Apache provider docstring improvements (#31730)

airflow/providers/apache/druid/transfers/hive_to_druid.py

@@ -32,10 +32,10 @@
 
 
 class HiveToDruidOperator(BaseOperator):
-    """
-    Moves data from Hive to Druid, [del]note that for now the data is loaded
-    into memory before being pushed to Druid, so this operator should
-    be used for smallish amount of data.[/del].
+    """Moves data from Hive to Druid.
+
+    [del]note that for now the data is loaded into memory before being pushed to
+    Druid, so this operator should be used for smallish amount of data.[/del]
 
     :param sql: SQL query to execute against the Druid database. (templated)
     :param druid_datasource: the datasource you want to ingest into in druid

airflow/providers/apache/hive/operators/hive_stats.py

@@ -33,10 +33,11 @@
 
 
 class HiveStatsCollectionOperator(BaseOperator):
-    """Gathers partition statistics using a dynamically generated Presto query.
+    """Gather partition statistics and insert them into MySQL.
 
-    The collected stats are inserted into a MySQL table with this format. Stats
-    overwrite themselves if you rerun the same date/partition.
+    Statistics are gathered with a dynamically generated Presto query and
+    inserted with this format. Stats overwrite themselves if you rerun the
+    same date/partition.
 
     .. code-block:: sql
 

airflow/providers/apache/hive/transfers/vertica_to_hive.py

@@ -93,11 +93,12 @@ def __init__(
 
     @classmethod
     def type_map(cls, vertica_type):
-        """
-        Vertica-python datatype.py does not provide the full type mapping access.
-        Manual hack.
+        """Manually hack Vertica-Python type mapping.
+
+        The stock datatype.py does not provide the full type mapping access.
 
-        Reference: https://github.com/uber/vertica-python/blob/master/vertica_python/vertica/column.py
+        Reference:
+        https://github.com/uber/vertica-python/blob/master/vertica_python/vertica/column.py
         """
         type_map = {
             5: "BOOLEAN",

airflow/providers/apache/kylin/operators/kylin_cube.py

@@ -32,9 +32,7 @@
 
 
 class KylinCubeOperator(BaseOperator):
-    """
-    This operator is used to submit request about kylin build/refresh/merge,
-    and can track job status . so users can easier to build kylin job.
+    """Submit request about Kylin build/refresh/merge and track job status.
 
     For more detail information in
     `Apache Kylin <http://kylin.apache.org/>`_

airflow/providers/apache/livy/triggers/livy.py

@@ -79,10 +79,10 @@ def serialize(self) -> tuple[str, dict[str, Any]]:
         )
 
     async def run(self) -> AsyncIterator[TriggerEvent]:
-        """
-        Checks if the _polling_interval > 0, in that case it pools Livy for
-        batch termination asynchronously.
-        else returns the success response.
+        """Run the trigger.
+
+        If ``_polling_interval > 0``, this pools Livy for batch termination
+        asynchronously. Otherwise the success response is created immediately.
         """
         try:
             if self._polling_interval > 0:

airflow/providers/apache/spark/hooks/spark_submit.py

@@ -166,10 +166,12 @@ def __init__(
         self._env: dict[str, Any] | None = None
 
     def _resolve_should_track_driver_status(self) -> bool:
-        """Whether this hook should poll the Spark driver status.
+        """Check if we should track the driver status.
 
-        If this returns True, the hook would send subsequent spark-submit status
-        requests after the initial spark-submit request.
+        If so, we should send subsequent spark-submit status requests after the
+        initial spark-submit request.
+
+        :return: if the driver status should be tracked
         """
         return "spark://" in self._connection["master"] and self._connection["deploy_mode"] == "cluster"
 

airflow/providers/apache/sqoop/hooks/sqoop.py

@@ -27,9 +27,9 @@
 
 
 class SqoopHook(BaseHook):
-    """
-    This hook is a wrapper around the sqoop 1 binary. To be able to use the hook
-    it is required that "sqoop" is in the PATH.
+    """Wrapper around the sqoop 1 binary.
+
+    To be able to use the hook, it is required that "sqoop" is in the PATH.
 
     Additional arguments that can be passed via the 'extra' JSON field of the
     sqoop connection:
@@ -95,8 +95,7 @@ def cmd_mask_password(self, cmd_orig: list[str]) -> list[str]:
         return cmd
 
     def popen(self, cmd: list[str], **kwargs: Any) -> None:
-        """
-        Remote Popen.
+        """Remote Popen.
 
         :param cmd: command to remotely execute
         :param kwargs: extra arguments to Popen (see subprocess.Popen)
@@ -223,9 +222,9 @@ def import_table(
         extra_import_options: dict[str, Any] | None = None,
         schema: str | None = None,
     ) -> Any:
-        """
-        Imports table from remote location to target dir. Arguments are
-        copies of direct sqoop command line arguments.
+        """Import table from remote location to target dir.
+
+        Arguments are copies of direct sqoop command line arguments.
 
         :param table: Table to read
         :param schema: Schema name
@@ -266,8 +265,7 @@ def import_query(
         driver: Any | None = None,
         extra_import_options: dict[str, Any] | None = None,
     ) -> Any:
-        """
-        Imports a specific query from the rdbms to hdfs.
+        """Import a specific query from the rdbms to hdfs.
 
         :param query: Free format query to run
         :param target_dir: HDFS destination dir
@@ -375,9 +373,9 @@ def export_table(
         extra_export_options: dict[str, Any] | None = None,
         schema: str | None = None,
     ) -> None:
-        """
-        Exports Hive table to remote location. Arguments are copies of direct
-        sqoop command line Arguments.
+        """Export Hive table to remote location.
+
+        Arguments are copies of direct Sqoop command line Arguments
 
         :param table: Table remote destination
         :param schema: Schema name