Hadoop基于词频统计例子

package com.imooc.bigdata.hadoop.project.mrv2;

import com.imooc.bigdata.hadoop.project.utils.LogParser;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 java.io.IOException;
/**

• @author XJX

• 通过ip解析之省份浏览器统计
  */
  public class PVStatV2App {

  // Driver端的代码：八股文
  public static void main(String[] args) throws Exception{
  Configuration configuration = new Configuration();

   Job job = Job.getInstance(configuration);
   job.setJarByClass(PVStatV2App.class);
  
   job.setMapperClass(MyMapper.class);
   job.setReducerClass(MyReducer.class);
  
   job.setMapOutputKeyClass(Text.class);
   job.setMapOutputValueClass(LongWritable.class);
  
   job.setOutputKeyClass(Text.class);
   job.setOutputValueClass(LongWritable.class);
  
   FileInputFormat.setInputPaths(job, new Path("input/etl"));
   FileOutputFormat.setOutputPath(job, new Path("output/v2/pvstat/"));
  
   job.waitForCompletion(true);
  

  }

  static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

   private LogParser parser;
   private LongWritable ONE = new LongWritable(1);
   private Text KEY = new Text("key");
   /**
    * 初始化数据
    *
    * @param context
    * @throws IOException
    * @throws InterruptedException
    */
   @Override
   protected void setup(Context context) throws IOException, InterruptedException {
       parser = new LogParser();
   }
   /**
    * 日志处理
    *
    * @param key
    * @param value
    * @param context
    * @throws IOException
    * @throws InterruptedException
    */
   @Override
   protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
       context.write(KEY, ONE);
   }
  

  }
  /**

  • 统计key
    */
    static class MyReducer extends Reducer<Text, LongWritable, NullWritable, LongWritable> {

    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {

    long count = 0;
    for(LongWritable access : values) {
    count++;
    }
    context.write(NullWritable.get(), new LongWritable(count));

    }
    }

}