Question

我在这里遇到了一个小问题： - 我可以使用shell中的过滤器扫描表格 - 我可以使用hbase shell删除一行但我找不到扫描表格的方法，迭代结果并删除它们。是否有可能“管道”？ hbase shell中的命令还是我必须做一个ruby脚本（注意：我不知道如何做）

我想做什么：

扫描＆＃39; mytable＆＃39;，{COLUMNS =＆gt; [＆＃39; c：1]，FILTER =＆gt; ＆＃34; SingleColumnValueFilter（＆＃39; c＆＃39;，＆＃39; 1＆＃39;，=，＆＃39;二进制：-1＆＃39;，true，true）＆＃34;} |删除＆＃39; mytable＆＃39;，$ result_i，＆＃39; c：1＆＃39;

由于

Answer 1

好的，我明白了，我在这里发布了rb脚本

require 'java'
require 'net/http'

import java.io.IOException

import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.HConstants
import org.apache.hadoop.hbase.MasterNotRunningException
import org.apache.hadoop.hbase.client.HBaseAdmin
import org.apache.hadoop.hbase.client.HTable
import org.apache.hadoop.hbase.client.Scan
import org.apache.hadoop.hbase.client.Delete
import org.apache.hadoop.hbase.filter.FirstKeyOnlyFilter
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter
import org.apache.hadoop.hbase.filter.CompareFilter
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase.util.Writables
import org.apache.hadoop.hbase.HTableDescriptor
import org.apache.hadoop.hbase.HColumnDescriptor

log_level = org.apache.log4j.Level::ERROR
org.apache.log4j.Logger.getLogger("org.apache.zookeeper").setLevel(log_level)
org.apache.log4j.Logger.getLogger("org.apache.hadoop.hbase").setLevel(log_level)

config = HBaseConfiguration.create
config.set 'fs.default.name', config.get(HConstants::HBASE_DIR)

TAB = 'mytable'.to_java_bytes
FAM = 'c'.to_java_bytes
ID = '1'.to_java_bytes

scan = Scan.new()

scan.cache_blocks = false
scan.caching = 10
scan.addColumn FAM, ID


filter = SingleColumnValueFilter.new(FAM, ID, CompareFilter::CompareOp.valueOf('EQUAL'), '-1'.to_java_bytes)
filter.setFilterIfMissing(true)

scan.setFilter(filter)


iter = nil 
table = nil
scanner = nil
while true
  begin
    table = HTable.new config, TAB
    scanner = table.getScanner(scan)    
    iter = scanner.iterator
    break
  rescue IOException => ioe
    print "Exception trying to scan #{TAB}: #{ioe}"
    sleep 1
  end
end

start = Time.at(java.util.Date.new.getTime/1000)
print "Start Time : " + start.inspect

while iter.hasNext
  result = iter.next
  delete = Delete.new result.getRow()
  delete.deleteColumn(FAM, ID)
  table.delete delete

end

scanner.close


ending = Time.at(java.util.Date.new.getTime/1000)
print "Start Time : " + ending.inspect

Hbase shell - 在扫描结果上调用hbase命令

1 个答案: