一、下载安装hadoop2.7.1

?下述两种版本任选其一下载，建议下载第二种，不需要做加入.dll和.exe操作，但是空间大。我都下了，使用时，只需要把环境变量路径变一下即可。

?1.版本hadoop2.7.1下载

?链接:
https://archive.apache.org/dist/hadoop/core/hadoop-2.7.1/
在这里插入图片描述
emsp;解压 D:\Env\hadoop-2.7.1

在这里插入图片描述

?2.其他版本下载

?链接:
https://mirrors.tuna.tsinghua.edu.cn/apache/hadoop/common/
?下面以2.10.1为例:
在这里插入图片描述

?我安装的路径D:\Env\hadoop-2.10.2

?把这个路径给复制了。
?最后还要添加hadoop.dll和winutils.exe文件到你hadoop的bin目录下
?再此处下载https://github.com/steveloughran/winutils
?解压之后，找到对应版本的放进去

二、配置环境变量

?D:\Env\hadoop-2.10.2

在这里插入图片描述
?%HADOOP_HOME%\bin

三、IDEA运行单词计算

?创建一个Maven项目，并且再pom.xml加入如下依赖:

<properties>
        <java.version>1.8</java.version>
<!--        <hadoop.version>2.7.1</hadoop.version>-->
        <hadoop.version>2.10.2</hadoop.version>
    </properties>
    <dependencies>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-api</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

</dependencies>

?创建一个WordCount的类
?官网上也有，只需要把如下改成自己本地的输入输出地址即可
在这里插入图片描述
? 测试文件: D:\\test\\a.txt


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 java.io.IOException;
import java.util.StringTokenizer;

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();

        @Override
        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();

        @Override
        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();
        Job job = Job.getInstance(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(  "D:\\test\\a.txt" ));
        FileOutputFormat.setOutputPath(job, new Path("D:\\test\\b" ));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}