mapreduce-二次排序 -夜幕思年华_mapreduce二次排序-CSDN博客

本文链接：https://blog.csdn.net/qq_24137609/article/details/90693146

package com.doop.gw.hadoop.reducer.secondOrder;

import java.io.ByteArrayOutputStream;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.junit.Test;


public class SecondarySort {

  public static class IntPair implements WritableComparable<IntPair> {
    int first;
    int second;
    
    public void set(int left, int right) {
      first = left;
      second = right;
    }

    public int getFirst() {
      return first;
    }
    
    @Override
    //反序列化，从流中的二进制转换成IntPair
    public void readFields(DataInput in) throws IOException {
      // TODO Auto-generated method stub
      first = in.readInt();
      second = in.readInt();
    }

    @Override
    //序列化，将IntPair转化成使用流传送的二进制
    public void write(DataOutput out) throws IOException {
      // TODO Auto-generated method stub
      out.writeInt(first);
      out.writeInt(second);
    }

    @Override
    //key的比较
    //这个方法是用于二次排序的。

    public int compareTo(IntPair o) {
      // TODO Auto-generated method stub
      if (first != o.first) {
        //如果FIRST不相同，进行对比后排序
        return first < o.first ? -1 : 1;
      } else if (second != o.second) {
        //如果first相等，按second排序，至于是升序还是降序，你可自已根据返回值确定
        return second < o.second ? -1 : 1;
      } else {
        return 0;
      }
    }

    //新定义类应该重写的两个方法
    @Override
    //The hashCode() method is used by the HashPartitioner (the default partitioner in MapReduce)
    public int hashCode() {
      return first * 157 + second;
    }

    @Override
    public boolean equals(Object right) {
      if (right == null) {
        return false;
      }
      if (this == right) {
        return true;
      }
      if (right instanceof IntPair) {
        IntPair r = (IntPair) right;
        return r.first == first && r.second == second;
      } else {
        return false;
      }
    }
  }

  /**
   * 分区函数类。根据first确定Partition。
   */
  public static class FirstPartitioner extends Partitioner<IntPair, IntWritable> {

    @Override
    public int getPartition(IntPair key, IntWritable value, int numPartitions) {
      return Math.abs(key.getFirst() * 127) % numPartitions;
    }
  }
  
  public static class GroupingComparator extends WritableComparator {
    protected GroupingComparator() {
      super(IntPair.class, true);
    }

    @Override
    //Compare two WritableComparables.
    public int compare(WritableComparable w1, WritableComparable w2) {
      IntPair ip1 = (IntPair) w1;
      IntPair ip2 = (IntPair) w2;
      int l = ip1.getFirst();
      int r = ip2.getFirst();
      return l == r ? 0 : (l < r ? -1 : 1);
    }
  }


  // 自定义map
  public static class Map extends Mapper<LongWritable, Text, IntPair, IntWritable> {
    private final IntPair intkey = new IntPair();
    private final IntWritable intvalue = new IntWritable();
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      String line = value.toString();
      StringTokenizer tokenizer = new StringTokenizer(line);
      int left = 0;
      int right = 0;
      if (tokenizer.hasMoreTokens()) {
        left = Integer.parseInt(tokenizer.nextToken());
        if (tokenizer.hasMoreTokens()) {
          right = Integer.parseInt(tokenizer.nextToken());
        }
        intkey.set(left, right);
        intvalue.set(right);
        context.write(intkey, intvalue);
      }
    }
  }

  // 自定义reduce
  public static class Reduce extends Reducer<IntPair, IntWritable, Text, IntWritable> {
    private final Text left = new Text();
    private static final Text SEPARATOR = new Text(
        "------------------------------------------------");

    public void reduce(IntPair key, Iterable<IntWritable> values, Context context)
        throws IOException, InterruptedException {
      context.write(SEPARATOR, null);
      left.set(Integer.toString(key.getFirst()));
      for (IntWritable val : values) {
        context.write(left, val);
      }
    }
  }

  static final String INPUT_PATH = "hdfs://192.168.33.104:8020/input/secondSort";
  static final String OUT_PATH = "hdfs://192.168.33.104:8020/output";

  public static void main(String[] args)
      throws IOException, InterruptedException, ClassNotFoundException, URISyntaxException {
    // TODO Auto-generated method stub
    // 读取hadoop配置
    Configuration conf = new Configuration();
    FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
    Path outPath = new Path(OUT_PATH);
    if (fileSystem.exists(outPath)) {
      fileSystem.delete(outPath, true);
    }

    // 实例化一道作业
    Job job = new Job(conf, "secondarysort");
    job.setJarByClass(SecondarySort.class);
    // Mapper类型
    job.setMapperClass(Map.class);
    // 不再需要Combiner类型，因为Combiner的输出类型<Text, IntWritable>对Reduce的输入类型<IntPair, IntWritable>不适用
    //job.setCombinerClass(Reduce.class);
    // Reducer类型
    job.setReducerClass(Reduce.class);
    // 分区函数
    job.setPartitionerClass(FirstPartitioner.class);
    // 分组函数
    job.setGroupingComparatorClass(GroupingComparator.class);

    // map 输出Key的类型
    job.setMapOutputKeyClass(IntPair.class);
    // map输出Value的类型
    job.setMapOutputValueClass(IntWritable.class);
    // rduce输出Key的类型，是Text，因为使用的OutputFormatClass是TextOutputFormat
    job.setOutputKeyClass(Text.class);
    // rduce输出Value的类型
    job.setOutputValueClass(IntWritable.class);

    // 将输入的数据集分割成小数据块splites，同时提供一个RecordReder的实现。
    job.setInputFormatClass(TextInputFormat.class);
    // 提供一个RecordWriter的实现，负责数据输出。
    job.setOutputFormatClass(TextOutputFormat.class);
    // 输入hdfs路径
    FileInputFormat.setInputPaths(job, new Path(INPUT_PATH));
    // 输出hdfs路径
    FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));
    // 提交job
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }


  /**
   * 读取文件
   */
  @Test
  public void testRead() {
    Configuration conf = new Configuration();
    try {
      // 根据配置文件创建HDFS对象
      conf.set("fs.defaultFS", "hdfs://192.168.33.104:8020"); //远程需要设定
      FileSystem fs = FileSystem.get(conf);
      Path path = new Path("hdfs://192.168.33.104:8020/output/part-r-00000");
      FSDataInputStream fis = fs.open(path);
      ByteArrayOutputStream baos = new ByteArrayOutputStream();
      IOUtils.copyBytes(fis, baos, 1024);
      fis.close();
      System.out.println(new String(baos.toByteArray()));
    } catch (IOException e) {
      e.printStackTrace();
    }
  }
}