hadoop初识--HelloHadoopV1

/**
 * HelloHadoop
 * 此程序用来了解Hadoop的<key,value>,并且练习hadoop api 编程
 *
 * 测试方法：
 * 1、将该程序打包在hadoop0.21.0平台上；打成jar包，并将jar包拷贝到usr/local/hadoop（hadoop的安装目录）下
 * 2、格式化namenode：
 * hadoop@wxy:/usr/local/hadoop$ ./bin/hadoop namenode -format
 * 3、启动hadoop
 * hadoop@wxy:/usr/local/hadoop$ ./bin/start-all.sh

 * 4、查看hadoop运行情况 ￥jps

 * 5、在hdfs上创建input文件夹，将文本文件READ.TXT拷贝到hdfs(/user/hadoop/input)上

 

 
 * 6执行：
 * hadoop@wxy:/usr/local/hadoop$ bin/hadoop jar HelloHadoop.jar

 *7 查看运行结果

 如上图，产生/user/hadoop/output-hh1文件夹，文件夹中包含运行结果

 
 *
 *注意：
 *1.在hdfs 上来源文档路径为 "/user/hadoop/input"
 *  注意必须先放资料到此hdfs上的文件夹内，且文件夹内只能放文件，不能再放文件夹     
 *2. 运算完后，程序将执行结果放在hdfs 的输出路径为 "/user/$YOUR_NAME/output-hh1"
 *  注意此文件夹为运算结束后才产生的，所以运算之前不会产生该文件夹  
 * 
 *浏览器中输入：http://localhost:50030/jobtracker.jsp查看运行状态
 */

 

 

package HelloHadoopV1;

import java.io.IOException;

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

/**
 * HelloHadoop
 * @author wxy
 * 此程序用来了解Hadoop的<key,value>,并且练习hadoop api 编程
 * 
 */
public class HelloHadoop {

	static public class HelloMapper extends Mapper<LongWritable,Text,LongWritable,Text>{
		public void map(LongWritable key,Text value,Context context)
		    throws IOException,InterruptedException {
			//将输入的资料，原封不动的写入输出
			context.write((LongWritable)key, (Text)value);
		}
	}
	
	static public class HelloReducer extends Reducer<LongWritable,Text,LongWritable,Text>{
		public void reduce(LongWritable key,Iterable<Text> values,Context context)
		    throws IOException,InterruptedException {
			Text val = new Text();
			//取得values的值，放入val中
			for(Text str:values){
				val.set(str.toString());
			}
			//将获取的资料引入输出
			context.write(key, val);
		}
	}
	
	public static void main(String[] args)throws IOException,InterruptedException,ClassNotFoundException{
		//引入 ￥HADOOP_HOME/conf 启用默认配置
		Configuration conf = new Configuration();
		//定义一个job，宣告job取得conf并设定名称 Hadoop Hello World
		Job job = new Job(conf,"Hadoop Hello World");
		//设置运算主程序，即执行类
		job.setJarByClass(HelloHadoop.class);
		//设置输入路径
		FileInputFormat.setInputPaths(job,"input");
		//设置输出路径
		FileOutputFormat.setOutputPath(job,new Path("output-hh1"));
		//指定Map class，即设定Mapper的实现类
		job.setMapperClass(HelloMapper.class);
		//指定reduce class，即设定Reducer的实现类
		job.setReducerClass(HelloReducer.class);
		//开始运算
		job.waitForCompletion(true);
		
	}
}