HBase的hbase shell 详解

关注

原创最新推荐文章于 2026-07-02 09:36:50 发布 1.2k 阅读 AI 写同款· GEO 优化 ›

我用两个月时间，终于把优快云付费资源项目玩明白了！关于项目的定位，这是一个知识付费项目，根据市场研究机构的数据显示,到2023年,全球知识付费市场规模将达到2000亿美元，所以说知识付费的前景是十分广阔的，当下互联网时代信息大爆炸，80后、90后、00后群体对知识付费的认可度也大幅提升，同时这群作为知识付费的主流人群已经具备了更强的消费能力，而且对于知识付费的需求更高。目前整个知识付费领域仍然在发展起步的初期，尽快在知识付费领域布局可以帮助我们在这波红利中获得一份不错的收益。而且个人认为，阅读详情

进入hbase命令行
./hbase shell
显示hbase中的表
list
创建user表，里面包含info，date两个列族
create 'user','info','data'
create 'user',{NAME => 'info', VERSIONS => 5},{NAME => 'data' , VERSIONS => 5 }
插入数据 put
  hbase> put 'ns1:t1', 'r1', 'c1', 'value'
  hbase> put 't1', 'r1', 'c1', 'value'
  hbase> put 't1', 'r1', 'c1', 'value', ts1
  hbase> put 't1', 'r1', 'c1', 'value', {ATTRIBUTES=>{'mykey'=>'myvalue'}}
  hbase> put 't1', 'r1', 'c1', 'value', ts1, {ATTRIBUTES=>{'mykey'=>'myvalue'}}
  hbase> put 't1', 'r1', 'c1', 'value', ts1, {VISIBILITY=>'PRIVATE|SECRET'}

put 'user' , 'rk0001' , 'info:name' , 'zjs'
put 'user' , 'rk0001' , 'info:age' , '18'
put 'user' , 'rk0001' , 'info:sex' , '男'
put 'user' , 'rk0001' , 'data:name' , 'lt'
put 'user' , 'rk0001' , 'data:age' , '19'
put 'user' , 'rk0001' , 'data:sex' , '女'

put 'user' , 'rk0002' , 'info:name' , 'zjszjs'
put 'user' , 'rk0002' , 'info:age' , '1818'
put 'user' , 'rk0002' , 'info:sex' , '男男'
put 'user' , 'rk0002' , 'data:name' , 'ltlt'
put 'user' , 'rk0002' , 'data:age' , '1919'
put 'user' , 'rk0002' , 'data:sex' , '女女'

查询数据 get
  hbase> t.get 'r1'
  hbase> t.get 'r1', {TIMERANGE => [ts1, ts2]}
  hbase> t.get 'r1', {COLUMN => 'c1'}
  hbase> t.get 'r1', {COLUMN => ['c1', 'c2', 'c3']}
  hbase> t.get 'r1', {COLUMN => 'c1', TIMESTAMP => ts1}
  hbase> t.get 'r1', {COLUMN => 'c1', TIMERANGE => [ts1, ts2], VERSIONS => 4}
  hbase> t.get 'r1', {COLUMN => 'c1', TIMESTAMP => ts1, VERSIONS => 4}
  hbase> t.get 'r1', {FILTER => "ValueFilter(=, 'binary:abc')"}
  hbase> t.get 'r1', 'c1'
  hbase> t.get 'r1', 'c1', 'c2'
  hbase> t.get 'r1', ['c1', 'c2']
  hbase> t.get 'r1', {CONSISTENCY => 'TIMELINE'}
  hbase> t.get 'r1', {CONSISTENCY => 'TIMELINE', REGION_REPLICA_ID => 1}

get 'user' , 'rk0001'
get 'user' , 'rk0002' , {COLUMN => 'info:name', VERSIONS => 10}

扫描数据 scan
  hbase> scan 'hbase:meta'
  hbase> scan 'hbase:meta', {COLUMNS => 'info:regioninfo'}
  hbase> scan 'ns1:t1', {COLUMNS => ['c1', 'c2'], LIMIT => 10, STARTROW => 'xyz'}
  hbase> scan 't1', {COLUMNS => ['c1', 'c2'], LIMIT => 10, STARTROW => 'xyz'}
  hbase> scan 't1', {COLUMNS => 'c1', TIMERANGE => [1303668804, 1303668904]}
  hbase> scan 't1', {REVERSED => true}
  hbase> scan 't1', {ROWPREFIXFILTER => 'row2', FILTER => "
    (QualifierFilter (>=, 'binary:xyz')) AND (TimestampsFilter ( 123, 456))"}
  hbase> scan 't1', {FILTER =>
    org.apache.hadoop.hbase.filter.ColumnPaginationFilter.new(1, 0)}
  hbase> scan 't1', {CONSISTENCY => 'TIMELINE'}
  hbase> scan 't1', { COLUMNS => ['c1', 'c2'], ATTRIBUTES => {'mykey' => 'myvalue'}}
  hbase> scan 't1', { COLUMNS => ['c1', 'c2'], AUTHORIZATIONS => ['PRIVATE','SECRET']}
  hbase> scan 't1', {COLUMNS => ['c1', 'c2'], CACHE_BLOCKS => false}
  hbase> scan 't1', {RAW => true, VERSIONS => 10}
  hbase> t = get_table 't'
  hbase> t.scan

scan 'user'

创建user表，里面包含info，date两个列族
create 'user','info','data'(不指定VERSIONS时，默认VERSIONS=1)
create 'user',{NAME => 'info', VERSIONS => 5},{NAME => 'data' , VERSIONS => 5 }

向user表中插入信息，row key 值为rk0001 列族info中添加name列标识符，值为zhangsan
put 'user','rk0001','info:name','zhansan'
向user表中插入信息，row key 值为rk0001 列族info中添加gender列标识符，female
put 'user','rk0001','info:gender','female'
向user表中插入信息，row key 值为rk0001 列族info中添加age列标识符，值为18
put 'user','rk0001','info:age','18'
向user表中插入信息，row key 值为rk0001 列族info中添加pic列标识符，值为picture
put 'user','rk0001','info:pic','picture'

获取user表中，row key为rk0001的所有信息
get  'user','rk0001'

获取user表中，row key为rk0001，info列族中的所有信息
get 'user', 'rk0001', 'info'

获取user表中，row key为rk0001，info列族中的name和age列标识符中的信息
get 'user', 'rk0001', 'info:name', 'info:age'

获取user表中，row key为rk0001，info,data 列族的信息
get 'user', 'rk0001', 'info', 'data'
get 'user', 'rk0001', {COLUMN => ['info' ,'data']}
get 'user', 'rk0001', {COLUMN => ['info:name' ,'data:age']}

获取user表中，row key为rk0001，列族为info，版本号最新5个的信息
get 'user', 'rk0001', {COLUMN =>'info'},{VERSIONS =>5}
get 'user', 'rk0001', {COLUMN =>'info:name'},{VERSIONS =>5}

获取user表中row key 为rk0001，cell的值为zjs的信息
get 'user', 'rk0001', {FILTER => "ValueFilter(=, 'binary:zjs')"}

后去user表中row key为rk0001，列标示符中含有’a‘的信息
get 'user', 'rk0001' ,{FILTER => "(QualifierFilter(=,'substring:z'))"}


查询user表中所有的信息

scan 'user'

查询user表中列族为info的信息
scan 'user', {COLUMUN => 'info'}
scan 'user', {COLUMN => 'info',RAW =>true, VERSIONS =>5}

查询user表中，列族为info，data的信息
scan 'user', {COLUMN => ['info', 'data']}
scan 'user', {COLUMN => ['info:name', 'data:age']}

查询user表中列族为info，列标识符为name的信息
scan 'user', {COLUMN =>'info:name'}
查询user表中列族为info，列标识符为name的信息,版本最多5个
scan 'user', {COLUMN =>'info:name'},{VERSIONS => 5}

查询user表中，列族为info个data且列标识符含有a字符的信息
scan 'user' ,{COLUMN =>['info' , 'data'], FILTER => "(QualifierFilter(=,'substring:a'))"}
 scan 'user' ,{COLUMN =>['info' , 'data'], FILTER => "(QualifierFilter(=,'substring:a'))"}
ROW                                COLUMN+CELL
 rk0001                            column=data:age, timestamp=1529670010281, value=19
 rk0001                            column=data:name, timestamp=1529670010202, value=lt
 rk0001                            column=info:age, timestamp=1529670009879, value=18
 rk0001                            column=info:name, timestamp=1529669995801, value=zjs
 rk0002                            column=data:age, timestamp=1529670128578, value=1919
 rk0002                            column=data:name, timestamp=1529670128531, value=ltlt
 rk0002                            column=info:age, timestamp=1529670128445, value=1818
 rk0002                            column=info:name, timestamp=1529670128315, value=zjszjs
2 row(s) in 0.0410 seconds

查询user表中，列族为info，rk范围是[rk0001,rk0003]的数据
scan 'user', {CLOUMN =>'info' , STARTROW => 'rk0001' , ENDROW => 'rk0003'}
scan 'user', {COLUMN =>'info' , STARTROW => 'rk0001' , ENDROW => 'rk0003'}
ROW                                COLUMN+CELL
 rk0001                            column=info:age, timestamp=1529670009879, value=18
 rk0001                            column=info:name, timestamp=1529669995801, value=zjs
 rk0001                            column=info:sex, timestamp=1529670010078, value=\xE7\x94\xB7
 rk0002                            column=info:age, timestamp=1529670128445, value=1818
 rk0002                            column=info:name, timestamp=1529670128315, value=zjszjs
 rk0002                            column=info:sex, timestamp=1529670128489, value=\xE7\x94\xB7\xE7\x94\xB7
2 row(s) in 0.0320 seconds

查询user表中，row key 以rk字符开头的
scan 'user' ,{FILTER => "PrefixFilter('rk')"}
scan 'user' ,{FILTER => "PrefixFilter('rk')"}
ROW                                COLUMN+CELL
 rk0001                            column=data:age, timestamp=1529670010281, value=19
 rk0001                            column=data:name, timestamp=1529670010202, value=lt
 rk0001                            column=data:sex, timestamp=1529670012330, value=\xE5\xA5\xB3
 rk0001                            column=info:age, timestamp=1529670009879, value=18
 rk0001                            column=info:name, timestamp=1529669995801, value=zjs
 rk0001                            column=info:sex, timestamp=1529670010078, value=\xE7\x94\xB7
 rk0002                            column=data:age, timestamp=1529670128578, value=1919
 rk0002                            column=data:name, timestamp=1529670128531, value=ltlt
 rk0002                            column=data:sex, timestamp=1529670129123, value=\xE5\xA5\xB3\xE5\xA5\xB3
 rk0002                            column=info:age, timestamp=1529670128445, value=1818
 rk0002                            column=info:name, timestamp=1529670128315, value=zjszjs
 rk0002                            column=info:sex, timestamp=1529670128489, value=\xE7\x94\xB7\xE7\x94\xB7
2 row(s) in 0.0640 seconds

查询user中，指定范围的数据
scan 'user', {TIMERANGE => [1529670010202,1529670012330]}
ROW                                COLUMN+CELL
 rk0001                            column=data:age, timestamp=1529670010281, value=19
 rk0001                            column=data:name, timestamp=1529670010202, value=lt
1 row(s) in 0.0190 seconds

删除数据
删除user表中row key为rk0001，info列族中列标识符为name的数据
delete 'user','rk0001','info:name'
0 row(s) in 0.4830 seconds
hbase(main):002:0> scan 'user'
ROW                                COLUMN+CELL
 rk0001                            column=data:age, timestamp=1529670010281, value=19
 rk0001                            column=data:name, timestamp=1529670010202, value=lt
 rk0001                            column=data:sex, timestamp=1529670012330, value=\xE5\xA5\xB3
 rk0001                            column=info:age, timestamp=1529670009879, value=18
 rk0001                            column=info:sex, timestamp=1529670010078, value=\xE7\x94\xB7
 rk0002                            column=data:age, timestamp=1529670128578, value=1919
 rk0002                            column=data:name, timestamp=1529670128531, value=ltlt
 rk0002                            column=data:sex, timestamp=1529670129123, value=\xE5\xA5\xB3\xE5\xA5\xB3
 rk0002                            column=info:age, timestamp=1529670128445, value=1818
 rk0002                            column=info:name, timestamp=1529670128315, value=zjszjs
 rk0002                            column=info:sex, timestamp=1529670128489, value=\xE7\x94\xB7\xE7\x94\xB7
2 row(s) in 0.0870 seconds

删除user表，row key为rk0002，列标识符为info：name，timestamp为1529670128315的数据
delete 'user', 'rk0002', 'info:name', 1529670128315
0 row(s) in 0.0100 seconds

hbase(main):004:0> scan 'user'
ROW                                COLUMN+CELL
 rk0001                            column=data:age, timestamp=1529670010281, value=19
 rk0001                            column=data:name, timestamp=1529670010202, value=lt
 rk0001                            column=data:sex, timestamp=1529670012330, value=\xE5\xA5\xB3
 rk0001                            column=info:age, timestamp=1529670009879, value=18
 rk0001                            column=info:sex, timestamp=1529670010078, value=\xE7\x94\xB7
 rk0002                            column=data:age, timestamp=1529670128578, value=1919
 rk0002                            column=data:name, timestamp=1529670128531, value=ltlt
 rk0002                            column=data:sex, timestamp=1529670129123, value=\xE5\xA5\xB3\xE5\xA5\xB3
 rk0002                            column=info:age, timestamp=1529670128445, value=1818
 rk0002                            column=info:sex, timestamp=1529670128489, value=\xE7\x94\xB7\xE7\x94\xB7
2 row(s) in 0.0480 seconds

清理user表中的数据
truncate 'user'
修改表结构
首先停用user表(新版本不需要)
disable 'user'
添加两个列族
alter 'user', NAME =>'f1'
alter 'user', NAME =>'f2'
启用表
enable 'user'


删除一个列族
disable 'user'
alter 'user' ,NAME => 'f1', METHOD => 'delete'
或者
alter 'user', 'delete' => 'f1'

添加列族f1,同时删除列族f2
alter 'user', {NAME => 'f1'},{NAME => 'f2', METHOD => 'delete'}

将user表中的info列族的版本号改成10
alter 'user', NAME => info , VERSIONS =>5
 disable 'user'
0 row(s) in 2.9250 seconds

hbase(main):002:0> desc 'user'
Table user is DISABLED
user
COLUMN FAMILIES DESCRIPTION
{NAME => 'data', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_SCOPE => '0', VERSIONS => '5', COMPRESSION => 'NONE
', MIN_VERSIONS => '0', TTL => 'FOREVER', KEEP_DELETED_CELLS => 'FALSE', BLOCKSIZE => '65536', IN_MEMORY => 'false', BLOCKCACHE => 't
rue'}
{NAME => 'info', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_SCOPE => '0', VERSIONS => '5', COMPRESSION => 'NONE
', MIN_VERSIONS => '0', TTL => 'FOREVER', KEEP_DELETED_CELLS => 'FALSE', BLOCKSIZE => '65536', IN_MEMORY => 'false', BLOCKCACHE => 't
rue'}
2 row(s) in 0.0620 seconds

hbase(main):003:0> alter 'user', NAME=> 'info', VERSIONS => 15
Updating all regions with the new schema...
1/1 regions updated.
Done.
0 row(s) in 2.0130 seconds

hbase(main):004:0> enable
enable                     enable_all                 enable_peer                enable_table_replication
hbase(main):004:0> enable 'user'
0 row(s) in 1.4350 seconds

hbase(main):005:0> desc 'user'
Table user is ENABLED
user
COLUMN FAMILIES DESCRIPTION
{NAME => 'data', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_SCOPE => '0', VERSIONS => '5', COMPRESSION => 'NONE
', MIN_VERSIONS => '0', TTL => 'FOREVER', KEEP_DELETED_CELLS => 'FALSE', BLOCKSIZE => '65536', IN_MEMORY => 'false', BLOCKCACHE => 't
rue'}
{NAME => 'info', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_SCOPE => '0', VERSIONS => '15', COMPRESSION => 'NON
E', MIN_VERSIONS => '0', TTL => 'FOREVER', KEEP_DELETED_CELLS => 'FALSE', BLOCKSIZE => '65536', IN_MEMORY => 'false', BLOCKCACHE => '
true'}
2 row(s) in 0.0210 seconds







启用表
enable 'user'

删除表
disable 'user'
drop 'user'