Amazon Customer Sales Pipeline #5
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Amazon Customer Sales Pipeline | |
| on: | |
| workflow_dispatch: | |
| env: | |
| S3_BUCKET: "s3://smalldataset1/" | |
| GLUE_DATABASE: "smalldatabase" | |
| EMR_CLUSTER_NAME: "amazon-sales-cluster" | |
| REGION: "us-east-1" | |
| CRAWLER_NAME: "amazon_data_crawler" | |
| jobs: | |
| run-pipeline: | |
| runs-on: ubuntu-latest | |
| steps: | |
| # Step 1: Set up AWS CLI | |
| - name: Configure AWS CLI | |
| run: | | |
| aws configure set aws_access_key_id ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws configure set aws_secret_access_key ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws configure set region ${{ env.REGION }} | |
| aws configure set aws_session_token ${{ secrets.AWS_SESSION_TOKEN }} | |
| # Step 2: Run EMR Job | |
| - name: Submit EMR Job | |
| run: | | |
| aws emr create-cluster \ | |
| --name ${{ env.EMR_CLUSTER_NAME }} \ | |
| --release-label emr-6.7.0 \ | |
| --applications Name=Spark \ | |
| --ec2-attributes KeyName=EC2_Ankit,InstanceProfile=EMR_EC2_DefaultRole \ | |
| --service-role EMR_DefaultRole \ | |
| --instance-groups '[{"InstanceGroupType":"MASTER","InstanceType":"m5.xlarge","InstanceCount":1}, | |
| {"InstanceGroupType":"CORE","InstanceType":"m5.xlarge","InstanceCount":1}]' \ | |
| --steps '[{ | |
| "Name": "Spark job", | |
| "ActionOnFailure": "CONTINUE", | |
| "Jar": "command-runner.jar", | |
| "Args": ["spark-submit", "--deploy-mode", "cluster", "s3://emr-sparkjob-script/scripts/transform_ok.py"] | |
| }]' \ | |
| --log-uri s3://amazonathenaquery/logs/ \ | |
| --auto-terminate | |
| # Step 3: Create Glue Crawler (if not exists) | |
| - name: Create Glue Crawler | |
| run: | | |
| aws glue create-crawler \ | |
| --name ${{ env.CRAWLER_NAME }} \ | |
| --role LabRole \ | |
| --database-name ${{ env.GLUE_DATABASE }} \ | |
| --targets S3Targets=[{Path="${{ env.S3_BUCKET }}"}] \ | |
| || echo "Crawler already exists, skipping creation." | |
| # Step 4: Trigger Glue Crawler | |
| - name: Run Glue Crawler | |
| run: | | |
| aws glue start-crawler --name ${{ env.CRAWLER_NAME }} |