hadoop第三题

该博客详细介绍了如何使用Hadoop MapReduce实现单表JOIN操作。通过一个名为`Miao`的Java程序,展示了MapReduce的Mapper和Reducer类如何处理数据,将JOIN操作分布在网络中进行。Mapper部分解析输入数据并生成键值对,Reducer则负责将JOIN操作的结果整合。此程序适用于大规模数据处理场景,尤其是在传统数据库JOIN操作效率低下的情况下。
摘要由CSDN通过智能技术生成

import java.io.IOException;

import java.util.*;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

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 org.apache.hadoop.util.GenericOptionsParser;

public class Miao {

 public static int time = 0;

 public static class Map extends Mapper<Object, Text, Text, Text>{

  public void map(Object key, Text value, Context context) throws IOException,InterruptedException{

   String child_name = new String();

   String parent_name = new String();

   String relation_type = new String();

   String line = value.toString();

   int i = 0;

   while(line.charAt(i) != ' '){

    i++;

   }

   String[] values = {line.substring(0,i),line.substring(i+1)};

   if(values[0].compareTo("child") != 0){

    child_name = values[0];

    parent_name = values[1];

    relation_type = "1";

    context.write(new Text(values[1]), new Text(relation_type+"+"+child_name+"+"+parent_name));

    relation_type = "2";

    context.write(new Text(values[0]), new Text(relation_type+"+"+child_name+"+"+parent_name));

   }

  }

 }

 public static class Reduce extends Reducer<Text, Text, Text, Text>{

  public void reduce(Text key, Iterable<Text> values,Context context) throws IOException,InterruptedException{

   if(time == 0){

    context.write(new Text("grand_child"), new Text("grand_parent"));

    time++;

   }

   int grand_child_num = 0;

   String grand_child[] = new String[10];

   int grand_parent_num = 0;

   String grand_parent[]= new String[10];

   Iterator ite = values.iterator();

   while(ite.hasNext()){

    String record = ite.next().toString();

    int len = record.length();

    int i = 2;

    if(len == 0) continue;

    char relation_type = record.charAt(0);

    String child_name = new String();

    String parent_name = new String();

    while(record.charAt(i) != '+'){

     child_name = child_name + record.charAt(i);

     i++;

    }

    i=i+1;

    while(i<len){

     parent_name = parent_name+record.charAt(i);

     i++;

    }

    if(relation_type == '1'){

     grand_child[grand_child_num] = child_name;

     grand_child_num++;

    }

    else{

     grand_parent[grand_parent_num] = parent_name;

     grand_parent_num++;

    }

   }

   if(grand_parent_num != 0 && grand_child_num != 0 ){

    for(int m = 0;m<grand_child_num;m++){

     for(int n=0;n<grand_parent_num;n++){

      context.write(new Text(grand_child[m]), new Text(grand_parent[n]));

     }

    }

   }

  }

 }

 public static void main(String[] args) throws Exception{

  Configuration conf = new Configuration();

  conf.set("fs.default.name","hdfs://localhost:9000");

  String[] otherArgs = new String[]{"input","output"};

  if (otherArgs.length != 2) {

   System.err.println("Usage: wordcount <in><out>");

   System.exit(2);

   }

  Job job = Job.getInstance(conf,"Single table join");

  job.setJarByClass(Miao.class);

  job.setMapperClass(Map.class);

  job.setReducerClass(Reduce.class);

  job.setOutputKeyClass(Text.class);

  job.setOutputValueClass(Text.class);

  FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

  FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

  System.exit(job.waitForCompletion(true) ? 0 : 1); 

 }

}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值