一、hbase shell的基礎命令
# 版本號查看
[root@Test-Hadoop-NN-01 hbase]$ ./bin/hbase version
HBase 2.4.0
Source code repository git://apurtell-ltm.internal.salesforce.com/Users/apurtell/src/hbase revision=282ab70012ae843af54a6779543ff20acbcbb629# 客戶端登錄
[root@Cloud-Hadoop-NN-01 hbase]$ ./bin/hbase shell# 查看所有表
hbase> list### 創建數據表student，包含Sname、Ssex、Sage、Sdept、course列族/列
### 說明：插入數據指定列族不指定列名時，默認使用列名“” ！！！
hbase> create 'student','Sname','Ssex','Sage','Sdept','course'# 描述表信息
hbase> describe 'student'
Table student is ENABLED
student
COLUMN FAMILIES DESCRIPTION
{NAME => 'Sage', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', COMPRESSION => 'NONE', TTL => 'FOREVER', MIN_VERSIO
NS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'} {NAME => 'Sdept', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', COMPRESSION => 'NONE', TTL => 'FOREVER', MIN_VERSI
ONS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'} {NAME => 'Sname', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', COMPRESSION => 'NONE', TTL => 'FOREVER', MIN_VERSI
ONS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'} {NAME => 'Ssex', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', COMPRESSION => 'NONE', TTL => 'FOREVER', MIN_VERSIO
NS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'} {NAME => 'course', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', COMPRESSION => 'NONE', TTL => 'FOREVER', MIN_VERS
IONS => '0', BLOCKCACHE => 'true', BLOCKSIZE => '65536', REPLICATION_SCOPE => '0'}
5 row(s)# 插入數據表student：Sname:xing='Shen'
hbase> put 'student','10001','Sname:xing','Shen'
hbase> put 'student','10001','Sname:ming','HY'
hbase> put 'student','10001','Ssex',1# 查詢數據表student：rowkey='10001'
hbase> get 'student','10001'
Took 0.0052 seconds
hbase:014:0> get 'student','10001'
COLUMN CELL Sname:ming timestamp=2025-05-14T16:42:55.882, value=HY Sname:xing timestamp=2025-05-14T16:42:43.429, value=Shen Ssex: timestamp=2025-05-14T16:48:28.510, value=1
1 row(s)
Took 0.0161 seconds # 查詢數據表student：全部數據
hbase> scan 'student'
ROW COLUMN+CELL 10001 column=Sname:ming, timestamp=2025-05-14T16:42:55.882, value=HY 10001 column=Sname:xing, timestamp=2025-05-14T16:42:43.429, value=Shen 10001 column=Ssex:, timestamp=2025-05-14T16:48:28.510, value=1
1 row(s)
Took 0.0135 seconds ### 創建數據表scores：包含grade,course字段
hbase> create 'scores','grade','course'# 插入數據表scores：rowkey=zhangsan01 ......
hbase> put 'scores','zhangsan01','grade:','101'
hbase> put 'scores','zhangsan01','course:art','90'
hbase> put 'scores','zhangsan01','course:math','99',1498003561726
#這里手動設置時間戳的時候一定不能大于當前系統時間，否則無法刪除該數據。這里手動設置數據是為了下面的DependentColumnFilter過濾器試驗。可以查看一下插入第一條數據的時間戳，再插入第二條數據的時間戳為第一條數據的時間戳
hbase> put 'scores','zhangsan02','grade:','102',1498003601365
hbase> put 'scores','zhangsan02','course:art','90'
hbase> put 'scores','zhangsan02','course:math','66',1498003561726
hbase> put 'scores','lisi01','grade:','201',1498003561726
hbase> put 'scores','lisi01','course:art','89'
hbase> put 'scores','lisi01','course:math','89',1498003561726# 查詢兩個rowkey之間的數據
hbase> scan 'scores',{STARTROW=>'zhangsan01',STOPROW=>'zhangsan02'}
ROW COLUMN+CELL zhangsan01 column=course:art, timestamp=1498003561726, value=90 zhangsan01 column=course:math, timestamp=1498003561726, value=99 zhangsan01 column=grade:, timestamp=1498003593575, value=101
1 row(s) in 0.0140 seconds# 根據列名查詢
hbase> scan 'scores',{COLUMNS=>'course:art'}
ROW COLUMN+CELL lisi01 column=course:art, timestamp=1498003655021, value=89 zhangsan01 column=course:art, timestamp=1498003561726, value=90 zhangsan02 column=course:art, timestamp=1498003601365, value=90
3 row(s) in 0.0120 seconds# 查詢兩個rowkey之間&根據列名來查詢
hbase> scan 'scores',{COLUMNS=>'course:art',STARTROW=>'zhangsan01',STOPROW=>'zhangsan02'}
ROW COLUMN+CELL zhangsan01 column=course:art, timestamp=1498003561726, value=90
1 row(s) in 0.0110 seconds# 限制查找條數
hbase> scan 'scores',{LIMIT=>1}
ROW COLUMN+CELL zhangsan01 column=course:art, timestamp=1498003561726, value=90 zhangsan01 column=course:math, timestamp=1498003561726, value=99 zhangsan01 column=grade:, timestamp=1498003593575, value=101
1 row(s) in 0.0140 seconds# 查詢時序數據
hbase> get 'pfme','dh_p_030_13030006@_@1747090800@_@'
# 查詢時序數據
hbase> get 'pfme','dh_p_030_13030006@_@1747130400@_@FF-67-12-02-10-6A'# 客戶端退出
hbase> exit
二、hbase shell 實現rowkey的模糊查詢
# 前綴匹配法
#查詢以"2025"開頭的rowkey，左閉右開區間（性能較高）
hbase> scan 'table_name', {STARTROW => '2025', STOPROW => '2025z'}# 正則表達式過濾
#查詢包含"123"的rowkey（性能較低，全表掃描時慎用，建議配合STARTROW/STOPROW縮小范圍）
hbase> scan 'table_name', {FILTER => "RowFilter(=, 'regexstring:.*123.*')"}# 子串匹配優化方案
#查詢中間含"123"的rowkey（需預知固定長度），適用于已知字段固定位置時的精準匹配
hbase> scan 'table_name', { STARTROW => '000123', STOPROW => '999123z', FILTER => "ValueFilter(=, 'substring:123')"}# 分頁模糊查詢
#分頁查詢含"123"的rowkey（每頁10條），通過STARTROW參數實現翻頁功能
hbase> scan 'table_name', { FILTER => "PageFilter(10) AND RowFilter(=, 'substring:123')"}#eg: 查詢DH專業的ct-tsdb
scan 'pfme', {STARTROW => 'dh_p_030_13030006@_@1747206000', STOPROW => 'dh_p_030_13030006@_@1747206000z'}
三、hbase shell 實現列值的模糊查詢
#查詢列族cf和列名c1中以123開頭的所有行
hbase> scan 'table_name', {COLUMNS => ['cf:c1'], FILTER => "(PrefixFilter('123'))"}#查詢指定的列值中包含"123"的所有行
hbase> scan 'table_name', {COLUMNS => ['cf1:c1', 'cf2:c2'], FILTER => "ValueFilter(=, regexstring:'.*123.*')"}
參考文檔：
https://blog.csdn.net/m0_37739193/article/details/73615016#
https://blog.csdn.net/vbirdbest/article/details/88236575
