编写MR
编写Mapper
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
/**
* Mapper过程
* Mapper是一个泛型类,分别代表:输入键,输入值,输出键和输出值类型
*/
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
Text keyOut = new Text();
IntWritable valueOut = new IntWritable();
String[] arr = value.toString().split(" ");
for (String s : arr) {
keyOut.set(s);
valueOut.set(1);
context.write(keyOut, valueOut);
}
}
}
编写Reducer
package com.yuangh.hadoop.mr.demo;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
*Map的输出就是Reduce的输入
*
*/
public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
/**
* reduce
*/
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int count = 0;
for (IntWritable iw : values) {
count = count + iw.get();
}
//输出
context.write(key, new IntWritable(count));
}
}
主函数
package com.yuangh.hadoop.mr.demo;
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;
public class WCApp {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//设置job的各种属性
job.setJobName("WCApp"); //作业名称
job.setJarByClass(WCApp.class); //搜索类
job.setInputFormatClass(TextInputFormat.class); //设置输入格式
//设置输入路径
FileInputFormat.addInputPath(job, new Path(args[0]));
//设置输出路径
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(WCMapper.class); //mapper类
job.setReducerClass(WCReducer.class); //reducer类
job.setNumReduceTasks(1); //reduce个数
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
}
}
详细过程解析(Local模式运行MR流程)
- 创建外部Job(mapreduce.Job),设置配置信息
- 通过jobsubmitter将job.xml + split等文件写入临时目录
- 通过jobSubmitter提交job给localJobRunner
- LocalJobRunner将外部Job 转换成成内部Job
- 内部Job线程,开放分线程执行job
- job执行线程分别计算Map和reduce任务信息并通过线程池孵化新线程执行MR任务
在hadoop集群上运行MR程序
-
将本地项目使用maven打包成jar文件
-
将打包好的jar文件放入到集群中(共享目录就行)
-
运行 hadoop jar 命令
hadoop jar MyHadoop.jar com.yuangh.hadoop.mr.WCApp hdfs://s201/user/centosmin0/wc/data hdfs://s201/user/centosmin0/wc/out
http://s201:50070查看
http://s201:8088端口查看