1.hadoop-window的安装这里不过多赘述 运行成功之后的结果如下图

2.在idea中新建一个maven项目

pom.xml

<xml version="1.0" encoding="UTF-8">
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.test</groupId>
    <artifactId>wordcount</artifactId>
    <version>1.0-SNAPSHOT</version>
    <packaging>jar</packaging>
    <url>http://maven.apache.org</url>


    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>3.8.1</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-client</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.8.0</version>
        </dependency>
        <dependency>
            <groupId>io.netty</groupId>
            <artifactId>netty-common</artifactId>
            <version>4.1.5.Final</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>${project.artifactId}</finalName>
    </build>

</project>

新建一个wordcount类

package com.hadoop.wordcount;
import org.apache.hadoop.fs.FileUtil;
import org.apache.hadoop.io.IntWritable;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.util.Iterator;
import java.util.StringTokenizer;

/**
 * Created by bee on 8/30/18.
 */
public class WordCount {


    public static class TokenizerMapper extends
            Mapper<Object, Text, Text, IntWritable> {


        public static final 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()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }

    }

    public static class IntSumReduce 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;
            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 IOException, ClassNotFoundException, InterruptedException {

        Configuration conf = new Configuration();
        //设置hdfs地址之后就会自动寻找数据然后进行mapreduce操作,输入地址不能自己新建，程序运行会自动创建
        String[] otherArgs = new String[]{"hdfs://localhost:9000/input/dream.txt","hdfs://localhost:9000/output/wordcount/"};
        /*String[] otherArgs = new String[]{"input/dream.txt","output"};*/
        if (otherArgs.length != 2) {
            System.err.println("Usage:Merge and duplicate removal <in> <out>");
            System.exit(2);
        }

        Job job = Job.getInstance(conf, "WordCount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setReducerClass(WordCount.IntSumReduce.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);
    }
}

在hdf地址中创建input文件夹

hadoop fs -mkdir /input

将本地文件dream拷贝到input文件夹下

hadoop fs -put F:\dream.txt /input

点进运行idea中的worcount

运行成功之后

点击之后下载，结果如下

至此wordcount运行完成