hadoop使用idea编写mapreduce操作远程服务器的hadoop上的hdfs

首先通过idea创建一个maven文件
导入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>cn.yw</groupId>
    <artifactId>cn.yw</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.3</version>
        </dependency>


        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.7.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.7.3</version>
        </dependency>

        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>
    </dependencies>

</project>

版本号不需要和自己的hadoop版本一致
然后做个最简单的单词计数
然后开始写map层

package cn.yw;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class WordCount extends Mapper<LongWritable, Text,Text, IntWritable>{

    protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException {
        //设置分隔符
        String[] words = value.toString().split("\t");

        //每个字存入
        for(String word : words){
            context.write(new Text(word),new IntWritable(1));
        }
    }
}


导入的包要注意都是hadoop的包
然后写Reduce层
package cn.yw;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;
import java.util.Iterator;

public class WordREducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    protected  void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
        int Count = 0;

        Iterator<IntWritable> iterator = values.iterator();

        //迭代器计数
        while (iterator.hasNext()) {
            IntWritable value = iterator.next();
            Count += value.get();
        }

        context.write(key, new IntWritable());
    }
}

最后写main层整合map和reduce

package cn.yw;


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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import javax.security.auth.login.AppConfigurationEntry;

import java.io.FileInputStream;
import java.net.URI;

public class Wc {

    public static void main(String[] args) throws Exception{

        //hadoop用户不然不能拥有写进去的权限
        System.setProperty("HADOOP_USER_NAME","hadoop");

        //hdfs的地址
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://106.15.179.224:9000");
        configuration.set("dfs.client.use.datanode.hostname", "true");

        //输入输出的文件m目录
        String input="/input/text.txt";
        String output="/output/";

//        FileUtil.deleteDir(output);
        Job job = Job.getInstance(configuration);

        //主函数位置
        job.setJarByClass(Wc.class);
        //map函数位置
        job.setMapperClass(WordCount.class);
        job.setReducerClass(WordREducer.class);
        //map设置出来的
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //reduce设置出来的
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //删除output文件夹
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://106.15.179.224:9000"),configuration,"hadoop");
        Path outputPath = new Path(output);
        if(fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath,true);
        }

        FileInputFormat.setInputPaths(job,new Path(input));
        FileOutputFormat.setOutputPath(job, outputPath);

        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : -1);

    }
}

遇到的坑如下
首先9000端口访问不了
在服务器的host文件下配置0.0.0.0 允许远程访问

然后还要在自己电脑上下载个hadoop和配置自己的本机host 配置主机名对应服务器的ip这个超级重要被坑了一天