glue-workflow.js

import * as cdk from 'aws-cdk-lib';
import * as glue from 'aws-cdk-lib/aws-glue';
import * as iam from 'aws-cdk-lib/aws-iam';
import * as s3 from 'aws-cdk-lib/aws-s3';
import { Construct } from 'constructs';

class GlueWorkflowStack extends cdk.Stack {
  constructor(scope: Construct, id: string, props?: cdk.StackProps) {
    super(scope, id, props);

    // Create an S3 bucket for source data
    const sourceBucket = new s3.Bucket(this, 'SourceBucket', {
      removalPolicy: cdk.RemovalPolicy.DESTROY,
    });

    // Create a Glue job
    const glueJob = new glue.CfnJob(this, 'MyGlueJob', {
      command: {
        name: 'glueetl',
        scriptLocation: `s3://${sourceBucket.bucketName}/path-to-your-glue-script.py`,
      },
      role: iam.Role.fromRoleArn(this, 'GlueJobRole', 'YOUR-GLUE-JOB-ROLE-ARN'),
    });

    // Define a Glue workflow
    const glueWorkflow = new glue.CfnWorkflow(this, 'MyGlueWorkflow', {
      defaultRunProperties: {
        JobName: glueJob.ref,
      },
    });

    // Add a trigger to the workflow (e.g., schedule)
    const trigger = new glue.CfnTrigger(this, 'MyGlueTrigger', {
      actions: [
        {
          jobName: glueJob.ref,
        },
      ],
      type: 'SCHEDULED',
      schedule: 'cron(0 0 * * ? *)', // Runs daily at midnight
      workflowName: glueWorkflow.ref,
    });
  }
}

const app = new cdk.App();
new GlueWorkflowStack(app, 'GlueWorkflowStack');