MapReduce -----WordCount演示

package com.ibeifeng.hadoop19_copy;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

//mapreduce编程框架有点像八股文的形式：主要分三部分；
//编写Map类。继承Mapper类，实现map方法
//编写Reduce类，继承Reducer类，实现reduce方法
//编写驱动帆方法run
/*
 * 原数据是
 * hadoop hdfs yarn
 * mapreduce linux hdfs
 * sqoop spark hdfs
 */
public class Wordcount {
 //Map
 public static class Map extends Mapper<LongWritable,Text,Text,IntWritable>{

  @Override
  protected void map(LongWritable key, Text value, Context context)
    throws IOException, InterruptedException {
   Text mapoutkey = new Text();
   IntWritable mapoutvalue = new IntWritable(1);
   String line = value.toString();
   String[] values = line.split(" ");
   for(String word : values){
    mapoutkey.set(word);
    context.write(mapoutkey, mapoutvalue);
   }
   
  }
   
 }
 
 
 public static class Reduce extends Reducer<Text,IntWritable,Text,IntWritable>{
  private final IntWritable reduceoutvalue = new IntWritable();
  
  @Override
  protected void reduce(Text key, Iterable<IntWritable> values,
    Context context)
    throws IOException, InterruptedException {
   
   int sum = 0;
   for(IntWritable value: values){
    sum += value.get();
   }
   reduceoutvalue.set(sum);
   context.write(key, reduceoutvalue);   
  }   
 }
 
 public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException{
  //获取Hadoop的默认配置信息
  Configuration conf = new Configuration();
  
  //创建job
  Job job = Job.getInstance(conf, "ZhouXuemei");
  
  //设置打成Jar包的类
  job.setJarByClass(Wordcount.class);
  
  //设置输入路径
  Path inpath = new Path(args[0]);
  FileInputFormat.setInputPaths(job, inpath);
  
  //设置Mapper类
  job.setMapperClass(Map.class);
  job.setMapOutputKeyClass(Text.class);
  job.setMapOutputValueClass(IntWritable.class);
  
  //设置Reducer类
  job.setReducerClass(Reduce.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);
  
  //设置输出路径
  Path outpath = new Path(args[1]);
  //判断输出路径是否存在，存在删除
  FileSystem fs = outpath.getFileSystem(conf);
  if(fs.exists(outpath)){
   fs.delete(outpath);
  }
  FileOutputFormat.setOutputPath(job, outpath);
  return job.waitForCompletion(true) ? 0:-1; 
 }
 
 public static void main(String[] args) throws ClassNotFoundException, IOException, InterruptedException{
  args = new String[]{"hdfs://node-1:8020/user/test.txt","hdfs://node-1:8020/user/output3"};
  int result = new Wordcount().run(args);
  System.out.println(result);
 }
}