MapReduce代码编写总览

一.pom.xml依赖

<dependencies>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.7.5</version>
    </dependency>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.7.5</version>
    </dependency>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.7.5</version>
    </dependency>

    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>2.7.5</version>
    </dependency>

    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>RELEASE</version>
    </dependency>
    
</dependencies>

二.Mapper

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

import java.io.IOException;

public class WordCountMapper extends Mapper<LongWritable,Text,Text,LongWritable> {

    private LongWritable longWritable = new LongWritable();
    private Text text = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] words = value.toString().split(",");
        for(String word:words){
            longWritable.set(1);
            text.set(word);
            context.write(text,longWritable);
        }
    }
}

三.Reducer

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text,LongWritable,Text,LongWritable> {

    private LongWritable longWritable = new LongWritable();


    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

        long num = 0;
        for(LongWritable value:values){
            num += value.get();
        }
        longWritable.set(num);
        context.write(key,longWritable);

    }
}

四.JobMain

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class JobMain extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {
        Job job = Job.getInstance(super.getConf(),"workcount");

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://node1:8020/wordcount"));

        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(WordCountReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("hdfs://node1:8020/wordcount_out"));

        boolean bl = job.waitForCompletion(true);
        return bl ? 0:1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();

        int run = ToolRunner.run(configuration,new JobMain(),args);
        System.exit(run);
    }
}

注：
1.若想要使用本地模式运行，则仅需要将输入与输出目录更改为本地目录即可，如：

TextOutputFormat.setOutputPath(job,new Path("file:///D:\mapreduce\output"));

2.输出时的目标目录不能存在，否则会警告

五.运行方式

1.点击Lifecycle内的package进行打包
2.将jar包上传至虚拟机，可使用命令rz直接上传
3.运行jar包，使用命令：
hadoop jar jar包名 Main完整路径，如：
hadoop jar wordcount-1.0-SNAPSHOT.jar top.fullstar.mapreduce.JobMain
4.运行完毕后从浏览器端即可下载结果