MapReduce05——分区

1、有words.txt文件内容如下，其中以制表符分割，需求：利用mapreduce按照性别分区

Smith	male
Alice	female
Tony	male
Doris	female

2、分析
map阶段：
（1）、mapreduce逐行读取文件，得到每行的值
（2）、以制表符分割后，姓名为key，性别为value输出
reduce阶段：
（1）、直接输出即可
自定义分区类：

package com.qujiuge.partition;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

/**
 * 这里的两个Text对应的是map输出的类型
 */
public class Partition extends Partitioner<Text, Text> {
    @Override
    public int getPartition(Text key, Text value, int i) {
        if ("female".equals(value.toString())) return 0;
        return 1;
    }
}

3、创建maven工程后，添加如下依赖

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.9.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.9.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.9.2</version>
        </dependency>
    </dependencies>

4、编写mapreduce程序

package com.qujiuge.partition;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.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;

public class Driver {
    static class PartitionMapper extends Mapper<LongWritable, Text, Text, Text> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] fields = line.split("\t");
            if (fields.length == 2) {
                context.write(new Text(fields[0]), new Text(fields[1]));
            }
        }
    }

    static class PartitionReducer extends Reducer<Text, Text, Text, Text> {
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            super.reduce(key, values, context);
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration config = new Configuration();
        Job job = Job.getInstance(config);

        job.setJarByClass(com.qujiuge.sort_.Driver.class);

        job.setMapperClass(PartitionMapper.class);
        job.setReducerClass(PartitionReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        job.setPartitionerClass(Partition.class); // 指定自定义分区类
        job.setNumReduceTasks(2); // 同时指定相应数量的reduce

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        FileSystem fs = FileSystem.get(config);
        Path outPath = new Path(args[1]);
        if (fs.exists(outPath)) {
            fs.delete(outPath, true);
        }
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, outPath);

        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

项目结构如下：

5、将words.txt文件上传到hdfs中

6、将项目打包成jar文件后，用hadoop jar命令执行

运行结果：