人大云计算检测系统——1000-1002题

初接触hadoop，发现这个OJ是练习写map/reduce程序的好地方：http://cloudcomputing.ruc.edu.cn/

下面是自己拍的一些题的答案，其中很多都是可以在hadoop实战这本书上找到的。

第1000题：

import java.io.IOException;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

/**
 * 
 * @author urey
 *
 */
public class MyMapre {

	/**
	 * @param args
	 * @throws IOException 
	 * @throws InterruptedException 
	 * @throws ClassNotFoundException 
	 */
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		// TODO Auto-generated method stub
		
		Configuration conf = new Configuration();
		Job job = new Job(conf,"qw 1000");
		job.setJarByClass(MyMapre.class);
		job.setMapperClass(TokenizerMapper.class);
		job.setCombinerClass(IntSumReducer.class);
		job.setReducerClass(IntSumReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true) ? 0:1);
	}
	
	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);
		} 
	}
}

第1001题：

import java.io.IOException;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class MyMapre {

	/**
	 * @param args
	 * @throws IOException 
	 * @throws InterruptedException 
	 * @throws ClassNotFoundException 
	 */
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		// TODO Auto-generated method stub
		Configuration conf = new Configuration();
		Job job = new Job(conf,"qw 1001");
		job.setJarByClass(MyMapre.class);
		job.setMapperClass(Map.class);
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true) ? 0:1);
	}
	
	public static class Map extends Mapper<LongWritable, Text, LongWritable, IntWritable> {
	    
		public void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException {
	        Integer sum = 0;  
	        String line = value.toString();  
	        StringTokenizer itr = new StringTokenizer(line); 
	        if (itr.hasMoreElements())  
	        key = new LongWritable(Integer.parseInt(itr.nextToken()));
	        while(itr.hasMoreElements()){  
	        	sum += Integer.parseInt(itr.nextToken()); 
	        } 
	        context.write(key, new IntWritable(sum)); 
	   }     
	   
	}

}

第1002题：

import java.io.IOException;

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.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class MyMapre {

}
	/**
	 * @param args
	 * @throws IOException 
	 * @throws InterruptedException 
	 * @throws ClassNotFoundException 
	 */
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		// TODO Auto-generated method stub
		Configuration conf = new Configuration();
		Job job = new Job(conf,"qw 1002");
		job.setJarByClass(MyMapre.class);
		job.setMapperClass(Map.class);
		job.setReducerClass(Reduce.class);
		job.setPartitionerClass(Partition.class);
		job.setMapOutputKeyClass(IntWritable.class);
		job.setMapOutputValueClass(IntWritable.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true) ? 0:1);
	}
	
	public static class Map extends Mapper<Object, Text, IntWritable, IntWritable> {
		private static IntWritable data = new IntWritable();
		
		public void map(Object key,Text value,Context context)
				throws IOException,InterruptedException{  
			String line = value.toString();
			data.set(Integer.parseInt(line));
			context.write(data, new IntWritable(1));
		}
	}
	
	public static class Reduce extends Reducer<IntWritable , IntWritable, IntWritable, IntWritable> {
		private static IntWritable linenum= new IntWritable (1);
		
		public void reduce(IntWritable key,Iterable<IntWritable> values,Context context)
				throws IOException,InterruptedException{  
			for(IntWritable val:values){
				context.write(linenum, key);
				linenum=new IntWritable(linenum.get()+1);
			}
		}
	}
	
	public static class Partition extends Partitioner <IntWritable,IntWritable> {
		
		public int getPartition(IntWritable key, IntWritable value, int numPartitions) {
			int Maxnumber = 65223;
			int bound = Maxnumber/numPartitions + 1 ;
			int keynumber = key.get();
			for(int i=1;i<=numPartitions;i++) {
				if(keynumber < bound*i && keynumber >= bound*(i-1)) {
					return i-1;
				}
			}
			return -1;
		}
	}
}