Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support for thrift over HTTPS for Hive connections #306

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Support for thrift over HTTPS for Hive connections #306

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion dev_requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,6 @@ pytest-timeout==1.2.0
requests>=1.0.0
requests_kerberos>=0.12.0
sasl>=0.2.1
thrift>=0.10.0
thrift>=0.13.0
#thrift_sasl>=0.1.0
git+https://github.com/cloudera/thrift_sasl # Using master branch in order to get Python 3 SASL patches
26 changes: 24 additions & 2 deletions pyhive/hive.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,8 @@
import thrift.protocol.TBinaryProtocol
import thrift.transport.TSocket
import thrift.transport.TTransport
import thrift.transport.THttpClient
import re

# PEP 249 module globals
apilevel = '2.0'
Expand Down Expand Up @@ -98,8 +100,8 @@ class Connection(object):
"""Wraps a Thrift session"""

def __init__(self, host=None, port=None, username=None, database='default', auth=None,
configuration=None, kerberos_service_name=None, password=None,
thrift_transport=None):
configuration=None, kerberos_service_name=None, password=None, path='cliservice',
cafile=None, cert_file=None, key_file=None, thrift_transport=None):
"""Connect to HiveServer2

:param host: What host HiveServer2 runs on
Expand All @@ -109,6 +111,10 @@ def __init__(self, host=None, port=None, username=None, database='default', auth
:param configuration: A dictionary of Hive settings (functionally same as the `set` command)
:param kerberos_service_name: Use with auth='KERBEROS' only
:param password: Use with auth='LDAP' or auth='CUSTOM' only
:param path: Thrift over HTTPS service endpoint. Default value is cliservice
:param cafile: The CA certificate file to verify the peer (Hive Server 2)
:param cert_file: Client certificate for mTLS
:param key_file: Client private key for mTLS
:param thrift_transport: A ``TTransportBase`` for custom advanced usage.
Incompatible with host, port, auth, kerberos_service_name, and password.

Expand Down Expand Up @@ -174,6 +180,22 @@ def sasl_factory():
sasl_client.init()
return sasl_client
self._transport = thrift_sasl.TSaslClientTransport(sasl_factory, sasl_auth, socket)
elif auth == 'CERTIFICATE':
has_incompatible_arg = (
host is None
or port is None
or path is None
or cafile is None
or cert_file is None
or key_file is None
)
if has_incompatible_arg:
raise ValueError("CERTIFICATE (Thrift over HTTPS) auth cannot be used without "
"host/port/path/cafile/cert_file/key_file")
path = re.sub(r'^[/]*', '', path)
uri = 'https://' + host + ':' + str(port) + '/' + path
self._transport = thrift.transport.THttpClient.THttpClient(uri_or_host=uri, cafile=cafile, cert_file=cert_file, key_file=key_file)

else:
# All HS2 config options:
# https://cwiki.apache.org/confluence/display/Hive/Setting+Up+HiveServer2#SettingUpHiveServer2-Configuration
Expand Down