WritableComparable 案例部分排序

package com.sort;

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class FlowBean implements WritableComparable<FlowBean> {
    private long upFlow;
    private long downFlow;
    private long sumFlow;

    public FlowBean() {
    }

    // 排序
    public int compareTo(FlowBean bean) {
        int result;
        if (this.sumFlow > bean.getSumFlow()){
            result = -1;
        }else if (this.sumFlow < bean.getSumFlow()){
            result = 1;
        }else {
            result = 0;
        }
        return result;
    }
    // 序列化
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
    }
    // 反序列化
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readLong();
        this.downFlow = in.readLong();
        this.sumFlow = in.readLong();
    }

    public long getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }

    public long getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(long downFlow) {
        this.downFlow = downFlow;
    }

    public long getSumFlow() {
        return sumFlow;
    }

    public void setSumFlow(long sumFlow) {
        this.sumFlow = sumFlow;
    }

    @Override
    public String toString() {
        return upFlow + "\t" + downFlow + "\t" + sumFlow;
    }
}

package com.sort;

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

import java.io.IOException;

public class SortMapper extends Mapper<LongWritable, Text, FlowBean, Text> {
    FlowBean k = new FlowBean();
    Text v = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 13509468723    7335    110349    117684
        // 1. 读取一行数据
        String line = value.toString();
        String[] words = line.split("\t");
        // 2.设置 key
        k.setUpFlow(Long.parseLong(words[1]));
        k.setDownFlow(Long.parseLong(words[2]));
        k.setSumFlow(Long.parseLong(words[3]));
        // 3.设置 value
        v.set(words[0]);
        // 4.写入
        context.write(k, v);
    }
}

package com.sort;

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

public class PhonePartitioner extends Partitioner<FlowBean, Text> {
    @Override
    public int getPartition(FlowBean bean, Text text, int numPartitions) {
        // 136、137、138、139
        // 1.注意 text 是 电话
        int partition;
        String phonePre = text.toString().substring(0, 3);
        // 2.分区
        if ("136".equals(phonePre)){
            partition = 0;
        }else if ("137".equals(phonePre)){
            partition = 1;
        }else if ("138".equals(phonePre)){
            partition = 2;
        }else if ("139".equals(phonePre)){
            partition = 3;
        }else {
            partition = 4;
        }
        return partition;
    }
}

package com.sort;

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

import java.io.IOException;

public class SortReducer extends Reducer<FlowBean, Text,Text,FlowBean> {
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
        // 1. 循环写入
        for (Text value : values) {
            context.write(value, key);
        }
    }
}

package com.sort;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 java.io.IOException;

public class SortDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"E:\\a\\output", "E:\\a\\output2"};
        // 1.获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        // 2.设置jar
        job.setJarByClass(SortDriver.class);
        // 3.关联mapper和reducer
        job.setMapperClass(SortMapper.class);
        job.setReducerClass(SortReducer.class);
        // 4.设置mapper输出的k v
        job.setMapOutputKeyClass(FlowBean.class);
        job.setMapOutputValueClass(Text.class);
        // 5.设置整体输出的 k, v
        job.setOutputKeyClass(Text.class);
        job.setOutputKeyClass(FlowBean.class);
        // 8. 设置分区
        job.setPartitionerClass(PhonePartitioner.class);
        // 9.设置 NumReduceTask
        job.setNumReduceTasks(5);
        // 6.设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // 7.提交job
        boolean wait = job.waitForCompletion(true);
        System.exit(wait? 0: 1);
    }
}