hadoop之"hello world"--wordCount

hadoop版本1.2.1 ,开发IDE：eclipse;

编写map函数,继承mapper类。

package com.cjh.hadoop;

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

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordMapper extends Mapper<Object, Text, Text, IntWritable>{

	private final static IntWritable one = new IntWritable(1);
	private Text word = new Text() ; 
	@Override
	protected void map(Object key, Text value,
			Context context)
			throws IOException, InterruptedException {
		//map中的key为每一行的偏移量,value为每一行的内容
		//StringTokenizer是java.util中的类,根据空格分隔一行中的每一个单词
		StringTokenizer itr = new StringTokenizer(value.toString()) ;
		
		while(itr.hasMoreTokens()){
			word.set(itr.nextToken());
			context.write(word, one);
		}
	}
	
	

}

编写reduce函数，继承Reducer类

package com.cjh.hadoop;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

	
	private IntWritable result = new IntWritable() ; 
	@Override
	protected 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);
	}

	
}

编写main函数

package com.cjh.hadoop;


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


public class WordMain {

	public static void main(String[] args) throws Exception {
		//读取hadoop的配置文件，如site-core.xml等。
		Configuration conf = new Configuration();
		//GenericOptionsParser这个类的主要作用是解析用户指定的参数并且修改conf的配置信息
		String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
		
		if(otherArgs.length != 2){
			System.err.println("Usage: wordcount <in> <out>");
			System.exit(2);
		}
		
		//一个MapReduce任务。第二个参数为Job的名称
		Job job = new Job(conf,"WordCount") ;
		
		//主类
		job.setJarByClass(WordMain.class);
		//设置mapper类
		job.setMapperClass(WordMapper.class);
		//设置合成类
		job.setCombinerClass(WordReducer.class);
		//设置reducer类
		job.setReducerClass(WordReducer.class);
		//设置输出key类型
		job.setOutputKeyClass(Text.class);
		//设置输出value类型
		job.setOutputValueClass(IntWritable.class);
		//输入路径
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		//输出路径
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		//等待job完成
		System.exit(job.waitForCompletion(true) ? 0 : 1);
		
	}
}

编写完代码后，打jar包上传到hadoop_home路径下。使用命令：bin/hadoop jar wordcount.jar com.cjh.hadoop.WordMain /user/hadoop/input/test* /user/hadoop/output_wordcount   执行mapReduce。成功后，使用命令：bin/hadoop fs -text /user/hadoop/output_wordcount/part-r-00000 查看输出文件。

遇到的问题：

1.3个类中导入的包一定要正确。

2.设置output文件夹的时候一定是不存在的。否则报错