# Minimal DataOps DataBrew module configuration.
# Deploys a single DataBrew profile job against an S3 dataset.

# (Optional) DataOps project name for resource autowiring
projectName: dataops-project-sample

# (Optional) Map of dataset names to DataBrew dataset definitions
datasets:
  my-dataset:
    # File format for S3-based datasets
    format: CSV
    input:
      # S3 input location
      s3InputDefinition:
        bucket: ssm:/path_to_bucket_name
        key: 'data/input/'

# (Optional) Map of job names to DataBrew job definitions — the
# module's primary resource.
jobs:
  my-profile-job:
    # Job type: PROFILE for data profiling, RECIPE for transformation
    type: 'PROFILE'
    # Input dataset reference
    dataset:
      generated: my-dataset
    # See CONFIGURATION.md for role reference options (name, arn, id).
    # IAM execution role for job permissions
    executionRole:
      name: glue-role
    # KMS key ARN for encrypting job outputs
    kmsKeyArn: ssm:/path_to_kms_arn