WCJob

package com.sxt.hbase;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
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;

public class WCJob {

	public static void main(String[] args) throws Exception {
		
		Configuration conf = new Configuration();
		conf.set("fs.defaultFS", "hdfs://node01:8020");
		// 完全分布式HBase集群  指定ZooKeeper集群地址
		// 伪分布式  单独指定那一台HBase节点
		conf.set("hbase.zookeeper.quorum", "node02,node03,node04");
		
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(com.sxt.hbase.WCJob.class);
		
		job.setMapperClass(WCMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
// 		boolean addDependencyJars 本地运行 该参数应该设置为false；集群方式运�?该参�?默认为true即可
//		TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job);
	 
		TableMapReduceUtil.initTableReducerJob("wc", WCReducer.class, job, null, null, null, null, false);
		   
		Path path = new Path("/usr/wc");
		FileInputFormat.addInputPath(job, path);
		
		job.waitForCompletion(true);
	}
	
}