通过map reduce统计应用ip访问次数

通过map reduce统计应用ip访问次数

1:数据源文件准备

数据源文件：access.log

内容如下：部分：

  

2：上传数据源文件到hdfs中

将此文件上传到hadoop hdfs文件系统中：

  

 hadoop fs -put access.log /ip/input/

3：编写map reduce程序：

     

package com.wangmm.hadoop.mapreduce;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

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

public class IPCounter {
	
	static final String IN_PUT = "hdfs://icity0:9000/ip/input";
	static final String OUT_PUT = "hdfs://icity0:9000/ip/output";
	
	public static void main(String[] args) throws IOException, URISyntaxException, InterruptedException, ClassNotFoundException {
		
		Configuration conf = new Configuration();
		
		FileSystem fileSystem = FileSystem.get(new URI(IN_PUT), conf);
		
		Path outPath = new Path(OUT_PUT);
		
		if(fileSystem.exists(outPath)){
			fileSystem.delete(outPath,true);
		}
		
		Job job = new Job(conf, IPCounter.class.getSimpleName());
		job.setJarByClass(IPCounter.class);
		
//		FileInputFormat.addInputPath(job, new Path(IN_PUT));
		FileInputFormat.setInputPaths(job, IN_PUT);
		
		job.setMapperClass(IpMapper.class);
		job.setReducerClass(IpReduce.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		
		FileOutputFormat.setOutputPath(job, outPath);
		
		job.waitForCompletion(true);
		
	}
	
	
	static class IpMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
		
		protected void map(LongWritable key, Text value, org.apache.hadoop.mapreduce.Mapper<LongWritable,Text,Text,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			System.out.println(value.toString());
			String ip[] = value.toString().split("- -");
			for (int i = 0; i < ip.length; i++) {
				System.out.print(ip[0].toString());
			}
			System.out.println("------------------");
			String ipStr = ip[0].toString().trim();
			System.out.println(ipStr+"-----");
			context.write(new Text(ipStr), new LongWritable(1));
			
		};
		
	}
	
	static class IpReduce extends Reducer<Text,LongWritable,Text, LongWritable>{
		
		protected void reduce(Text k2, java.lang.Iterable<LongWritable> v2, org.apache.hadoop.mapreduce.Reducer<Text,LongWritable,Text,LongWritable>.Context context) throws java.io.IOException ,InterruptedException {
			Long counts = 0L;
			for (LongWritable v : v2) {
				counts += v.get();
			}
			context.write(k2, new LongWritable(counts));
		};
		
	}

}

工程截图：

  

4：运行map reduce程序

   

5：查看hdfs结果

[hadoop@icity0 ~]$ hadoop fs -cat /ip/output/part-r-00000
Warning: $HADOOP_HOME is deprecated.

172.16.17.166	31
172.16.17.198	79
172.16.18.148	186
172.16.16.219	1256
172.16.35.141	1102
172.16.35.146	2986
172.16.35.159	6

至此，简单的通过map reduce 实现的ip访问次数统计完成。