This is an automated email from the ASF dual-hosted git repository.
fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new ca704421 Add `hive.kerberos-service-name` configuration option (#2032)
(#2141)
ca704421 is described below
commit ca7044216d00df1ec6863937ca1abd656ce8ff4e
Author: gardenia <[email protected]>
AuthorDate: Tue Jun 24 21:01:33 2025 +0100
Add `hive.kerberos-service-name` configuration option (#2032) (#2141)
<!--
Thanks for opening a pull request!
-->
<!-- In the case this PR will resolve an issue, please replace
${GITHUB_ISSUE_ID} below with the actual Github issue id. -->
<!-- Closes #2032 -->
# Rationale for this change
Added new configuration parameter hive.kerberos-service-name (#2032)
hive.kerberos-service-name
Defaults to "hive"
# Are these changes tested?
added unit test.
# Are there any user-facing changes?
this change adds an optional configuration parameter for the hive
catalog (hive.kerberos-service-name) which defaults to "hive". the
change includes doc updates.
<!-- In the case of user-facing changes, please add the changelog label.
-->
Co-authored-by: Colm Dougan <[email protected]>
---
mkdocs/docs/configuration.md | 9 +++++----
pyiceberg/catalog/hive.py | 14 ++++++++++++--
tests/catalog/test_hive.py | 18 ++++++++++++++++--
3 files changed, 33 insertions(+), 8 deletions(-)
diff --git a/mkdocs/docs/configuration.md b/mkdocs/docs/configuration.md
index 922e60e1..bc514e39 100644
--- a/mkdocs/docs/configuration.md
+++ b/mkdocs/docs/configuration.md
@@ -439,10 +439,11 @@ catalog:
s3.secret-access-key: password
```
-| Key | Example | Description |
-|------------------------------| ------- | --------------------------------- |
-| hive.hive2-compatible | true | Using Hive 2.x compatibility mode |
-| hive.kerberos-authentication | true | Using authentication via Kerberos |
+| Key | Example | Description
|
+|------------------------------| ------- |
------------------------------------ |
+| hive.hive2-compatible | true | Using Hive 2.x compatibility mode
|
+| hive.kerberos-authentication | true | Using authentication via Kerberos
|
+| hive.kerberos-service-name | hive | Kerberos service name (default
hive) |
When using Hive 2.x, make sure to set the compatibility flag:
diff --git a/pyiceberg/catalog/hive.py b/pyiceberg/catalog/hive.py
index 05dd408f..09437dd1 100644
--- a/pyiceberg/catalog/hive.py
+++ b/pyiceberg/catalog/hive.py
@@ -130,6 +130,8 @@ HIVE2_COMPATIBLE_DEFAULT = False
HIVE_KERBEROS_AUTH = "hive.kerberos-authentication"
HIVE_KERBEROS_AUTH_DEFAULT = False
+HIVE_KERBEROS_SERVICE_NAME = "hive.kerberos-service-name"
+HIVE_KERBEROS_SERVICE_NAME_DEFAULT = "hive"
LOCK_CHECK_MIN_WAIT_TIME = "lock-check-min-wait-time"
LOCK_CHECK_MAX_WAIT_TIME = "lock-check-max-wait-time"
@@ -149,9 +151,16 @@ class _HiveClient:
_transport: TTransport
_ugi: Optional[List[str]]
- def __init__(self, uri: str, ugi: Optional[str] = None, kerberos_auth:
Optional[bool] = HIVE_KERBEROS_AUTH_DEFAULT):
+ def __init__(
+ self,
+ uri: str,
+ ugi: Optional[str] = None,
+ kerberos_auth: Optional[bool] = HIVE_KERBEROS_AUTH_DEFAULT,
+ kerberos_service_name: Optional[str] = HIVE_KERBEROS_SERVICE_NAME,
+ ):
self._uri = uri
self._kerberos_auth = kerberos_auth
+ self._kerberos_service_name = kerberos_service_name
self._ugi = ugi.split(":") if ugi else None
self._transport = self._init_thrift_transport()
@@ -161,7 +170,7 @@ class _HiveClient:
if not self._kerberos_auth:
return TTransport.TBufferedTransport(socket)
else:
- return TTransport.TSaslClientTransport(socket,
host=url_parts.hostname, service="hive")
+ return TTransport.TSaslClientTransport(socket,
host=url_parts.hostname, service=self._kerberos_service_name)
def _client(self) -> Client:
protocol = TBinaryProtocol.TBinaryProtocol(self._transport)
@@ -314,6 +323,7 @@ class HiveCatalog(MetastoreCatalog):
uri,
properties.get("ugi"),
property_as_bool(properties, HIVE_KERBEROS_AUTH,
HIVE_KERBEROS_AUTH_DEFAULT),
+ properties.get(HIVE_KERBEROS_SERVICE_NAME,
HIVE_KERBEROS_SERVICE_NAME_DEFAULT),
)
except BaseException as e:
last_exception = e
diff --git a/tests/catalog/test_hive.py b/tests/catalog/test_hive.py
index fef0d6ac..a36425eb 100644
--- a/tests/catalog/test_hive.py
+++ b/tests/catalog/test_hive.py
@@ -48,6 +48,7 @@ from pyiceberg.catalog.hive import (
DO_NOT_UPDATE_STATS,
DO_NOT_UPDATE_STATS_DEFAULT,
HIVE_KERBEROS_AUTH,
+ HIVE_KERBEROS_SERVICE_NAME,
LOCK_CHECK_MAX_WAIT_TIME,
LOCK_CHECK_MIN_WAIT_TIME,
LOCK_CHECK_RETRIES,
@@ -1300,7 +1301,20 @@ def test_create_hive_client_success() -> None:
with patch("pyiceberg.catalog.hive._HiveClient", return_value=MagicMock())
as mock_hive_client:
client = HiveCatalog._create_hive_client(properties)
- mock_hive_client.assert_called_once_with("thrift://localhost:10000",
"user", False)
+ mock_hive_client.assert_called_once_with("thrift://localhost:10000",
"user", False, "hive")
+ assert client is not None
+
+
+def test_create_hive_client_with_kerberos_success() -> None:
+ properties = {
+ "uri": "thrift://localhost:10000",
+ "ugi": "user",
+ HIVE_KERBEROS_AUTH: "true",
+ HIVE_KERBEROS_SERVICE_NAME: "hiveuser",
+ }
+ with patch("pyiceberg.catalog.hive._HiveClient", return_value=MagicMock())
as mock_hive_client:
+ client = HiveCatalog._create_hive_client(properties)
+ mock_hive_client.assert_called_once_with("thrift://localhost:10000",
"user", True, "hiveuser")
assert client is not None
@@ -1313,7 +1327,7 @@ def test_create_hive_client_multiple_uris() -> None:
client = HiveCatalog._create_hive_client(properties)
assert mock_hive_client.call_count == 2
mock_hive_client.assert_has_calls(
- [call("thrift://localhost:10000", "user", False),
call("thrift://localhost:10001", "user", False)]
+ [call("thrift://localhost:10000", "user", False, "hive"),
call("thrift://localhost:10001", "user", False, "hive")]
)
assert client is not None
