# DataOps Job module configuration demonstrating Amazon DataZone data lineage.
# Deploys a Glue ETL job that emits OpenLineage events to a DataZone /
# SageMaker Unified Studio domain, mirroring the Glue Studio "Generate lineage
# events" toggle. See the module README section "DataZone Data Lineage".

# (Optional) DataOps project name for job resource autowiring.
projectName: dataops-project-test

# Map of job names to Glue job definitions.
jobs:
  LineageJob:
    # IAM role ARN for Glue job execution permissions.
    executionRoleArn: arn:{{partition}}:iam::{{account}}:role/example-lineage-glue-role
    # Job command configuration.
    command:
      # Job type. (enum: glueetl, pythonshell)
      name: 'glueetl'
      # (Optional) Python version. (enum: 2, 3)
      pythonVersion: '3'
      # Relative path to the Glue script.
      scriptLocation: ./src/glue/python/job.py
    # Job description.
    description: Glue ETL job emitting DataZone lineage events
    # (Optional) DataZone Spark lineage requires Glue 5.0 or higher.
    glueVersion: '5.0'
    # (Optional) Amazon DataZone lineage configuration.
    lineage:
      # Emit OpenLineage events to DataZone.
      enabled: true
      # DataZone (SageMaker Unified Studio) domain ID receiving the events.
      domainId: dzd_examplelineage
      # (Optional) Glue Data Catalog account for spark.glue.accountId. Must be a
      # 12-digit account ID. Defaults to the deploying account.
      # accountId: '123456789012'
      # (Optional) Set to false when the execution role is externally managed and
      # you will grant datazone:PostLineageEvent yourself. Defaults to true.
      # manageExecutionRolePolicy: false