hadoop二次排序案例,二次排序后寻找key字段相同,value最大值再输出到文件中。

二次排序就是首先按照第一字段排序，然后再对第一字段相同的行按照第二字段排序，注意不能破坏第一次排序的结果。
1). 保存文件第二字段与第四字段:

package com.GroupOrder;

import org.apache.hadoop.io.WritableComparable;

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

public class OrderBean implements WritableComparable<OrderBean> {
    private String Order_id;    //商品id
    private Double Order_price;    //商品价格

    public OrderBean() {
        super();
    }

    public OrderBean(String order_id, Double order_price) {
        Order_id = order_id;    //商品种类
        Order_price = order_price;  //销售额
    }

    public int compareTo(OrderBean orderBean) {
        int result = Order_id.compareTo(orderBean.getOrder_id());   //按照Ascill表进行比较
        //第一次排序: 先对商品种类进行升序排序(该值作为key)
        if (result > 0) {
            result = 1;
        } else if (result < 0) {
            result = -1;
        } else {
            //第二次排序:再对销售额进行降序排序(该值作为value,不影响商品种类排序)

            if (Order_price > orderBean.getOrder_price()) {
                result = -1;
            } else if (Order_price < orderBean.getOrder_price()) {
                result = 1;
            } else {
                result = 0;
            }
        }
        return result;
    }

    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(Order_id);
        dataOutput.writeDouble(Order_price);

    }

    public void readFields(DataInput dataInput) throws IOException {
        Order_id = dataInput.readUTF();
        Order_price = dataInput.readDouble();

    }

    public Double getOrder_price() {
        return Order_price;
    }

    public void setOrder_price(Double order_price) {
        Order_price = order_price;
    }

    public String getOrder_id() {
        return Order_id;
    }

    public void setOrder_id(String order_id) {
        Order_id = order_id;
    }


    @Override
    public String toString() {
        return Order_id + '\t' +
                Order_price;
    }
}

序列化与反序列化顺序必须一致,你是用那种方式将数据写入内存中(序列化),
那就一定得用这种方式将数据从内存中读取出来(今天写入一个String类型数据到内存中(writeChars方法),完事之后，完了我不知道用什么方法从内存读取数据了,就用了一个readUTF方法,主程序一运行
Order_id = dataInput.readUTF();
Order_price = dataInput.readDouble();
这两变量为null,悲剧了…
所以还是序列化用什么方法将数据写入内存中,就用什么方法从内存中读取数据.不过我还是没明白序列化中writeChars 方法对应的 反序列方法怎么写,我的提示并没有它的反序列方法

2. .Map程序

package com.GroupOrder;

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

import java.io.IOException;

public class OrderMapper extends Mapper<LongWritable, Text,OrderBean, NullWritable> {

    OrderBean k = new OrderBean();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //0	Office Supplies	2	408.3


        //1.获取一行
        String line = value.toString();

        //2.分割
        String[] fields = line.split(",");
        String Order_id = fields[1];
        Double Order_price = Double.parseDouble(fields[3]);

        //3. 封装
        k.setOrder_id(Order_id);
        k.setOrder_price(Order_price);

        //4.写出

        context.write(k,NullWritable.get());
    }
}

Map程序的输出类型OrderBean, NullWritable.NullWritable是一个特殊类，实现方法为空实现,不从数据流中读数据，也不写入数据,只充当占位符,NullWritable.get()获取的是一个空值(理解起来就是将OrderBean中的字段都作为key,便于排序.但value值我们不给它值不合适,写入空值无疑是一个好方法)

3. Reduce程序:

package com.GroupOrder;

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

import java.io.IOException;

public class OrderReducer extends Reducer<OrderBean, NullWritable,OrderBean,NullWritable> {

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

        context.write(key,NullWritable.get());
    }
}

4. 主程序

package com.GroupOrder;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
     args = new String[]{"F:\\scala\\Workerhdfs\\input5","F:\\scala\\Workerhdfs\\output5"};
        //1.获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        
        //2.设置jar路径
        job.setJarByClass(OrderDriver.class);

        //3.关联mapper和reducer
        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);
        
        //4 设置mapper输出的key和value类型
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        //5. 设置最终输出的key和value类型
        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        //6.设置输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));


        //7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

效果如下:

5. .寻找key相同,value最大值输出到文件中,添加以下程序：

package com.GroupOrder;

import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;

public class OrderGroupComparator extends WritableComparator {
     
      protected OrderGroupComparator(){
          super(OrderBean.class,true);
      }

    @Override
    public int compare(WritableComparable a, WritableComparable b) {

        //只要商品种类相同，就认为是相同的key

        OrderBean aBean = (OrderBean) a;
        OrderBean bBean = (OrderBean) b;

        int result = aBean.getOrder_id().compareTo(bBean.getOrder_id());
        if (result > 0) {
            result = 1;
        } else if (result < 0) {
            result = -1;
        } else {
            result = 0;
        }
        return result;

    }
}

在4.主程序中添加一行代码,设置reduce端的分组:

package com.GroupOrder;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 OrderDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
     args = new String[]{"F:\\scala\\Workerhdfs\\input5","F:\\scala\\Workerhdfs\\output6"};
        //1.获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        
        //2.设置jar路径
        job.setJarByClass(OrderDriver.class);

        //3.关联mapper和reducer
        job.setMapperClass(OrderMapper.class);
        job.setReducerClass(OrderReducer.class);
        
        //4 设置mapper输出的key和value类型
        job.setMapOutputKeyClass(OrderBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        //5. 设置最终输出的key和value类型
        job.setOutputKeyClass(OrderBean.class);
        job.setOutputValueClass(NullWritable.class);

        //设置 reduce端的分组
      job.setGroupingComparatorClass(OrderGroupComparator.class);

        //6.设置输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));


        //7.提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

效果如下:

jar包形式,运行在hadoop集群上:
这里将jar包上传到hadoop文件系统…

hadoop文件系统新建一个目录,并且将测试文件上传至此目录下，提交到yarn上运行.

查看分区文件内容: