new Text();

        @Override
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, ONE);
            }
        }

    }

    public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            IntWritable val;
            for (Iterator i = values.iterator(); i.hasNext(); sum += val.get()) {
                val = (IntWritable) i.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }

    public static void main(String[] args) throws Exception {
        System.setProperty("hadoop.home.dir", "D:\hadoop-common-2.7.3");
        Configuration configuration = new Configuration();

        Job job = Job.getInstance(configuration, "WordCount");
        job.setJarByClass(WordCount.class);

        //设置Map和Reduce类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置reduce输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置map输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        String[] otherArgs = new String[]{"input/dream.txt", "output"};
        Path path = new Path(otherArgs[1]);
        FileSystem fileSystem = path.getFileSystem(configuration);
        if (fileSystem.exists(path)) {
            fileSystem.delete(path, true);
        }
        // 设置输入/输出数据存放位置
        FileInputFormat.setInputPaths(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }

}

二、结果

三，遇到的问题

报错语句1：

HADOOP_HOME or hadoop.home.dir are not set

解决方法：

1，下载winutils.exe包：https://github.com/SweetInk/hadoop-common-bin 。然后将其放到hadoop的包（意思就是说，windows中需要解压hadoop的安装包）的bin目录下。

2，在程序起始处添加语句：

System.setProperty("hadoop.home.dir", "D:\\hadoop-common-2.7.3");

3，在system32文件夹下添加hadoop.dll文件 

报错语句2：

org.apache.hadoop.mapred.FileAlreadyExistsException

解决方法：

输出目录是运行时程序生成的，删除就行了

报错语句3：

java.lang.UnsatisfiedLinkError

解决方法：

原因是hadoop版本不一致，程序用的hadoop jar 包的版本是2.7.3，而我之前引入的hadoop.home的文件版本是2.2.0

重新下载hadoop包并配置hadoop_home 或者重新引入jar包即可

一定要注意细节！这个错误网上的说法五花八门，花了好久才找出来