1. 程式人生 > >hadoop初級班(二)

hadoop初級班(二)

<span style="font-size:18px;">package ustc.hilab.wordcount;

import java.io.exception;
import java.util.StringTokenizer;

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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount{
    public static class TokenizerMapper
    extends Mapper<Object,Text,Text,IntWritable>{
        private final static IntWritable one=new IntWritable(1);
        private Text word=new Text();
        
        public void map(Object key,Text value,Context context)throws IOException,interruptedException{
        StringTokenizer itr=new StringTokenizer(value.toString());
        while (itr.hasMoreTokens()){
        word.set(itr.nextToken());
        context.write(word,one)
                }
        }
    }
   
    
    public static class IntSumReducer 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[]otherArgs=new GenericOptionsParser(conf,args).getRemainingArgs();
    if(otherArgs.length!=2){
        System.err.println("usage:wordcount<in><out>");
        System.exit(2);
    }
    
    Job job=new Job(conf,"wordcount")
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setReducerClass(IntsumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Intwritable.class);
    FileInputFormat.addInputPath(job,new Path(otherArgs[0]));
    FileOutputFormat.addOutputPath(job,new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true)?0:1);
    
    }
    
}
                                                </span>