Skip to content

Replace BaseHook to Task SDK for apache/spark #52683

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

Merged
amoghrajesh merged 4 commits into from
Jul 4, 2025
Merged

Replace BaseHook to Task SDK for apache/spark #52683

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
496cbf2
Replace BaseHook to Task SDK for apache/spark
bdsoha Jul 2, 2025
7095bf9
Merge branch 'main' into feature/migrate-spark-to-sdk
bdsoha Jul 2, 2025
0df1656
Merge branch 'main' into feature/migrate-spark-to-sdk
bdsoha Jul 3, 2025
5c15116
Ready for review
bdsoha Jul 3, 2025
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
5 changes: 1 addition & 4 deletions providers/apache/spark/src/airflow/providers/apache/spark/hooks/spark_connect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,7 @@
from typing import Any, cast
from urllib.parse import quote, urlparse, urlunparse

try:
from airflow.sdk import BaseHook
except ImportError:
from airflow.hooks.base import BaseHook # type: ignore[attr-defined,no-redef]
from airflow.providers.apache.spark.version_compat import BaseHook
from airflow.utils.log.logging_mixin import LoggingMixin


Expand Down
6 changes: 1 addition & 5 deletions providers/apache/spark/src/airflow/providers/apache/spark/hooks/spark_sql.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,7 @@
from typing import TYPE_CHECKING, Any

from airflow.exceptions import AirflowException, AirflowNotFoundException

try:
from airflow.sdk import BaseHook
except ImportError:
from airflow.hooks.base import BaseHook # type: ignore[attr-defined,no-redef]
from airflow.providers.apache.spark.version_compat import BaseHook

if TYPE_CHECKING:
try:
Expand Down
6 changes: 1 addition & 5 deletions providers/apache/spark/src/airflow/providers/apache/spark/hooks/spark_submit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,7 @@

from airflow.configuration import conf as airflow_conf
from airflow.exceptions import AirflowException

try:
from airflow.sdk import BaseHook
except ImportError:
from airflow.hooks.base import BaseHook # type: ignore[attr-defined,no-redef]
from airflow.providers.apache.spark.version_compat import BaseHook
from airflow.security.kerberos import renew_from_kt
from airflow.utils.log.logging_mixin import LoggingMixin

Expand Down
9 changes: 9 additions & 0 deletions providers/apache/spark/src/airflow/providers/apache/spark/version_compat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,13 @@ def get_base_airflow_version_tuple() -> tuple[int, int, int]:


AIRFLOW_V_3_0_PLUS = get_base_airflow_version_tuple() >= (3, 0, 0)
AIRFLOW_V_3_1_PLUS: bool = get_base_airflow_version_tuple() >= (3, 1, 0)


if AIRFLOW_V_3_1_PLUS:
from airflow.sdk import BaseHook
else:
from airflow.hooks.base import BaseHook # type: ignore[attr-defined,no-redef]

if AIRFLOW_V_3_0_PLUS:
from airflow.sdk import BaseOperator
Expand All @@ -41,5 +48,7 @@ def get_base_airflow_version_tuple() -> tuple[int, int, int]:

__all__ = [
"AIRFLOW_V_3_0_PLUS",
"AIRFLOW_V_3_1_PLUS",
"BaseHook",
"BaseOperator",
]