CC00004.hbase——|Hadoop&HBase.V04|——|HBase.v04|HBase Shell操作|

一、HBase shell 基本操作

### --- 进入Hbase客户端命令操作界面

[root@linux121 ~]# hbase shell

### --- 查看帮助命令

hbase(main):003:0> help

### --- 查看当前数据库中有哪些表

hbase(main):003:0> list
TABLE                                                                                                                                                                                          
0 row(s) in 0.5710 seconds

=> []

hbase(main):005:0> create 'yanqi', 'base_info', 'extra_info'
=> Hbase::Table - yanqi
hbase(main):006:0> list                                                                                                                                                                                        
yanqi

### --- 创建一张yanqi表， 包含base_info、extra_info两个列族

hbase(main):005:0> create 'yanqi', 'base_info', 'extra_info'
=> Hbase::Table - yanqi
hbase(main):006:0> list                                                                                                                                                                                        
yanqi

~~~     或者(Hbase建表必须指定列族信息)
~~~     VERSIONS 是指此单元格内的数据可以保留最近的 3 个版本

hbase(main):004:0>  hbase(main):008:0> create 'yanqi', {NAME => 'base_info', VERSIONS => '3'},{NAME => 'extra_info',VERSIONS => '3'}
hbase(main):008:0> list                                                                                                                                                                                     
yanqi

### --- 添加数据操作

~~~     # 向yanqi表中插入信息，row key为 rk1，列族base_info中添加name列标示符，值为wang
hbase(main):009:0> put 'yanqi', 'rk1', 'base_info:name', 'wang'

~~~     # 向yanqi表中插入信息，row key为rk1，列族base_info中添加age列标示符，值为30
hbase(main):011:0> put 'yanqi', 'rk1', 'base_info:age', 30

~~~     # 向yanqi表中插入信息，row key为rk1，列族extra_info中添加address列标示符，值为shanghai
hbase(main):012:0> put 'yanqi', 'rk1', 'extra_info:address', 'shanghai'

二、查询数据

### --- 通过rowkey进行查询
~~~     获取表中row key为rk1的所有信息

hbase(main):013:0> get 'yanqi', 'rk1'
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang                                                                                                           
 extra_info:address                              timestamp=1630575836086, value=shanghai

### --- 查看rowkey下面的某个列族的信息
~~~     # 获取yanqi表中row key为rk1，base_info列族的所有信息

hbase(main):014:0> get 'yanqi', 'rk1', 'base_info'
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang

### --- 查看rowkey指定列族指定字段的值
~~~     # 获取表中row key为rk1，base_info列族的name、age列标示符的信息

hbase(main):015:0>  get 'yanqi', 'rk1', 'base_info:name', 'base_info:age'
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang

### --- 查看rowkey指定多个列族的信息
~~~     # 获取yanqi表中row key为rk1，base_info、extra_info列族的信息

hbase(main):016:0> get 'yanqi', 'rk1', 'base_info', 'extra_info'
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang                                                                                                           
 extra_info:address                              timestamp=1630575836086, value=shanghai

~~~     # 或者
hbase(main):017:0> get 'yanqi', 'rk1', {COLUMN => ['base_info', 'extra_info']}
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang                                                                                                           
 extra_info:address                              timestamp=1630575836086, value=shanghai  

~~~     # 或者
hbase(main):001:0> get 'yanqi', 'rk1', {COLUMN => ['base_info:name','extra_info:address']}
COLUMN                                           CELL                                                                                                                                          
 base_info:name                                  timestamp=1630575785484, value=wang                                                                                                           
 extra_info:address                              timestamp=1630575836086, value=shanghai

### --- 指定rowkey与列值查询
~~~     # 获取表中row key为rk1，cell的值为wang的信息

hbase(main):004:0> get 'yanqi', 'rk1', {FILTER => "ValueFilter(=,'binary:wang')"}
COLUMN                                           CELL                                                                                                                                          
 base_info:name                                  timestamp=1630575785484, value=wang

### --- 指定rowkey与列值模糊查询
~~~     # 获取表中row key为rk1，列标示符中含有a的信息

hbase(main):005:0> get 'yanqi', 'rk1', {FILTER => "(QualifierFilter(=,'substring:a'))"}
COLUMN                                           CELL                                                                                                                                          
 base_info:age                                   timestamp=1630575821963, value=30                                                                                                             
 base_info:name                                  timestamp=1630575785484, value=wang                                                                                                           
 extra_info:address                              timestamp=1630575836086, value=shanghai

### --- 查询所有数据
~~~     # 查询yanqi表中的所有信息

hbase(main):010:0> scan 'yanqi'
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang                                                                                    
 rk1                                             column=extra_info:address, timestamp=1630575836086, value=shanghai

### --- 列族查询
~~~     # 查询表中列族为 base_info 的信息
~~~     # Scan时可以设置是否开启Raw模式,开启Raw模式会返回包括已添加删除标记但是未实际删除的数据
~~~     # VERSIONS指定查询的最大版本数

hbase(main):011:0> scan 'yanqi', {COLUMNS => 'base_info'}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang                                                                                    
1 row(s) in 0.0380 seconds
hbase(main):012:0> scan 'yanqi', {COLUMNS => 'base_info', RAW => true, VERSIONS=> 3}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang

### --- 指定多个列族与按照数据值模糊查询
~~~     # 查询yanqi表中列族为 base_info 和 extra_info且列标示符中含有a字符的信息

hbase(main):013:0> scan 'yanqi', {COLUMNS => ['base_info', 'extra_info'], FILTER=> "(QualifierFilter(=,'substring:a'))"}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang                                                                                    
 rk1                                             column=extra_info:address, timestamp=1630575836086, value=shanghai

### --- rowkey的范围值查询(非常重要)
~~~     # 查询yanqi表中列族为base_info，rk范围是[rk1, rk3)的数据(
~~~     rowkey底层存储是字典序)按rowkey顺序存储。

hbase(main):014:0> scan 'yanqi', {COLUMNS => 'base_info', STARTROW => 'rk1',ENDROW => 'rk3'}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang

### --- 指定rowkey模糊查询
~~~     # 查询yanqi表中row key以rk字符开头的

hbase(main):015:0> scan 'yanqi',{FILTER=>"PrefixFilter('rk')"}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang                                                                                    
 rk1                                             column=extra_info:address, timestamp=1630575836086, value=shanghai

三、更新数据

### --- 更新数据

~~~     更新操作同插入操作一模一样，只不过有数据就更新，没数据就添加
~~~     更新数据值

~~~     # 把yanqi表中rowkey为rk1的base_info列族下的列name修改为liang

hbase(main):016:0>  put 'yanqi', 'rk1', 'base_info:name', 'liang'

四、删除数据和表

### --- 指定rowkey以及列名进行删除
~~~     # 删除yanqi表row key为rk1，列标示符为 base_info:name 的数据

hbase(main):017:0> delete 'yanqi', 'rk1', 'base_info:name'

### --- 指定rowkey，列名以及时间戳信息进行删除
~~~     # 删除yanqi表row key为rk1，列标示符为base_info:name的数据

scan 'yanqi', {COLUMNS => 'base_info', RAW => true, VERSIONS => 3}
hbase(main):018:0> scan 'yanqi', {COLUMNS => 'base_info', RAW => true, VERSIONS => 3}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630576437128, type=DeleteColumn                                                                             
 rk1                                             column=base_info:name, timestamp=1630576413147, value=liang                                                                                   
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang  

hbase(main):019:0> delete 'yanqi', 'rk1', 'base_info:name',1630575785484

hbase(main):020:0> scan 'yanqi', {COLUMNS => 'base_info', RAW => true, VERSIONS=> 3}
ROW                                              COLUMN+CELL                                                                                                                                   
 rk1                                             column=base_info:age, timestamp=1630575821963, value=30                                                                                       
 rk1                                             column=base_info:name, timestamp=1630576437128, type=DeleteColumn                                                                             
 rk1                                             column=base_info:name, timestamp=1630576413147, value=liang                                                                                   
 rk1                                             column=base_info:name, timestamp=1630575785484, type=DeleteColumn                                                                             
 rk1                                             column=base_info:name, timestamp=1630575785484, value=wang

### --- 删除列族
~~~     # 删除 base_info 列族

hbase(main):001:0> alter 'yanqi', 'delete' => 'base_info'

### --- 清空表数据
~~~     # 删除yanqi表数据

hbase(main):001:0> truncate 'yanqi'

### --- 删除表：删除yanqi表

~~~     # 先disable 再drop
hbase(main):003:0> disable 'yanqi'
hbase(main):004:0> drop 'yanqi'

~~~     # 如果不进行disable，直接drop会报错
ERROR: Table user is enabled. Disable it first.