您当前的位置: 首页 >  hbase

99 MapReduce操作Hbase

杨林伟 发布时间:2019-08-12 14:18:53 ,浏览量:0

1.实现方法

Hbase对MapReduce提供支持,它实现了TableMapper类和TableReducer类,我们只需要继承这两个类即可。

1、写个mapper继承TableMapper 参数:Text:mapper的输出key类型; IntWritable:mapper的输出value类型。 其中的map方法如下:

map(ImmutableBytesWritable key, Result value,Context context)

参数:key:rowKey;
     value: Result ,一行数据; 
	 context上下文

2、写个reduce继承TableReducer 参数:Text:reducer的输入key; IntWritable:reduce的输入value; ImmutableBytesWritable:reduce输出到hbase中的rowKey类型。

其中的reduce方法如下:

reduce(Text key, Iterable values,Context context)

参数: key:reduce的输入key;
      values:reduce的输入value;
2.表

1、建立数据来源表‘word’,包含一个列族‘content’ 向表中添加数据,在列族中放入列‘info’,并将短文数据放入该列中,如此插入多行,行键为不同的数据即可

2、建立输出表‘stat’,包含一个列族‘content’

3、通过Mr操作Hbase的‘word’表,对‘content:info’中的短文做词频统计,并将统计结果写入‘stat’表的‘content:info中’,行键为单词

3.实现
package com.itcast.hbase;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

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.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
/**
 * mapreduce操作hbase
 * @author wilson
 *
 */
public class HBaseMr {
	/**
	 * 创建hbase配置
	 */
	static Configuration config = null;
	static {
		config = HBaseConfiguration.create();
		config.set("hbase.zookeeper.quorum", "slave1,slave2,slave3");
		config.set("hbase.zookeeper.property.clientPort", "2181");
	}
	/**
	 * 表信息
	 */
	public static final String tableName = "word";//表名1
	public static final String colf = "content";//列族
	public static final String col = "info";//列
	public static final String tableName2 = "stat";//表名2
	/**
	 * 初始化表结构,及其数据
	 */
	public static void initTB() {
		HTable table=null;
		HBaseAdmin admin=null;
		try {
			admin = new HBaseAdmin(config);//创建表管理
			/*删除表*/
			if (admin.tableExists(tableName)||admin.tableExists(tableName2)) {
				System.out.println("table is already exists!");
				admin.disableTable(tableName);
				admin.deleteTable(tableName);
				admin.disableTable(tableName2);
				admin.deleteTable(tableName2);
			}
			/*创建表*/
				HTableDescriptor desc = new HTableDescriptor(tableName);
				HColumnDescriptor family = new HColumnDescriptor(colf);
				desc.addFamily(family);
				admin.createTable(desc);
				HTableDescriptor desc2 = new HTableDescriptor(tableName2);
				HColumnDescriptor family2 = new HColumnDescriptor(colf);
				desc2.addFamily(family2);
				admin.createTable(desc2);
			/*插入数据*/
				table = new HTable(config,tableName);
				table.setAutoFlush(false);
				table.setWriteBufferSize(5);
				List lp = new ArrayList();
				Put p1 = new Put(Bytes.toBytes("1"));
				p1.add(colf.getBytes(), col.getBytes(),	("The Apache Hadoop software library is a framework").getBytes());
				lp.add(p1);
				Put p2 = new Put(Bytes.toBytes("2"));p2.add(colf.getBytes(),col.getBytes(),("The common utilities that support the other Hadoop modules").getBytes());
				lp.add(p2);
				Put p3 = new Put(Bytes.toBytes("3"));
				p3.add(colf.getBytes(), col.getBytes(),("Hadoop by reading the documentation").getBytes());
				lp.add(p3);
				Put p4 = new Put(Bytes.toBytes("4"));
				p4.add(colf.getBytes(), col.getBytes(),("Hadoop from the release page").getBytes());
				lp.add(p4);
				Put p5 = new Put(Bytes.toBytes("5"));
				p5.add(colf.getBytes(), col.getBytes(),("Hadoop on the mailing list").getBytes());
				lp.add(p5);
				table.put(lp);
				table.flushCommits();
				lp.clear();
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			try {
				if(table!=null){
					table.close();
				}
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}
	/**
	 * MyMapper 继承 TableMapper
	 * TableMapper 
	 * Text:输出的key类型,
	 * IntWritable:输出的value类型
	 */
	public static class MyMapper extends TableMapper {
		private static IntWritable one = new IntWritable(1);
		private static Text word = new Text();
		@Override
		//输入的类型为:key:rowKey; value:一行数据的结果集Result
		protected void map(ImmutableBytesWritable key, Result value,
				Context context) throws IOException, InterruptedException {
			//获取一行数据中的colf:col
			String words = Bytes.toString(value.getValue(Bytes.toBytes(colf), Bytes.toBytes(col)));// 表里面只有一个列族,所以我就直接获取每一行的值
			//按空格分割
			String itr[] = words.toString().split(" ");
			//循环输出word和1
			for (int i = 0; i             
关注
打赏
1688896170
查看更多评论
0.1116s