Hbase 导入数据

package an.hbase.operation;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.MasterNotRunningException;
import org.apache.hadoop.hbase.ZooKeeperConnectionException;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;

public class HbasicOperation {

	/**
	 * @param args
	 * @throws IOException 
	 */
	private static String inputfile = "/home/an/plateform/logData/SogouQ.sample";//输入的数据
	public static void main(String[] args) throws IOException {
		// TODO Auto-generated method stub
		
		
		/**init the configuration of Hbase*/
		Configuration conf = HBaseConfiguration.create();
		conf.set("hbase.zookeeper.quorun", "localhost");
		HBaseAdmin admin = new HBaseAdmin(conf);
		
		/**
		 * 测试使用java类来读取文件，然后将生成的文件进行文本分析，
		 * 提取对应的关键字来创建相应的table，并将
		 * 生成的数据导入进去
		 * */
		 FileInputStream fis  =   new  FileInputStream(inputfile ); //打开文件
		 InputStreamReader isr  =   new  InputStreamReader(fis,  "gbk" ); 
		 BufferedReader br  =   new  BufferedReader(isr); 
		 String[] contents = {"visit_time","user_id","query","link_rank","click_url"};
		 String log  =   null ;
		
		
		/**HBaseAdmin.create() 可以用来创建一张新表，该方法的参数为HTableDescription
		 * 用来描述表名和相关的列簇。该方法的返回值为HTable类，用于对表进行相关的操作
		 * */
		
		
		HTableDescriptor tableDescripter = new HTableDescriptor("Sogou".getBytes());
		tableDescripter.addFamily(new HColumnDescriptor("fam1"));
		admin.createTable(tableDescripter);
		HTable table = new HTable(conf,"Sogou");
		
		
		 int num_line = 1;//输入的row编号
		 while  ((log  =  br.readLine())  !=   null ) { 
			 String[] logs = log.split("\t");
				if(logs.length != 5){//不是正常的日志文件 
					continue; //进入下一次循环
				}
				//加入行
				Put putRow = new Put(String.valueOf(num_line).getBytes());
				for(int i = 0;i < 5; i++){
					putRow.add("fam1".getBytes(),contents[i].getBytes(),logs[i].getBytes());
					table.put(putRow);
				}//for
				num_line ++;
			 
	        } //while
		 
		
	}//main

}