Hbaseshell scan多种过滤操作

查询数据

get 'bjcjtest1_hdrive_2000',"\x00\x80\x03\x8D\x96\xA9\xDCO\xB6"

scan 'tts_201905',{STARTROW=>"\x00\x80\x0C\x9FD\xF1\x09|\x7F",STOPROW=>"\x00\x80\x0DJB\x03\xED\xAC\x0D\x00"}

get多版本

get 't1','rowkey1',{COLUMN=>'f1:name',VERSIONS=>3}

前缀过滤扫描

scan 'station429_hdrive_40000', {FILTER => "(PrefixFilter ('aaa')"}

通过hbase shell命令触发compaction

major_compact

查看meta表

scan 'hbase:meta'

查看表数据，scan过滤器

scan 'station428_hdrive_40000', {LIMIT=>1}

scan 'users',{FILTER=>"MultipleColumnPrefixFilter('a','c')"}

scan 'users',{FILTER=>'FirstKeyOnlyFilter()'}

scan 'users',{FILTER=>"ColumnPrefixFilter('ag')"}

scan 'users',{FILTER=>"QualifierFilter(=,'regexstring:.ge')"}

scan 'users',{FILTER=>"SingleColumnValueFilter('info','age',=,'regexstring:.4')"}

scan 'users',{FILTER=>"MultipleColumnPrefixFilter('a','c')"}  //指定多个列前缀。

scan 'users',{FILTER=>"ColumnRangeFilter('a',true,'c',false)"} //从列a开始，到C之前的

scan 'tts_201905',{FILTER=>'KeyOnlyFilter()',STARTROW=>"\x00\x80\x0C\x9FD\xF1\x09|\x7F",STOPROW=>"\x00\x80\x0DJB\x03\xED\xAC\x0D\x00"}

scan 'users',{FILTER=>"RowFilter(=,'substring:01')"}

scan 'testByCrq', FILTER=>"RowFilter(=,'substring:111')"

scan 'testByCrq', FILTER=>"RowFilter(=,'binary:0111486816556')"

scan 'testByCrq', FILTER=>"RowFilter(<=,'binary:0111486816556')"

scan 'table',FILTER=>"RowFilter(=,'regexstring:.2')"

scan 'table',FILTER=>"RowFilter(=,'regexstring:row2.')"

scan 'test1', {FILTER => RowFilter.new(CompareFilter::CompareOp.valueOf('EQUAL'), SubstringComparator.new('ts'))}

scan 'test1', {STARTROW=>'user1|ts2', FILTER => "PrefixFilter ('user1')"}

scan 'test1', FILTER=>"ColumnPrefixFilter('s') AND ( ValueFilter(=,'substring:123') OR ValueFilter(=,'substring:222') )"

scan ‘tweet0’, {FILTER=>”SingleColumnValueFilter(‘info’,’pubtime’,=,’regexstring:2014-11-08.*’)”}

scan ‘tweet0’, {FILTER=>”SingleColumnValueFilter(‘info’,’pubtime’,>=,’binary:2014-11-08 19:26:27’) AND SingleColumnValueFilter(‘info’,’pubtime’,<=,’binary:2014-11-10 20:20:00’)”}

scan ‘tweet0’, {FILTER=>”SingleColumnValueFilter(‘emotion’,’PB’,=,’binary:\x00\x00\x00\x05’)”, COLUMNS=>[‘emotion:PB’]}

scanner规范：

TIMERANGE，

FILTER，

LIMIT，

STARTROW（start row），

STOPROW（stop row），

ROWPREFIXFILTER（row prefix filter,行前缀）

TIMESTAMP，

MAXLENGTH，

or COLUMNS，

CACHE，

or RAW，

VERSIONS

Snapshot

snapshot 'myTable','myTableSnapshot-122112'

Listing Snapshots

list_snapshots

Deleting Snapshots

delete_snapshot 'myTableSnapshot-122112'

Restore a snapshot

disable 'myTable'
restore_snapshot 'myTableSnapshot-122112'

起始查询，返回结果不包括结束值

scan 'testtable',{STARTROW =>'key5',ENDROW =>'rowkey2'}

创建预分区表

create 'testsplit444', 'f', SPLITS => ['999trnv986rtpivo', 'h88jfuxlij5l5t5k', 'po4fdzxo4ifld24z']

create 'split_table_test', 'cf', {SPLITS_FILE => 'region_split_info.txt'}

create 't3','f1', { NUMREGIONS => 50, SPLITALGO => 'HexStringSplit' , COMPRESSION => 'snappy'}

查看region信息

status 'simple'

检测normalizer状态和enable/disable normalizer

normalizer_enabled

normalizer_switch false

建表以后改压缩格式及分裂政策

alter 'ts001_201905', NAME => 'f', COMPRESSION => 'GZ'

alter 'tablename', {METADATA => {'SPLIT_POLICY' => 'org.apache.hadoop.hbase.regionserver.DisabledRegionSplitPolicy'}}

create 'test2', 'cf2', {METADATA => {'SPLIT_POLICY' => 'org.apache.hadoop.hbase.regionserver.ConstantSizeRegionSplitPolicy'}}

create 'test', {METADATA => {'SPLIT_POLICY' => 'org.apache.hadoop.hbase.regionserver.ConstantSizeRegionSplitPolicy'}},{NAME => 'cf1'}

alter 'tts_201905',{METHOD => 'table_att',CONFIGURATION => {'SPLIT_POLICY' => 'org.apache.hadoop.hbase.regionserver.ConstantSizeRegionSplitPolicy'}},{NAME => 'f'}