ellisms commented on code in PR #64274: URL: https://github.com/apache/airflow/pull/64274#discussion_r3462936046
########## providers/amazon/src/airflow/providers/amazon/aws/operators/neptune_analytics.py: ########## @@ -0,0 +1,1025 @@ +# +# 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 __future__ import annotations + +from collections.abc import Sequence +from typing import TYPE_CHECKING, Any + +from botocore.exceptions import ClientError + +from airflow.providers.amazon.aws.hooks.neptune_analytics import NeptuneAnalyticsHook +from airflow.providers.amazon.aws.links.ec2 import VpcEndpointLink +from airflow.providers.amazon.aws.links.neptune_analytics import NeptuneGraphLink, NeptuneImportTaskLink +from airflow.providers.amazon.aws.operators.base_aws import AwsBaseOperator +from airflow.providers.amazon.aws.triggers.neptune_analytics import ( + NeptuneGraphAvailableTrigger, + NeptuneGraphDeletedTrigger, + NeptuneGraphPrivateEndpointAvailableTrigger, + NeptuneGraphPrivateEndpointDeletedTrigger, + NeptuneImportTaskCancelledTrigger, + NeptuneImportTaskCompleteTrigger, +) +from airflow.providers.amazon.aws.utils import validate_execute_complete_event +from airflow.providers.amazon.aws.utils.mixins import aws_template_fields +from airflow.providers.common.compat.sdk import conf + +if TYPE_CHECKING: + from airflow.sdk import Context + +from airflow.providers.amazon.aws.exceptions import ( + NeptuneGraphCreationFailedError, + NeptuneGraphDeletionFailedError, + NeptuneImportTaskCancellationFailedError, + NeptuneImportTaskFailedError, + NeptunePrivateEndpointCreationFailedError, + NeptunePrivateEndpointDeletionFailedError, +) + + +class NeptuneCreateGraphOperator(AwsBaseOperator[NeptuneAnalyticsHook]): + """ + Creates an empty Amazon Neptune Graph database. + + Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds. + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:NeptuneCreateGraphOperator` + + :param graph_name: Name of Neptune graph to create + :param vector_search_config: Specifies the number of dimensions for vector embeddings that will be loaded into the graph. + :param provisioned_memory: The provisioned memory-optimized Neptune Capacity Units (m-NCUs) to use for the graph. + :param public_connectivity: Specifies whether or not the graph can be reachable over the internet. + :param replica_count: The number of replicas in other AZs. + :param deletion_protection: Indicates whether or not to enable deletion protection on the graph. + The graph can't be deleted when deletion protection is enabled. + :param kms_key_id: Specifies a KMS key to use to encrypt data in the new graph. + :param tags: Specifies metadata tags to add to the graph. + :param wait_for_completion: Whether to wait for the graph to start. (default: True) + :param deferrable: If True, the operator will wait asynchronously for the graph to start. + This implies waiting for completion. This mode requires aiobotocore module to be installed. + (default: False) + :param waiter_delay: Time in seconds to wait between status checks. + :param waiter_max_attempts: Maximum number of attempts to check for job completion. + :param aws_conn_id: The Airflow connection used for AWS credentials. + If this is ``None`` or empty then the default boto3 behaviour is used. If + running Airflow in a distributed manner and aws_conn_id is None or + empty, then default boto3 configuration would be used (and must be + maintained on each worker node). + :param region_name: AWS region_name. If not specified then the default boto3 behaviour is used. + :param botocore_config: Configuration dictionary (key-values) for botocore client. See: + https://botocore.amazonaws.com/v1/documentation/api/latest/reference/config.html + :return: dictionary with Neptune graph id + """ + + aws_hook_class = NeptuneAnalyticsHook + template_fields: Sequence[str] = aws_template_fields( + "graph_name", "vector_search_config", "provisioned_memory" + ) + + template_fields_renderers = { + "vector_search_config": "json", + } + + operator_extra_links = (NeptuneGraphLink(),) + + def __init__( + self, + graph_name: str, + vector_search_config: dict, + provisioned_memory: int, + public_connectivity: bool | None = None, + replica_count: int | None = None, + deletion_protection: bool = False, + kms_key_id: str | None = None, + tags: dict | None = None, + wait_for_completion: bool = True, + waiter_delay: int = 30, + waiter_max_attempts: int = 60, + deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False), + **kwargs, + ): + super().__init__(**kwargs) + self.graph_name = graph_name + self.vector_search_config = vector_search_config + self.replica_count = replica_count + self.provisioned_memory = provisioned_memory + self.public_connectivity = public_connectivity + self.deletion_protect = deletion_protection + self.kms_key_id = kms_key_id + self.tags = tags + self.wait_for_completion = wait_for_completion + self.deferrable = deferrable + self.waiter_delay = waiter_delay + self.waiter_max_attempts = waiter_max_attempts + + def execute(self, context: Context) -> dict: + self.log.info("Creating graph %s", self.graph_name) + + create_params = { + "graphName": self.graph_name, + "vectorSearchConfiguration": self.vector_search_config, + "provisionedMemory": self.provisioned_memory, + **{ + k: v + for k, v in { + "replicaCount": self.replica_count, + "publicConnectivity": self.public_connectivity, + "deletionProtection": self.deletion_protect, + "kmsKeyIdentifier": self.kms_key_id, + "tags": self.tags, + }.items() + if v is not None + }, + } + + response = self.hook.conn.create_graph(**create_params) + + self.log.info("Graph %s in status %s", self.graph_name, response.get("status", "Unknown")) + self.graph_id = response.get("id", None) + + graph_url = NeptuneGraphLink.format_str.format( + graph_id=self.graph_id, + aws_domain=NeptuneGraphLink.get_aws_domain(self.hook.conn_partition), + region_name=self.hook.conn_region_name, + ) + + NeptuneGraphLink.persist( + context=context, + operator=self, + region_name=self.hook.conn_region_name, + aws_partition=self.hook.conn_partition, + graph_id=self.graph_id, + ) + self.log.info("You can view this Neptune Graph at : %s", graph_url) + + if self.deferrable: + self.log.info("Deferring until graph %s is available", self.graph_id) + self.defer( + trigger=NeptuneGraphAvailableTrigger( + aws_conn_id=self.aws_conn_id, + graph_id=self.graph_id, + waiter_delay=self.waiter_delay, + waiter_max_attempts=self.waiter_max_attempts, + ), + method_name="execute_complete", + ) + + if self.wait_for_completion: + self.log.info("Waiting until graph %s is available", self.graph_id) + self.hook.get_waiter("graph_available").wait( + graphIdentifier=self.graph_id, + WaiterConfig={"Delay": self.waiter_delay, "MaxAttempts": self.waiter_max_attempts}, + ) + + return {"graph_id": self.graph_id} + + def execute_complete(self, context: Context, event: dict[str, Any] | None = None) -> dict[str, Any]: + + validated_event = validate_execute_complete_event(event) + + if validated_event.get("status") != "success": + raise NeptuneGraphCreationFailedError( + validated_event.get( + "message", + f"Neptune graph {validated_event.get('return_key')} creation did not complete successfully", + ) + ) + + self.log.info("Neptune graph %s complete", self.graph_id) + + return {"graph_id": self.graph_id} + + +class NeptuneCreatePrivateGraphEndpointOperator(AwsBaseOperator[NeptuneAnalyticsHook]): + """ + Creates a Neptune Graph private endpoint. + + .. seealso:: + For more information on how to use this operator, take a look at the guide: + :ref:`howto/operator:NeptuneCreatePrivateGraphEndpointOperator` + + :param graph_identifier: Neptune Graph id + :param vpc_id: VPC to create endpoint in + :param subnet_ids: Subnets in which private graph endpoint ENIs are created + :param vpc_security_group_ids: Security groups to be attached to the private graph endpoint + :param wait_for_completion: Whether to wait for the endpoint to be available. (default: True) + :param deferrable: If True, the operator will wait asynchronously for the endpoint to become available. + This implies waiting for completion. This mode requires aiobotocore module to be installed. + (default: False) + :param waiter_delay: Time in seconds to wait between status checks. + :param waiter_max_attempts: Maximum number of attempts to check for job completion. + :param aws_conn_id: The Airflow connection used for AWS credentials. + If this is ``None`` or empty then the default boto3 behaviour is used. If + running Airflow in a distributed manner and aws_conn_id is None or + empty, then default boto3 configuration would be used (and must be + maintained on each worker node). + :param region_name: AWS region_name. If not specified then the default boto3 behaviour is used. + :param botocore_config: Configuration dictionary (key-values) for botocore client. See: + https://botocore.amazonaws.com/v1/documentation/api/latest/reference/config.html + :return: dictionary with Neptune graph id + """ + + aws_hook_class = NeptuneAnalyticsHook + template_fields: Sequence[str] = aws_template_fields( + "graph_identifier", "vpc_id", "subnet_ids", "vpc_security_group_ids" + ) + + def __init__( + self, + graph_identifier: str, + vpc_id: str | None = None, + subnet_ids: list[str] | None = None, + vpc_security_group_ids: list[str] | None = None, + wait_for_completion: bool = True, + waiter_delay: int = 30, + waiter_max_attempts: int = 60, + deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False), + **kwargs, + ): + super().__init__(**kwargs) + self.graph_identifier = graph_identifier + self.vpc_id = vpc_id + self.subnet_ids = subnet_ids + self.vpc_security_group_ids = vpc_security_group_ids + self.wait_for_completion = wait_for_completion + self.deferrable = deferrable + self.waiter_delay = waiter_delay + self.waiter_max_attempts = waiter_max_attempts + + def execute(self, context: Context) -> dict: + self.log.info("Creating private endpoint for graph %s", self.graph_identifier) + + create_params = { + "graphIdentifier": self.graph_identifier, + **{ + k: v + for k, v in { + "vpcId": self.vpc_id, + "subnetIds": self.subnet_ids, + "vpcSecurityGroupIds": self.vpc_security_group_ids, + }.items() + if v is not None + }, + } + + # create the endpoint + + result = self.hook.conn.create_private_graph_endpoint(**create_params) + status = result.get("status", "Unknown") + + self.log.info("Status of endpoint: %s", status) + + if status in ["FAILED"]: + raise NeptunePrivateEndpointCreationFailedError( + f"Private endpoint failed to create for graph {self.graph_identifier}" + ) + + # if VPC not provided, use the one that is returned, which is the default VPC. Required for the waiter + self.vpc_id = result.get("vpcId", self.vpc_id) + + # get the vpce id since it may not be returned immediately + endpoint_id = self.hook._get_graph_endpoint_id(graph_id=self.graph_identifier, vpc_id=self.vpc_id) + + endpoint_url = VpcEndpointLink.format_str.format( + endpoint_id=endpoint_id, + aws_domain=VpcEndpointLink.get_aws_domain(self.hook.conn_partition), + region_name=self.hook.conn_region_name, + ) + + VpcEndpointLink.persist( + context=context, + operator=self, + region_name=self.hook.conn_region_name, + aws_partition=self.hook.conn_partition, + endpoint_id=endpoint_id, + ) + self.log.info("You can view this private endpoint at : %s", endpoint_url) + + if self.deferrable: + self.log.info("Deferring until endpoint is available") + self.defer( + trigger=NeptuneGraphPrivateEndpointAvailableTrigger( + aws_conn_id=self.aws_conn_id, + graph_id=self.graph_identifier, + vpc_id=self.vpc_id, + waiter_delay=self.waiter_delay, + waiter_max_attempts=self.waiter_max_attempts, + ), + method_name="execute_complete", + kwargs={"vpc_id": self.vpc_id}, + ) + + if self.wait_for_completion: + self.log.info("Waiting until endpoint is available") + self.hook.get_waiter("private_graph_endpoint_available").wait( + graphIdentifier=self.graph_identifier, + vpcId=self.vpc_id, + WaiterConfig={"Delay": self.waiter_delay, "MaxAttempts": self.waiter_max_attempts}, + ) + + return {"vpc_endpoint_id": endpoint_id, "graph_id": self.graph_identifier, "vpc_id": self.vpc_id} + + def execute_complete(self, context: Context, event: dict[str, Any] | None = None) -> dict[str, Any]: + validated_event = validate_execute_complete_event(event) + + if validated_event.get("status") != "success": + raise NeptunePrivateEndpointCreationFailedError( + validated_event.get("message", "Endpoint failed to create") + ) + + graph_id = validated_event["value"] + vpc_id = validated_event["vpc_id"] Review Comment: Fixed. `value` was an error and `vpc_id` should be an argument, since its sent as a `kwarg` from the caller. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
