# DataBrew config without projectName — explicit KMS, bucket, deployment role,
# and security configuration instead of auto-wiring from a DataOps project.

# KMS key ARN for encrypting DataOps resources and data.
kmsArn: arn:{{partition}}:kms:{{region}}:{{account}}:key/test-key-id
# S3 bucket name for project storage (scripts, artifacts, temp files).
bucketName: test-databrew-bucket
# IAM role ARN for deployment operations and resource management.
deploymentRoleArn: arn:{{partition}}:iam::{{account}}:role/test-deploy-role
# Glue security configuration name for job encryption (at rest, in transit, CloudWatch logs).
securityConfigurationName: test-security-config
# SNS topic ARN for job notifications and workflow alerts.
notificationTopicArn: arn:{{partition}}:sns:{{region}}:{{account}}:test-topic

recipes:
  mdaa-jdbc-recipe:
    description: Renames id column to employee_id
    steps: |
      [
        {
          "Action": {
            "Operation": "RENAME",
            "Parameters": {
              "sourceColumn": "id",
              "targetColumn": "employee_id"
            }
          }
        }
      ]

  mdaa-s3-recipe:
    description: Renames employee_id column back to id
    steps: |
      [
        {
          "Action": {
            "Operation": "RENAME",
            "Parameters": {
              "sourceColumn": "employee_id",
              "targetColumn": "id"
            }
          }
        }
      ]

  mdaa-catalog-recipe:
    description: Renames employee_id column back to id for catalog sources
    steps: |
      [
        {
          "Action": {
            "Operation": "RENAME",
            "Parameters": {
              "sourceColumn": "employee_id",
              "targetColumn": "id"
            }
          }
        }
      ]

datasets:
  mdaa-jdbc-dataset:
    input:
      databaseInputDefinition:
        glueConnectionName: project:connections/connectionJdbc
        databaseTableName: 'mydb_admin.allusers'

  mdaa-s3-dataset:
    input:
      s3InputDefinition:
        bucket: ssm:/path_to_bucket_name
        key: 'data/raw_data/input_data.csv.snappy'

  mdaa-catalog-dataset:
    input:
      dataCatalogInputDefinition:
        databaseName: project:databaseName/demo-database
        tableName: demo_raw_data

jobs:
  test-recipe-job6:
    type: 'RECIPE'
    projectName: 'mdaa-test-project'
    dataset:
      generated: mdaa-jdbc-dataset
    recipe:
      existing:
        name: org-dev-data-ops-databrew-mdaa-s3-recipe
    outputs:
      - location:
          bucket: ssm:/path_to_bucket_name
          key: 'data/databrew/transformed/'
        compressionFormat: 'SNAPPY'
        format: 'PARQUET'
        overwrite: true
        partitionColumns: ['id']
    # See CONFIGURATION.md for role reference options (name, arn, id).
    executionRole:
      name: ssm:/path_to_role_name
    kmsKeyArn: ssm:/path_to_kms_arn
    schedule:
      name: 'mdaa-test-job-schedule'
      cronExpression: 'Cron(50 21 * * ? *)'

  test-profile-job:
    type: 'PROFILE'
    dataset:
      generated: mdaa-jdbc-dataset
    outputLocation:
      bucket: ssm:/path_to_bucket_name
      key: 'data/databrew/profile/'
    executionRole:
      name: ssm:/path_to_role_name
    kmsKeyArn: ssm:/path_to_kms_arn
    schedule:
      name: 'mdaa-test-profile-schedule'
      cronExpression: 'Cron(50 21 * * ? *)'