abdulbasitds commented on a change in pull request #6007: URL: https://github.com/apache/airflow/pull/6007#discussion_r421971459
########## File path: airflow/providers/amazon/aws/operators/glue.py ########## @@ -0,0 +1,117 @@ +# -*- coding: utf-8 -*- +# +# 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 unicode_literals + +from airflow.providers.amazon.aws.hooks.glue import AwsGlueJobHook +from airflow.providers.amazon.aws.hooks.s3 import S3Hook +from airflow.models import BaseOperator +from airflow.utils.decorators import apply_defaults +import os.path + + +class AWSGlueJobOperator(BaseOperator): + """ + Creates an AWS Glue Job. AWS Glue is a serverless Spark + ETL service for running Spark Jobs on the AWS cloud. + Language support: Python and Scala + + :param job_name: unique job name per AWS Account + :type job_name: Optional[str] + :param script_location: location of ETL script. Must be a local or S3 path + :type script_location: Optional[str] + :param job_desc: job description details + :type job_desc: Optional[str] + :param concurrent_run_limit: The maximum number of concurrent runs allowed for a job + :type concurrent_run_limit: Optional[int] + :param script_args: etl script arguments and AWS Glue arguments + :type script_args: dict + :param connections: AWS Glue connections to be used by the job. + :type connections: list + :param retry_limit: The maximum number of times to retry this job if it fails + :type retry_limit:Optional[int] + :param num_of_dpus: Number of AWS Glue DPUs to allocate to this Job. + :type num_of_dpus: int + :param region_name: aws region name (example: us-east-1) + :type region_name: str + :param s3_bucket: S3 bucket where logs and local etl script will be uploaded + :type s3_bucket: Optional[str] + :param iam_role_name: AWS IAM Role for Glue Job Execution + :type iam_role_name: Optional[str] + """ + template_fields = () + template_ext = () + ui_color = '#ededed' + + @apply_defaults + def __init__(self, + job_name='aws_glue_default_job', + job_desc='AWS Glue Job with Airflow', + script_location=None, + concurrent_run_limit=None, + script_args=None, + connections=None, + retry_limit=None, + num_of_dpus=6, + aws_conn_id='aws_default', + region_name=None, + s3_bucket=None, + iam_role_name=None, + *args, **kwargs + ): + super(AWSGlueJobOperator, self).__init__(*args, **kwargs) + self.job_name = job_name + self.job_desc = job_desc + self.script_location = script_location + self.concurrent_run_limit = concurrent_run_limit + self.script_args = script_args or {} + self.connections = connections or [] + self.retry_limit = retry_limit + self.num_of_dpus = num_of_dpus + self.aws_conn_id = aws_conn_id, + self.region_name = region_name + self.s3_bucket = s3_bucket + self.iam_role_name = iam_role_name + self.S3_PROTOCOL = "s3://" + self.S3_ARTIFACTS_PREFIX = 'artifacts/glue-scripts/' + + def execute(self, context): + """ + Executes AWS Glue Job from Airflow + + :return: the id of the current glue job. + """ + if not self.script_location.startsWith(self.S3_PROTOCOL): Review comment: @zachliu I have made this change. @feluelle scrpt_location is already Optional[str] ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
