java计数器_用户定义的java计数器

package com.mapreduce.count;

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.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;public classCountDerived {//定义一个全局的计数器，每个map,reduce都可以访问到

enumCOUNT{

LINES_COUNT,

WORDS_COUNT

}public static voidmain(String[] args) throws Exception {//1 获取configuration

Configuration configuration = newConfiguration();//2 job

Job job=Job.getInstance(configuration);//3 作业jar包

job.setJarByClass(CountDerived.class);//4 map, reduce jar 包

job.setMapperClass(CounterMap.class);//5 map 输出类型

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(IntWritable.class);//6 最终 输出类型 (reducer)

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);//7 inputformatclass , outputformatclass 输入输出入文件类型 可能决定分片信息

job.setInputFormatClass(TextInputFormat.class);

job.setOutputFormatClass(TextOutputFormat.class);//8 输入输出文件路径

FileInputFormat.setInputPaths(job,new Path("d:/input"));

FileOutputFormat.setOutputPath(job,new Path("d:/output1"));//9 job提交

job.waitForCompletion(true);

}

}