[GitHub] [airflow] dacort commented on a change in pull request #16766: Add an Amazon EMR on EKS provider package

[GitBox <gi...@apache.org>]

dacort commented on a change in pull request #16766:
URL: https://github.com/apache/airflow/pull/16766#discussion_r665557984



##########
File path: airflow/providers/amazon/aws/hooks/emr_containers.py
##########
@@ -0,0 +1,189 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+from time import sleep
+from typing import Any, Dict, Optional
+
+from airflow.exceptions import AirflowException
+from airflow.providers.amazon.aws.hooks.base_aws import AwsBaseHook
+
+
+class EMRContainerHook(AwsBaseHook):
+    """
+    Interact with AWS EMR Virtual Cluster to run, poll jobs and return job status
+    Additional arguments (such as ``aws_conn_id``) may be specified and
+    are passed down to the underlying AwsBaseHook.
+
+    .. seealso::
+        :class:`~airflow.providers.amazon.aws.hooks.base_aws.AwsBaseHook`
+
+    :param virtual_cluster_id: Cluster ID of the EMR on EKS virtual cluster
+    :type virtual_cluster_id: str
+    """
+
+    INTERMEDIATE_STATES = (
+        "PENDING",
+        "SUBMITTED",
+        "RUNNING",
+    )
+    FAILURE_STATES = (
+        "FAILED",
+        "CANCELLED",
+        "CANCEL_PENDING",
+    )
+    SUCCESS_STATES = ("COMPLETED",)
+
+    def __init__(self, *args: Any, virtual_cluster_id: Optional[str] = None, **kwargs: Any) -> None:
+        super().__init__(client_type="emr-containers", *args, **kwargs)  # type: ignore
+        self.virtual_cluster_id = self._get_virtual_cluster_id(virtual_cluster_id, self.aws_conn_id)
+
+    def _get_virtual_cluster_id(self, virtual_cluster_id: str, aws_conn_id: str):
+        if virtual_cluster_id is not None:
+            return virtual_cluster_id
+
+        if aws_conn_id is not None:
+            conn = self.get_connection(aws_conn_id)
+            cluster_id = conn.extra_dejson.get('virtual_cluster_id')
+            if cluster_id:
+                return cluster_id
+            else:
+                raise AirflowException("Missing virtual_cluster_id in AWS connection")
+
+        raise AirflowException(
+            f"Cannot get EMR virtual cluster ID: Please pass `virtual_cluster_id` or set it in connection JSON: {aws_conn_id}"  # noqa: E501
+        )
+
+    def submit_job(
+        self,
+        name: str,
+        execution_role_arn: str,
+        release_label: str,
+        job_driver: dict,
+        configuration_overrides: Optional[dict] = None,
+        client_request_token: Optional[str] = None,
+    ) -> str:
+        """
+        Submit a job to the EMR Containers API and and return the job ID.
+        A job run is a unit of work, such as a Spark jar, PySpark script,
+        or SparkSQL query, that you submit to Amazon EMR on EKS.
+        See: https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/emr-containers.html#EMRContainers.Client.start_job_run  # noqa: E501
+
+        :param name: The name of the job run.
+        :type name: str
+        :param execution_role_arn: The IAM role ARN associated with the job run.
+        :type execution_role_arn: str
+        :param release_label: The Amazon EMR release version to use for the job run.
+        :type release_label: str
+        :param job_driver: Job configuration details, e.g. the Spark job parameters.
+        :type job_driver: dict
+        :param configuration_overrides: The configuration overrides for the job run,
+            specifically either application configuration or monitoring configuration.
+        :type configuration_overrides: dict
+        :param client_request_token: The client idempotency token of the job run request.
+            Use this if you want to specify a unique ID to prevent two jobs from getting started.
+        :type client_request_token: str
+        :return: Job ID
+        """
+        params = {
+            "name": name,
+            "virtualClusterId": self.virtual_cluster_id,
+            "executionRoleArn": execution_role_arn,
+            "releaseLabel": release_label,
+            "jobDriver": job_driver,
+            "configurationOverrides": configuration_overrides or {},
+        }
+        if client_request_token:
+            params["clientToken"] = client_request_token
+
+        response = self.get_conn().start_job_run(**params)

Review comment:
       It should - I'll go ahead and move to `self.conn`.




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscribe@airflow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org