hadoop初识--HelloHadoopV2

----------------------------说明------------------------------

此程序比HelloHadoopV1增加了：

  检查输出信息文件夹内是否存在输出文件并删除

  input文件夹内的文件若大于两个，则文件不会被覆盖

  map与reduce拆开，便于函数再利用

---------------------------------------------------------------

 

HelloMapperV2.java

package HelloHadoopV2;

import java.io.IOException;

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

public class HelloMapperV2 extends Mapper<LongWritable,Text,Text,Text>{
     public void map(LongWritable key,Text value,Context context)
       throws IOException, InterruptedException{
    	 context.write(new Text(key.toString()), value);
     }
}

 HelloReducerV2.java

package HelloHadoopV2;

import java.io.IOException;

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

public class HelloReducerV2 extends Reducer<Text,Text,Text,Text> {
    public void reduce(Text key,Iterable<Text> values,Context context) throws IOException, InterruptedException{
    	String str = new String("");
    	Text final_key = new Text();
    	Text final_value = new Text();
    	//将key值相同的values，通过 && 符号分隔之
    	for(Text tmp : values){
    		str += tmp.toString()+ " &&";
    	}
    	
    	final_key.set(key);
    	final_value.set(str);
    	
    	context.write(final_key, final_value);
    }
}

 HelloHadoopV2.java

package HelloHadoopV2;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 CheckAndDelete.CheckAndDelete;


public class HelloHadoopV2 {

	/**
	 * @param args
	 * @throws IOException 
	 * @throws ClassNotFoundException 
	 * @throws InterruptedException 
	 */
	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		Configuration conf = new Configuration();
		Job job = new Job(conf,"Hadoop Hello World 2");
		job.setJarByClass(HelloHadoopV2.class);
		//设置map and reduce以及 combiner class
		job.setMapperClass(HelloMapperV2.class);
		job.setCombinerClass(HelloReducerV2.class);
		job.setReducerClass(HelloReducerV2.class);
		//设定map的输出类型
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		//设定reduce的输出类型
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		//设置文件输入路径
		FileInputFormat.addInputPath(job,new Path("/user/hadoopinput"));
		//设置文件输出路径
		FileOutputFormat.setOutputPath(job,new Path("/user/hadoop/output-hh2"));
		//调用CheckAndDelete函数。检查是否存在文件夹，若存在则删除
		CheckAndDelete.checkAndDelete("/user/hadoop/output-hh2",conf);
		
		boolean status = job.waitForCompletion(true);
		
		if(status){
			System.err.println("Integrate Alert Job Finished !");
		}else{
			System.err.println("Integrate Alert Job Failed");
			System.exit(1);
		}
	}

}

 

测试方法：

1、启动hadoop

2、将该代码打包为HelloHadoop.jar，并将其拷贝到hadoop目录下

3、执行过程如 http://freewxy.iteye.com/blog/1102011 

4、查看结果：