# Sample config for the DataOps Data Quality module.
# Demonstrates standalone data quality rulesets with explicit KMS,
# bucket, deployment role, and security configuration (no projectName).

# 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-dq-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.
securityConfigurationName: test-security-config
# SNS topic ARN for job notifications and workflow alerts.
notificationTopicArn: arn:{{partition}}:sns:{{region}}:{{account}}:test-topic

# Map of ruleset names to Glue Data Quality ruleset definitions for automated table validation.
rulesets:
  customer-data-quality:
    # Description explaining the purpose and scope of the ruleset.
    description: Validate customer data completeness and uniqueness
    # Target table specifying which Glue Catalog table to validate.
    targetTable:
      # Glue database name containing the target table.
      databaseName: project:databaseName/customer-data
      # Glue table name to validate with data quality rules.
      tableName: customers
    # Ruleset as an array of structured rule objects.
    ruleset:
      - ruleType: IsComplete
        column: customer_id
      - ruleType: Uniqueness
        column: email
        comparisonOperator: '>'
        threshold: 0.95
      - ruleType: RowCount
        comparisonOperator: '>'
        value: 100

  order-data-quality:
    description: Validate order data freshness and values
    targetTable:
      databaseName: project:databaseName/order-data
      tableName: orders
    # Ruleset as a raw DQDL string.
    ruleset: |
      Rules = [
        IsComplete "order_id",
        ColumnValues "status" in ["pending", "completed", "cancelled"],
        RowCount > 0
      ]