首页 > 代码库 > Hadoop-2、Mapred初试

Hadoop-2、Mapred初试

import java.io.IOException;
import java.util.Iterator;
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.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;
import org.apache.hadoop.util.GenericOptionsParser;

public class Main{
    public static void main(String args[]) throws IOException, ClassNotFoundException, InterruptedException{
        Configuration conf = new Configuration();
        conf.addResource(new Path("/usr/hadoop-1.0.3/conf/core-site.xml"));
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        Job job = new Job(conf, "Main");
        job.setJarByClass(Main.class);
        job.setJobName("Main");
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reduce.class);
        job.setReducerClass(Reduce.class);
        
        //job.setInputFormatClass(TextInputFormat.class);
        //job.setOutputFormatClass(TextOutputFormat.class);
        
        FileInputFormat.setInputPaths(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        
        boolean success = job.waitForCompletion(true);
        
        System.out.print(success ? 0 : 1);
    }

    public static class Reduce extends Reducer<Text,IntWritable,Text,IntWritable>{
        public void reduce(Text key,Iterable<IntWritable> values,Context context) throws IOException, InterruptedException{
            int sum = 0;
            int count = 0;
            Iterator<IntWritable> iterator = values.iterator();
            
            while(iterator.hasNext()){
                sum += iterator.next().get();
                count++;
            }
            
            int average = (int)sum/count;
            context.write(key,new IntWritable(average));
        }
    }

    public static class Map extends Mapper<LongWritable,Text,Text,IntWritable>{
        public void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException{
            String line = value.toString();  //纯文本文件转化为string
            System.out.println(line);    
            
            StringTokenizer tokenizerArticle = new StringTokenizer(line,"\n");    //将输入的数据首先按行进行分割
            while(tokenizerArticle.hasMoreTokens()){    //分别对每行进行处理
                StringTokenizer tokenizerLine = new StringTokenizer(tokenizerArticle.nextToken());    //每行按空格划分
                String strName = tokenizerLine.nextToken();    //学生姓名部分
                String strScore = tokenizerLine.nextToken();    //成绩部分
                Text name = new Text(strName);
                int ScoreInt = Integer.parseInt(strScore);
                context.write(name, new IntWritable(ScoreInt));    //输出
            }
        }
    }
}

输入的文件夹名为:/TestDirs/     /T/        

注意Map和Reduce的类要是static的,不然会报错哦!