python+hiveserver2

gistfile1.py

import sys
import os
 
sys.path.append('/opt/cloudera/parcels/CDH/share/hue/apps/beeswax/gen-py')
 
from TCLIService import TCLIService
from TCLIService.ttypes import TOpenSessionReq, TGetTablesReq, TFetchResultsReq,\
  TStatusCode, TGetResultSetMetadataReq, TGetColumnsReq, TType,\
  TExecuteStatementReq, TGetOperationStatusReq, TFetchOrientation,\
  TCloseSessionReq, TGetSchemasReq, TCancelOperationReq
 
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
 
def get_value(colValue):
    if colValue.boolVal is not None:
      return colValue.boolVal.value
    elif colValue.byteVal is not None:
      return colValue.byteVal.value
    elif colValue.i16Val is not None:
      return colValue.i16Val.value
    elif colValue.i32Val is not None:
      return colValue.i32Val.value
    elif colValue.i64Val is not None:
      return colValue.i64Val.value
    elif colValue.doubleVal is not None:
      return colValue.doubleVal.value
    elif colValue.stringVal is not None:
      return colValue.stringVal.value
 
socket = TSocket.TSocket('localhost', 10000)
transport = TTransport.TBufferedTransport(socket)
protocol = TBinaryProtocol.TBinaryProtocol(transport)
client = TCLIService.Client(protocol)
transport.open()
 
kwargs = {'username': '...', 'configuration': {}}
kwargs['configuration'].update({'hive.server2.proxy.user': '...'})
request=TOpenSessionReq(**kwargs)
 
res = client.OpenSession(request)
session = res.sessionHandle
hql = "select * from ..."
query = TExecuteStatementReq(session, statement=hql, confOverlay={})
 
res = client.ExecuteStatement(query)
 
fetch_req = TFetchResultsReq(operationHandle=res.operationHandle, orientation=TFetchOrientation.FETCH_NEXT, maxRows=100)
resultsRes = client.FetchResults(fetch_req)
 
rows = []
for row in resultsRes.results.rows:
    rowData= []
    for i, col in enumerate(row.colVals):
        rowData.append(get_value(col))
    rows.append(rowData)
    if len(resultsRes.results.rows) == 0:
        break
 
for row in rows:
    print row