1.不说了,上代码.先是POM , 我这是 hadoop3.2.1的

<?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>org.example</groupId>
    <artifactId>Hadoop3.2.1</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>7</source>
                    <target>7</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>3.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>3.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>3.2.1</version>
    </dependency>
    <dependency>
        <groupId>commons-logging</groupId>
        <artifactId>commons-logging</artifactId>
        <version>1.2</version>
    </dependency>
    </dependencies>
</project>

2.这是Map任务 按数字大小分区 ,
原本是生成的5位以内的正整数 20万个 ,
做自定义分区实验
其中1-10000位0区 , 10000-20000为1区 , 其余为2区
这是代码

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;

public class TotalSortV2 extends Configured implements Tool {
    static class SimpleMapper extends Mapper<LongWritable, Text, IntWritable, IntWritable> {
        @Override
        protected void map(LongWritable key, Text value,
                           Context context) throws IOException, InterruptedException {
            IntWritable intWritable = new IntWritable(Integer.parseInt(value.toString()));
            context.write(intWritable, intWritable);
        }
    }

    static class SimpleReducer extends Reducer<IntWritable, IntWritable, IntWritable, NullWritable> {
        @Override
        protected void reduce(IntWritable key, Iterable<IntWritable> values,
                              Context context) throws IOException, InterruptedException {
            for (IntWritable value : values)
                context.write(value, NullWritable.get());
        }
    }

    public static class IteblogPartitioner extends Partitioner<IntWritable, IntWritable> {
        @Override
        public int getPartition(IntWritable key, IntWritable value, int numPartitions) {
            int keyInt = Integer.parseInt(key.toString());
            if (keyInt < 10000) {
                return 0;
            } else if (keyInt < 20000) {
                return 1;
            } else {
                return 2;
            }
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        
        Job job = Job.getInstance(getConf());
        job.setJarByClass(TotalSortV2.class);
        FileInputFormat.addInputPath(job, new Path("hdfs://node2:8020/have"));
        FileOutputFormat.setOutputPath(job, new Path("hdfs://node2:8020/have2"));

        job.setMapperClass(SimpleMapper.class);
        job.setReducerClass(SimpleReducer.class);
        job.setPartitionerClass(IteblogPartitioner.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(NullWritable.class);
        job.setNumReduceTasks(3);
        job.setJobName("dw_subject");
        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new TotalSortV2(), args);
        System.exit(exitCode);
    }
}

3.我是在idea上调试 ,看能不能运行 ,结果不能. 解决方法如下

image.png