0

I am write a python script to load data from hbase. But things seem to goes wrong in thrift generated files. Here is my code:

def create_hbase_connection():
    thrift_socket = TSocket.TSocket(thrift_server, thrift_port)
    thrift_socket.setTimeout(thrift_timeout)
    thrift_transport = TTransport.TFramedTransport(thrift_socket)
    thrift_protocol = TBinaryProtocol.TBinaryProtocolAccelerated(thrift_transport)
    thrift_client = THBaseService.Client(thrift_protocol)
    try:
        thrift_transport.open()
    except Exception as e:
        print "connect to hbase thrift failed. (%s)" % e
        sys.exit()

    return thrift_protocol, thrift_client

def fetch_rows_from_hbase(thrift_protocol, thrift_client, start_row = None):
    tscan = ttypes.TScan()
    if start_row != None:
        tscan.startRow = start_row
    tscan.maxVersions = max_versions
    tscan.filterString = "FamilyFilter(!=, 'binary:ge')"
    scan_id = thrift_client.openScanner(hbase_table_name, tscan)
    result = thrift_client.getScannerRows(scan_id, row_limits + 1)
    print result
    print "=================================================\n"
    thrift_client.closeScanner(scan_id)
    thrift_protocol.close()

if __name__ == '__main__':
    thrift_protocol, thrift_client = create_hbase_connection()
    fetch_rows_from_hbase(thrift_protocol, thrift_client)

And here is the error:

Traceback (most recent call last): File "./load_hbase.py", line 46, in fetch_rows_from_hbase(thrift_protocol, thrift_client) File "./load_hbase.py", line 37, in fetch_rows_from_hbase scan_id = thrift_client.openScanner(hbase_table_name, tscan) File "/home/lishaohua/kpn/load_hbase/thrift2/hbase/THBaseService.py", line 715, in openScanner return self.recv_openScanner() File "/home/lishaohua/kpn/load_hbase/thrift2/hbase/THBaseService.py", line 735, in recv_openScanner result.read(iprot) File "/home/lishaohua/kpn/load_hbase/thrift2/hbase/THBaseService.py", line 3278, in read fastbinary.decode_binary(self, iprot.trans, (self.class, self.thrift_spec)) AttributeError: 'TFramedTransport' object has no attribute 'trans'

I check the code in TTransport.py, TFramedTransport has the attribute self.__trans. How to fix this? I can simply change tans to __trans, but there are more problems.

Charles
  • 19
  • 6

1 Answers1

0

I used TBufferedTransport instead of TFramedTransport, and it worked. You can try my solution below:

class ThriftConn(object):
    def __init__(self, ip, port, service_cls):
        self.socket = TSocket.TSocket(ip, port)
        self.trans = TTransport.TBufferedTransport(self.socket)                                                                                                                                                   
        self.protocol = TBinaryProtocol.TBinaryProtocol(self.trans)
        self.client = service_cls.Client(self.protocol)

    def __enter__(self):
        self.trans.open()

    def __exit__(self, exception_type, exception_value, 
        exception_traceback):
        self.trans.close()

HBASE_SERVER_CLIENT = ThriftConn(ip, port, THBaseService)
with HBASE_SERVER_CLIENT:
    scan = TScan()
    scan_id = HBASE_SERVER_CLIENT.client.openScanner(table, scan)
Stephen Rauch
  • 47,830
  • 31
  • 106
  • 135
shangliuyan
  • 124
  • 1
  • 2