(五)Hive与Hbase整合

Hive与Hbase整合

一.Hive与Hbase对比

    https://blog.csdn.net/qq_32736999/article/details/83832376

    Hive与HBase各自有着不同的功能，但是归根接地，Hive与HBase的数据最终都是存储在HDFS上面的，为了节省磁盘的存储空间，一般不会将一份数据存储到多个地方。所以，我们可以直接将数据存入HBase，然后通过Hive整合HBase直接使用SQL语句分析HBase里面的数据即可。

二Hive与Hbase整合

需求一：将hive分析结果的数据，保存到HBase当中去

1.拷贝hbase的五个依赖jar包到hive的lib目录下

hbase的jar包都在/export/servers/hbase-1.2.0-cdh5.14.0/lib，我们需要拷贝五个jar包名字如下：
	hbase-client-1.2.0-cdh5.14.0.jar         	  
	hbase-hadoop2-compat-1.2.0-cdh5.14.0.jar 
	hbase-hadoop-compat-1.2.0-cdh5.14.0.jar  
	hbase-it-1.2.0-cdh5.14.0.jar    
	hbase-server-1.2.0-cdh5.14.0.jar
hive安装在node03机器上，我们直接在node03执行以下命令，通过创建软连接的方式来进行jar包的依赖：

ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-client-1.2.0-cdh5.14.0.jar  /export/servers/hive-1.1.0-cdh5.14.0/lib/hbase-client-1.2.0-cdh5.14.0.jar

ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-hadoop2-compat-1.2.0-cdh5.14.0.jar  /export/servers/hive-1.1.0-cdh5.14.0/lib/hbase-hadoop2-compat-1.2.0-cdh5.14.0.jar

ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-hadoop-compat-1.2.0-cdh5.14.0.jar  /export/servers/hive-1.1.0-cdh5.14.0/lib/hbase-hadoop-compat-1.2.0-cdh5.14.0.jar

ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-it-1.2.0-cdh5.14.0.jar  /export/servers/hive-1.1.0-cdh5.14.0/lib/hbase-it-1.2.0-cdh5.14.0.jar

ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-server-1.2.0-cdh5.14.0.jar /export/servers/hive-1.1.0-cdh5.14.0/lib/hbase-server-1.2.0-cdh5.14.0.jar

#Spark对Hbase-on-Hive的支持
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/guava-12.0.1.jar                         /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/htrace-core-3.2.0-incubating.jar         /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-common-1.2.0-cdh5.14.0.jar         /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-common-1.2.0-cdh5.14.0-tests.jar   /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-client-1.2.0-cdh5.14.0.jar         /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-server-1.2.0-cdh5.14.0.jar         /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-server-1.2.0-cdh5.14.0-tests.jar   /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/hbase-protocol-1.2.0-cdh5.14.0.jar       /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hbase-1.2.0-cdh5.14.0/lib/metrics-core-2.2.0.jar                   /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/
ln -s /export/servers/hive-1.1.0-cdh5.14.0/lib/hive-hbase-handler-1.1.0-cdh5.14.0.jar    /export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/jars/

2.修改hive-site.xml配置文件

#修改node03上hive-site.xml配置文件
cd /export/servers/hive-1.1.0-cdh5.14.0/conf
vim hive-site.xml

#添加如下配置
<property>
	<name>hive.zookeeper.quorum</name>
	<value>node01,node02,node03</value>
</property>

<property>
	<name>hbase.zookeeper.quorum</name>
	<value>node01,node02,node03</value>
</property>

3.修改hive-env.sh配置文件

#修改node03上hive-env.sh的配置文件
cd /export/servers/hive-1.1.0-cdh5.14.0/conf
vim hive-env.sh

export HADOOP_HOME=/export/servers/hadoop-2.6.0-cdh5.14.0
export HBASE_HOME=/export/servers/hbase-1.2.0-cdh5.14.0
export HIVE_CONF_DIR=/export/servers/hive-1.1.0-cdh5.14.0/conf

4.进入hive客户端并建表

①进入hive客户端(要确保Zookeeper集群、Hadoop集群、Hbase集群已启动)

cd /export/servers/hive-1.1.0-cdh5.14.0/
nohup bin/hive --service metastore &
nohup bin/hive --service hiveserver2 2>&1 &
bin/beeline 
# !connect jdbc:hive2://node03:10000

②创建数据库和外部表

create database hbasedb;
use hbasedb;

create external table if not exists score(
  id int,
  cname string,
  score int
)row format delimited fields terminated by '\t' 
stored as textfile;

③准备数据

cd ~
vim hive_hbase.txt

1	zhangsan	80
2	lisi	60
3	wangwu	30
4	zhaoliu	70

④加载至表内

load data local inpath '/root/hive_hbase.txt' into table score;
select * from score;

5.创建hive管理表与hbase进行映射，hive管理表当中的数据，都会存储到hbase上面去。

create table hbase_score(
  id int,
  cname string,
  score int
)stored by 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
with serdeproperties("hbase.columns.mapping" = "cf:name,cf:score")
tblproperties("hbase.table.name" = "hbase_score");
# 建表成功后再hbase中也创建了一个hbase_score表

6.在hive客户端中向表中插入数据

insert overwrite table hbase_score select * from score;

select * from hbase_score;
#在hive中查询hbase_score结果为
+-----------------+--------------------+--------------------+--+
| hbase_score.id  | hbase_score.cname  | hbase_score.score  |
+-----------------+--------------------+--------------------+--+
| 1               | zhangsan           | 80                 |
| 2               | lisi               | 60                 |
| 3               | wangwu             | 30                 |
| 4               | zhaoliu            | 70                 |
+-----------------+--------------------+--------------------+--+

在hbase客户端中查结果为

#查询命令为
scan 'hbase_score'

#查询结果为
ROW           COLUMN+CELL
 1            column=cf:name, timestamp=1567094300857, value=zhangsan
 1            column=cf:score, timestamp=1567094300857, value=80
 2            column=cf:name, timestamp=1567094300857, value=lisi
 2            column=cf:score, timestamp=1567094300857, value=60
 3            column=cf:name, timestamp=1567094300857, value=wangwu
 3            column=cf:score, timestamp=1567094300857, value=30
 4            column=cf:name, timestamp=1567094300857, value=zhaoliu
 4            column=cf:score, timestamp=1567094300857, value=70

需求二：创建hive外部表，映射HBase中的表模型

1.进入HBase客户端，创建表并手动插入加载一些数据

create 'hbase_hive_score',{ NAME =>'cf'}
put 'hbase_hive_score','1','cf:name','zhangsan'
put 'hbase_hive_score','1','cf:score', '95'
put 'hbase_hive_score','2','cf:name','lisi'
put 'hbase_hive_score','2','cf:score', '96'
put 'hbase_hive_score','3','cf:name','wangwu'
put 'hbase_hive_score','3','cf:score', '97'

2.进入hive客户端，按如下命令创建hive外部表

create external table hbase_to_hive_score(
  id int,
  name string,
  score int
)stored by 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
with serdeproperties ("hbase.columns.mapping" = ":key,cf:name,cf:score")
tblproperties("hbase.table.name" = "hbase_hive_score");