MapReduce 分析nginx日志例子

package com.sekorm.dataAnalysis.Main;


import java.io.IOException;
import java.util.List;


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.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 org.apache.hadoop.util.GenericOptionsParser;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;


import com.sekorm.bean.sekorm.NginxLogBean;
import com.sekorm.dataAnalysis.util.JacksonUtils;
import com.sekorm.dataAnalysis.util.ReadFileUtil;


public class Main {

private static final Logger log = LoggerFactory.getLogger(Main.class);



public static class MyMap extends Mapper<Object, Text, Text, IntWritable>{

private Text word = new Text(); 
private final static IntWritable one = new IntWritable(1);

public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
NginxLogBean bean=JacksonUtils.toBean(value.toString(), NginxLogBean.class);
word.set(bean.getRemote_addr());
context.write(word, one);
}
}


public static class MyReducer extends  Reducer<Text, IntWritable, Text, IntWritable> {  

private IntWritable result = new IntWritable();  

public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
int sum=0;
for(IntWritable val:values) {
sum+=val.get();
}
result.set(sum);
context.write(key, result);
}  

}  


public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] argArray = new GenericOptionsParser(conf,args).getRemainingArgs();

if(argArray.length!=2){
log.info("需要两个参数");
log.info("job 强制退出");
System.exit(1);
}

Job job = Job.getInstance(conf);
job.setJarByClass(Main.class);
// job.setNumReduceTasks(0);
job.setMapperClass(MyMap.class);
job.setCombinerClass(MyReducer.class);
job.setReducerClass(MyReducer.class);

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);

FileSystem fs = FileSystem.get(conf);
List<Path> list=ReadFileUtil.getSubPath(fs,new Path(args[0]));
fs.close();
for(Path path:list){
FileInputFormat.addInputPath(job, path);
}
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1); 

}


}