Hadoop2.x实战：WordCount、Sort、去重复、average实例MapRedure编写

Hadoop版本：2.6.0

Eclipse版本：luna

一、     Hadoop做的一个计算单词的实例

1、引入jar

	<dependencies>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.2.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>2.2.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.2.0</version>
		</dependency>
		<dependency>
			<groupId>jdk.tools</groupId>
			<artifactId>jdk.tools</artifactId>
			<version>1.6</version>
			<scope>system</scope>
			<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
		</dependency>
	</dependencies>

2、代码编写

package com.lin.wordcount;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
 
public class WordCount {
 
    public static class WordCountMapper extends MapReduceBase implements 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,OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while(itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                output.collect(word,one);//字符解析成key-value,然后再发给reducer
            }
 
        }
    }
 
    public static class WordCountReducer extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result =new IntWritable();
 
        public void reduce(Text key, Iterator<IntWritable>values, OutputCollector<Text, IntWritable> output, Reporter reporter)throws IOException {
            int sum = 0;
            while (values.hasNext()){//key相同的map会被发送到同一个reducer,所以通过循环来累加
                sum +=values.next().get();
            }
            result.set(sum);
            output.collect(key, result);//结果写到hdfs
        }
      
    }
 
    public static void main(String[] args)throws Exception {
    	//System.setProperty("hadoop.home.dir", "D:\\project\\hadoop-2.7.2"); 如果本地环境变量没有设置hadoop路径可以这么做
    	
        String input = "hdfs://hmaster:9000/input/LICENSE.txt";
        String output = "hdfs://hmaster:9000/output/";
 
        JobConf conf = new J