Stop using start_date in default_args in example_dags (#9982)

Author: kaxil

.pre-commit-config.yaml

@@ -323,6 +323,12 @@ repos:
         entry: "(airflow\\.){0,1}utils\\.dates\\.days_ago"
         files: \.py$
         pass_filenames: true
+      - id: restrict-start_date-in-default_args-in-example_dags
+        language: pygrep
+        name: "'start_date' should not be defined in default_args in example_dags"
+        entry: "default_args\\s*=\\s*{\\s*(\"|')start_date(\"|')"
+        files: \.*example_dags.*.py$
+        pass_filenames: true
       - id: check-integrations
         name: Check if integration list is aligned
         entry: ./scripts/ci/pre_commit/pre_commit_check_integrations.sh

airflow/example_dags/example_complex.py

@@ -26,12 +26,10 @@
 from airflow.operators.python import PythonOperator
 from airflow.utils.dates import days_ago
 
-default_args = {"start_date": days_ago(1)}
-
 with models.DAG(
     dag_id="example_complex",
-    default_args=default_args,
     schedule_interval=None,
+    start_date=days_ago(1),
     tags=['example'],
 ) as dag:
 

airflow/example_dags/example_trigger_target_dag.py

@@ -29,7 +29,8 @@
 
 dag = DAG(
     dag_id="example_trigger_target_dag",
-    default_args={"start_date": days_ago(2), "owner": "airflow"},
+    default_args={"owner": "airflow"},
+    start_date=days_ago(2),
     schedule_interval=None,
     tags=['example']
 )

airflow/providers/amazon/aws/example_dags/example_datasync_1.py

@@ -45,12 +45,11 @@
     "DESTINATION_LOCATION_URI", "s3://mybucket/prefix")
 # [END howto_operator_datasync_1_args_2]
 
-default_args = {"start_date": days_ago(1)}
 
 with models.DAG(
     "example_datasync_1_1",
-    default_args=default_args,
     schedule_interval=None,  # Override to match your needs
+    start_date=days_ago(1),
     tags=['example'],
 ) as dag:
 
@@ -64,7 +63,7 @@
 
 with models.DAG(
     "example_datasync_1_2",
-    default_args=default_args,
+    start_date=days_ago(1),
     schedule_interval=None,  # Override to match your needs
 ) as dag:
     # [START howto_operator_datasync_1_2]

airflow/providers/amazon/aws/example_dags/example_datasync_2.py

@@ -77,13 +77,12 @@
     getenv("UPDATE_TASK_KWARGS", default_update_task_kwargs)
 )
 
-default_args = {"start_date": days_ago(1)}
 # [END howto_operator_datasync_2_args]
 
 with models.DAG(
     "example_datasync_2",
-    default_args=default_args,
     schedule_interval=None,  # Override to match your needs
+    start_date=days_ago(1),
     tags=['example'],
 ) as dag:
 

airflow/providers/amazon/aws/example_dags/example_google_api_to_s3_transfer_advanced.py

@@ -51,8 +51,6 @@
 YOUTUBE_VIDEO_FIELDS = getenv("YOUTUBE_VIDEO_FIELDS", "items(id,snippet(description,publishedAt,tags,title))")
 # [END howto_operator_google_api_to_s3_transfer_advanced_env_variables]
 
-default_args = {"start_date": days_ago(1)}
-
 
 # pylint: disable=unused-argument
 # [START howto_operator_google_api_to_s3_transfer_advanced_task_1_2]
@@ -74,8 +72,8 @@ def _check_and_transform_video_ids(xcom_key, task_ids, task_instance, **kwargs):
 
 with DAG(
     dag_id="example_google_api_to_s3_transfer_advanced",
-    default_args=default_args,
     schedule_interval=None,
+    start_date=days_ago(1),
     tags=['example']
 ) as dag:
     # [START howto_operator_google_api_to_s3_transfer_advanced_task_1]

airflow/providers/amazon/aws/example_dags/example_google_api_to_s3_transfer_basic.py

@@ -32,12 +32,11 @@
 S3_DESTINATION_KEY = getenv("S3_DESTINATION_KEY", "s3://bucket/key.json")
 # [END howto_operator_google_api_to_s3_transfer_basic_env_variables]
 
-default_args = {"start_date": days_ago(1)}
 
 with DAG(
     dag_id="example_google_api_to_s3_transfer_basic",
-    default_args=default_args,
     schedule_interval=None,
+    start_date=days_ago(1),
     tags=['example']
 ) as dag:
     # [START howto_operator_google_api_to_s3_transfer_basic_task_1]

airflow/providers/amazon/aws/example_dags/example_imap_attachment_to_s3.py

@@ -33,11 +33,9 @@
 S3_DESTINATION_KEY = getenv("S3_DESTINATION_KEY", "s3://bucket/key.json")
 # [END howto_operator_imap_attachment_to_s3_env_variables]
 
-default_args = {"start_date": days_ago(1)}
-
 with DAG(
     dag_id="example_imap_attachment_to_s3",
-    default_args=default_args,
+    start_date=days_ago(1),
     schedule_interval=None,
     tags=['example']
 ) as dag:

airflow/providers/amazon/aws/example_dags/example_s3_to_redshift.py

@@ -34,8 +34,6 @@
 REDSHIFT_TABLE = getenv("REDSHIFT_TABLE", "test_table")
 # [END howto_operator_s3_to_redshift_env_variables]
 
-default_args = {"start_date": days_ago(1)}
-
 
 def _add_sample_data_to_s3():
     s3_hook = S3Hook()
@@ -50,7 +48,7 @@ def _remove_sample_data_from_s3():
 
 with DAG(
     dag_id="example_s3_to_redshift",
-    default_args=default_args,
+    start_date=days_ago(1),
     schedule_interval=None,
     tags=['example']
 ) as dag:

airflow/providers/google/ads/example_dags/example_ads.py

@@ -64,12 +64,10 @@
 
 # [END howto_google_ads_env_variables]
 
-default_args = {"start_date": dates.days_ago(1)}
-
 with models.DAG(
     "example_google_ads",
-    default_args=default_args,
     schedule_interval=None,  # Override to match your needs
+    start_date=dates.days_ago(1),
 ) as dag:
     # [START howto_google_ads_to_gcs_operator]
     run_operator = GoogleAdsToGcsOperator(