Skip to content

Fix generate_job_id method for BQ for cases when run_type=SCHEDULED #58035

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
potiuk merged 1 commit into from
Nov 17, 2025
Merged

Fix generate_job_id method for BQ for cases when run_type=SCHEDULED #58035

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
21 changes: 9 additions & 12 deletions providers/google/src/airflow/providers/google/cloud/hooks/bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,7 @@
from airflow.utils.hashlib_wrapper import md5
from airflow.utils.helpers import convert_camel_to_snake
from airflow.utils.log.logging_mixin import LoggingMixin
from airflow.utils.types import DagRunType

if TYPE_CHECKING:
import pandas as pd
Expand Down Expand Up @@ -1285,7 +1286,7 @@ def generate_job_id(
task_id: str,
logical_date: datetime | None,
configuration: dict,
run_after: pendulum.DateTime | None = None,
run_after: pendulum.DateTime | datetime | None = None,
force_rerun: bool = False,
) -> str:
if force_rerun:
Expand Down Expand Up @@ -1314,18 +1315,14 @@ def generate_job_id(
job_id = f"airflow_{dag_id}_{task_id}_{job_id_timestamp.isoformat()}_{uniqueness_suffix}"
return re.sub(r"[:\-+.]", "_", job_id)

def get_run_after_or_logical_date(self, context: Context) -> pendulum.DateTime:
def get_run_after_or_logical_date(self, context: Context) -> pendulum.DateTime | datetime | None:
dag_run = context.get("dag_run")
if not dag_run:
return pendulum.now("UTC")

if AIRFLOW_V_3_0_PLUS:
if dag_run := context.get("dag_run"):
run_after = pendulum.instance(dag_run.run_after)
else:
run_after = pendulum.now("UTC")
else:
if logical_date := context.get("logical_date"):
run_after = logical_date
else:
run_after = pendulum.now("UTC")
return run_after
return dag_run.start_date
return dag_run.start_date if dag_run.run_type == DagRunType.SCHEDULED else context.get("logical_date")

def split_tablename(
self, table_input: str, default_project_id: str, var_name: str | None = None
Expand Down
40 changes: 36 additions & 4 deletions providers/google/tests/unit/google/cloud/hooks/test_bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
from google.cloud.exceptions import NotFound

from airflow.exceptions import AirflowException
from airflow.models import DagRun
from airflow.providers.common.compat.assets import Asset
from airflow.providers.common.compat.sdk import Context
from airflow.providers.google.cloud.hooks.bigquery import (
Expand All @@ -52,6 +53,7 @@
_validate_src_fmt_configs,
_validate_value,
)
from airflow.utils.types import DagRunType

from tests_common.test_utils.version_compat import AIRFLOW_V_3_0_PLUS

Expand Down Expand Up @@ -684,14 +686,44 @@ def test_job_id_validity(self, mock_md5, test_dag_id, expected_job_id):
assert job_id == expected_job_id

def test_get_run_after_or_logical_date(self):
"""Test get_run_after_or_logical_date for both Airflow 3.x and pre-3.0 behavior."""
if AIRFLOW_V_3_0_PLUS:
from airflow.models import DagRun
ctx = Context(
dag_run=DagRun(
run_type=DagRunType.MANUAL,
start_date=pendulum.datetime(2025, 2, 2, tz="UTC"),
),
logical_date=pendulum.datetime(2025, 1, 1, tz="UTC"),
)
assert self.hook.get_run_after_or_logical_date(ctx) == pendulum.datetime(2025, 2, 2, tz="UTC")

ctx = Context(
dag_run=DagRun(
run_type=DagRunType.SCHEDULED,
start_date=pendulum.datetime(2025, 2, 2, tz="UTC"),
),
logical_date=pendulum.datetime(2025, 1, 1, tz="UTC"),
)
assert self.hook.get_run_after_or_logical_date(ctx) == pendulum.datetime(2025, 2, 2, tz="UTC")

ctx = Context(dag_run=DagRun(run_after=pendulum.datetime(2025, 1, 1)))
else:
ctx = Context(logical_date=pendulum.datetime(2025, 1, 1))
ctx = Context(
dag_run=DagRun(
run_type=DagRunType.MANUAL,
start_date=pendulum.datetime(2025, 2, 2, tz="UTC"),
),
logical_date=pendulum.datetime(2025, 1, 1, tz="UTC"),
)
assert self.hook.get_run_after_or_logical_date(ctx) == pendulum.datetime(2025, 1, 1, tz="UTC")

assert self.hook.get_run_after_or_logical_date(ctx) == pendulum.datetime(2025, 1, 1)
ctx = Context(
dag_run=DagRun(
run_type=DagRunType.SCHEDULED,
start_date=pendulum.datetime(2025, 2, 2, tz="UTC"),
),
logical_date=pendulum.datetime(2025, 1, 1, tz="UTC"),
)
assert self.hook.get_run_after_or_logical_date(ctx) == pendulum.datetime(2025, 2, 2, tz="UTC")

@mock.patch(
"airflow.providers.google.cloud.hooks.bigquery.BigQueryHook.get_job",
Expand Down