Source code for

# 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
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
from __future__ import annotations

from functools import cached_property
from typing import TYPE_CHECKING, Any, Sequence

from airflow.configuration import conf
from airflow.exceptions import AirflowException
from import GlueCrawlerCompleteTrigger
from import validate_execute_complete_event

    from airflow.utils.context import Context

from airflow.models import BaseOperator
from import GlueCrawlerHook

[docs]class GlueCrawlerOperator(BaseOperator): """ Creates, updates and triggers an AWS Glue Crawler. AWS Glue Crawler is a serverless service that manages a catalog of metadata tables that contain the inferred schema, format and data types of data stores within the AWS cloud. .. seealso:: For more information on how to use this operator, take a look at the guide: :ref:`howto/operator:GlueCrawlerOperator` :param config: Configurations for the AWS Glue crawler :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 poll_interval: Time (in seconds) to wait between two consecutive calls to check crawler status :param wait_for_completion: Whether to wait for crawl execution completion. (default: True) :param deferrable: If True, the operator will wait asynchronously for the crawl to complete. This implies waiting for completion. This mode requires aiobotocore module to be installed. (default: False) """
[docs] template_fields: Sequence[str] = ("config",)
[docs] ui_color = "#ededed"
def __init__( self, config, aws_conn_id="aws_default", region_name: str | None = None, poll_interval: int = 5, wait_for_completion: bool = True, deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False), **kwargs, ): super().__init__(**kwargs) self.aws_conn_id = aws_conn_id self.poll_interval = poll_interval self.wait_for_completion = wait_for_completion self.deferrable = deferrable self.region_name = region_name self.config = config @cached_property
[docs] def hook(self) -> GlueCrawlerHook: """Create and return a GlueCrawlerHook.""" return GlueCrawlerHook(self.aws_conn_id, region_name=self.region_name)
[docs] def execute(self, context: Context): """ Execute AWS Glue Crawler from Airflow. :return: the name of the current glue crawler. """ crawler_name = self.config["Name"] if self.hook.has_crawler(crawler_name): self.hook.update_crawler(**self.config) else: self.hook.create_crawler(**self.config)"Triggering AWS Glue Crawler") self.hook.start_crawler(crawler_name) if self.deferrable: self.defer( trigger=GlueCrawlerCompleteTrigger( crawler_name=crawler_name, waiter_delay=self.poll_interval, aws_conn_id=self.aws_conn_id, ), method_name="execute_complete", ) elif self.wait_for_completion:"Waiting for AWS Glue Crawler") self.hook.wait_for_crawler_completion(crawler_name=crawler_name, poll_interval=self.poll_interval) return crawler_name
[docs] def execute_complete(self, context: Context, event: dict[str, Any] | None = None) -> str: event = validate_execute_complete_event(event) if event["status"] != "success": raise AirflowException(f"Error in glue crawl: {event}") return self.config["Name"]

Was this entry helpful?