Add D400 pydocstyle check (#31742)

* Add D400 pydocstyle check

* Fix static checks

airflow/metrics/otel_logger.py

@@ -84,7 +84,7 @@ def name_is_otel_safe(prefix: str, name: str) -> bool:
 
 
 class SafeOtelLogger:
-    """Otel Logger"""
+    """Otel Logger."""
 
     def __init__(self, otel_provider, prefix: str = "airflow", allow_list_validator=AllowListValidator()):
         self.otel: Callable = otel_provider

airflow/metrics/validators.py

@@ -109,6 +109,7 @@ def stat_name_otel_handler(
 ) -> str:
     """
     Verifies that a proposed prefix and name combination will meet OpenTelemetry naming standards.
+
     See: https://opentelemetry.io/docs/reference/specification/metrics/api/#instrument-name-syntax
 
     :param stat_prefix: The proposed prefix applied to all metric names.

airflow/migrations/env.py

@@ -28,7 +28,7 @@
 
 
 def include_object(_, name, type_, *args):
-    """Filter objects for autogenerating revisions"""
+    """Filter objects for autogenerating revisions."""
     # Ignore _anything_ to do with Celery, or FlaskSession's tables
     if type_ == "table" and (name.startswith("celery_") or name == "session"):
         return False

airflow/migrations/utils.py

@@ -29,6 +29,7 @@ def get_mssql_table_constraints(conn, table_name) -> dict[str, dict[str, list[st
     is missing the primary key constraint name and the name is
     auto-generated by the SQL server. so this function helps to
     retrieve any primary or unique constraint name.
+
     :param conn: sql connection object
     :param table_name: table name
     :return: a dictionary of ((constraint name, constraint type), column name) of table

airflow/models/variable.py

@@ -127,7 +127,7 @@ def get(
         default_var: Any = __NO_DEFAULT_SENTINEL,
         deserialize_json: bool = False,
     ) -> Any:
-        """Gets a value for an Airflow Variable Key
+        """Gets a value for an Airflow Variable Key.
 
         :param key: Variable Key
         :param default_var: Default value of the Variable if the Variable doesn't exist

airflow/providers/amazon/aws/triggers/glue.py

@@ -25,7 +25,7 @@
 
 class GlueJobCompleteTrigger(BaseTrigger):
     """
-    Watches for a glue job, triggers when it finishes
+    Watches for a glue job, triggers when it finishes.
 
     :param job_name: glue job name
     :param run_id: the ID of the specific run to watch for that job

airflow/providers/amazon/aws/triggers/glue_crawler.py

@@ -28,7 +28,7 @@
 
 class GlueCrawlerCompleteTrigger(BaseTrigger):
     """
-    Watches for a glue crawl, triggers when it finishes
+    Watches for a glue crawl, triggers when it finishes.
 
     :param crawler_name: name of the crawler to watch
     :param poll_interval: The amount of time in seconds to wait between attempts.

airflow/providers/cncf/kubernetes/operators/resource.py

@@ -14,7 +14,7 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-"""Manage a Kubernetes Resource"""
+"""Manage a Kubernetes Resource."""
 
 from __future__ import annotations
 

airflow/providers/docker/operators/docker.py

@@ -500,7 +500,7 @@ def on_kill(self) -> None:
 
     @staticmethod
     def unpack_environment_variables(env_str: str) -> dict:
-        r"""Parse environment variables from the string
+        r"""Parse environment variables from the string.
 
         :param env_str: environment variables in the ``{key}={value}`` format,
             separated by a ``\n`` (newline)

airflow/providers/snowflake/hooks/snowflake_sql_api.py

@@ -80,7 +80,7 @@ def __init__(
         self.private_key: Any = None
 
     def get_private_key(self) -> None:
-        """Gets the private key from snowflake connection"""
+        """Gets the private key from snowflake connection."""
         conn = self.get_connection(self.snowflake_conn_id)
 
         # If private_key_file is specified in the extra json, load the contents of the file as a private key.
@@ -120,7 +120,7 @@ def execute_query(
         self, sql: str, statement_count: int, query_tag: str = "", bindings: dict[str, Any] | None = None
     ) -> list[str]:
         """
-        Using SnowflakeSQL API, run the query in snowflake by making API request
+        Using SnowflakeSQL API, run the query in snowflake by making API request.
 
         :param sql: the sql string to be executed with possibly multiple statements
         :param statement_count: set the MULTI_STATEMENT_COUNT field to the number of SQL statements
@@ -170,7 +170,7 @@ def execute_query(
 
     def get_headers(self) -> dict[str, Any]:
         """Based on the private key, and with connection details JWT Token is generated and header
-        is formed
+        is formed.
         """
         if not self.private_key:
             self.get_private_key()
@@ -196,7 +196,7 @@ def get_headers(self) -> dict[str, Any]:
 
     def get_request_url_header_params(self, query_id: str) -> tuple[dict[str, Any], dict[str, Any], str]:
         """
-        Build the request header Url with account name identifier and query id from the connection params
+        Build the request header Url with account name identifier and query id from the connection params.
 
         :param query_id: statement handles query ids for the individual statements.
         """
@@ -210,7 +210,7 @@ def get_request_url_header_params(self, query_id: str) -> tuple[dict[str, Any],
     def check_query_output(self, query_ids: list[str]) -> None:
         """
         Based on the query ids passed as the parameter make HTTP request to snowflake SQL API and logs
-         the response
+        the response.
 
         :param query_ids: statement handles query id for the individual statements.
         """

airflow/providers/snowflake/operators/snowflake.py

@@ -504,7 +504,7 @@ def execute(self, context: Context) -> None:
         self._hook.check_query_output(self.query_ids)
 
     def poll_on_queries(self):
-        """Poll on requested queries"""
+        """Poll on requested queries."""
         queries_in_progress = set(self.query_ids)
         statement_success_status = {}
         statement_error_status = {}

airflow/utils/hashlib_wrapper.py

@@ -30,10 +30,10 @@ def md5(__string: ReadableBuffer = b"") -> hashlib._Hash:
     """
     Safely allows calling the hashlib.md5 function with the "usedforsecurity" disabled
     when specified in the configuration.
+
     :param string: The data to hash.
         Default to empty str byte.
     :return: The hashed value.
-    :rtype: _Hash
     """
     if PY39:
         return hashlib.md5(__string, usedforsecurity=False)  # type: ignore

airflow/www/views.py

@@ -3795,7 +3795,7 @@ def grid_data(self):
         ]
     )
     def historical_metrics_data(self):
-        """Returns cluster activity historical metrics"""
+        """Returns cluster activity historical metrics."""
         start_date = _safe_parse_datetime(request.args.get("start_date"))
         end_date = _safe_parse_datetime(request.args.get("end_date"))
         with create_session() as session:

docs/apache-airflow/img/airflow_erd.sha256

@@ -1 +1 @@
-84df376cc094d640d7d04b46e4f4becd48fcd2e8ce0996c590b4293f22dbda44
+4bd168cc3731503483240260d78ddf0b610de6c79345b0cc4c749a92451e3b1d

pyproject.toml

@@ -38,7 +38,8 @@ extend-exclude = [
     "airflow/providers/google/ads/_vendor/*",
     # The files generated by stubgen aren't 100% valid syntax it turns out, and we don't ship them, so we can
     # ignore them in ruff
-    "airflow/providers/common/sql/*/*.pyi"
+    "airflow/providers/common/sql/*/*.pyi",
+    "airflow/migrations/versions/*.py"
 ]
 
 extend-select = [
@@ -53,7 +54,7 @@ extend-select = [
     "D106",
     "D2",
     "D3",
-    # "D400", WIP: see #31135
+    "D400",
     # "D401", # Not enabled by ruff, but we don't want it
     "D402",
     "D403",