python透過thrift操作hbase實例

thrift 是facebook開發並開源的二進位通訊中間件，透過thrift，我們可以充分利用各個語言的優勢，編寫高效的程式碼。

關於thrift的論文：http://pan.baidu.com/share/link?shareid=234128&uk=3238841275

機

/ubuntu/

安裝完成後到hbase的目錄下，找到Hbase.thrift，該檔案在

hbase-0.94.4/src/main/resources/org/ache/mhad thrift下可以找到

thrift --gen python hbase.thrift 會產生gen-py資料夾，將其修改成hbase

安裝

啟動hbase的thrift服務：bin/hbase-daemon.sh start thrift 預設連接埠是9090

創建表:

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
  
from hbase import Hbase
from hbase.ttypes import *
  
transport = TSocket.TSocket('localhost', 9090);
  
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport);
  
client = Hbase.Client(protocol)
transport.open()
  
  
contents = ColumnDescriptor(name='cf:', maxVersions=1)
client.createTable('test', [contents])
  
print client.getTableNames()

。看到剛剛的test表已經建立成功。

插入資料：

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
  
from hbase import Hbase
  
from hbase.ttypes import *
  
transport = TSocket.TSocket('localhost', 9090)
  
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
  
transport.open()
  
row = 'row-key1'
  
mutations = [Mutation(column="cf:a", value="1")]
client.mutateRow('test', row, mutations, None)

取得一行資料：

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
  
from hbase import Hbase
from hbase.ttypes import *
  
transport = TSocket.TSocket('localhost', 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
  
transport.open()
  
tableName = 'test'
rowKey = 'row-key1'
  
result = client.getRow(tableName, rowKey, None)
print result
for r in result:
    print 'the row is ' , r.row
    print 'the values is ' , r.columns.get('cf:a').value

回傳多行則需要使用scan：

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
  
from hbase import Hbase
from hbase.ttypes import *
  
transport = TSocket.TSocket('localhost', 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
transport.open()
  
scan = TScan()
tableName = 'test'
id = client.scannerOpenWithScan(tableName, scan, None)
  
result2 = client.scannerGetList(id, 10)
  
print result2

scannerGet則是每次只取一行資料：

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
  
from hbase import Hbase
from hbase.ttypes import *
  
transport = TSocket.TSocket('localhost', 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
transport.open()
  
scan = TScan()
tableName = 'test'
id = client.scannerOpenWithScan(tableName, scan, None)
result = client.scannerGet(id)
while result:
    print result
    result = client.scannerGet(id)