# yaml-language-server: $schema=../../schemas/@aws-mdaa/cli.json
# All resources will be deployed to the default region specified in the environment or AWS configurations.
# Can optional specify a specific AWS Region Name.
region: default

# Tags applied to all deployed resources
tag_config_data:
  costcentre: '123456'
  project: data-ecosystem

## Pre-Deployment Instructions

# Failure to do so may result in global naming conflicts.
# TODO: Set a globally unique organization name (used in S3 bucket names and resource prefixes)
organization: <YOUR_ORG_NAME>

# Optional: IAM permissions boundary policy ARN.
# When specified, the managed policy is applied as a permissions boundary
# to all IAM roles across all stacks. Supports hierarchy — can be overridden
# at the domain or environment level to use a different boundary per scope.
# permissions_boundary_arn: arn:aws:iam::<account-id>:policy/<boundary-policy-name>

# One or more domains may be specified. Domain name will be incorporated by default naming implementation
# to prefix all resource names.
domains:
  # The named of the domain. In this case, we are building a 'shared' domain.
  shared:
    # One or more environments may be specified, typically along the lines of 'dev', 'test', and/or 'prod'
    environments:
      # The environment name will be incorporated into resource name by the default naming implementation.
      dev:
        # The target deployment account can be specified per environment.
        # If 'default' or not specified, the account configured in the environment will be assumed.
        account: default
        # The list of modules which will be deployed. A module points to a specific MDAA CDK App, and
        # specifies a deployment configuration file if required.
        modules:
          # This module will create all the roles required for the datalake, as well as dataops layers running on top
          roles: # The module name (ie 'roles') will be incorporated into resource name by the default naming implementation.
            module_path: "@aws-mdaa/roles"
            module_configs:
              - ./roles.yaml

          # This module will deploy the S3 data lake buckets.
          # Coarse grained access may be granted directly to S3 for certain roles.
          datalake:
            module_path: "@aws-mdaa/datalake"
            module_configs:
              - ./datalake/datalake.yaml

          # This module will ensure the Glue Catalog is KMS encrypted.
          # NOTE: Account-level module — can only be deployed once per AWS account.
          glue-catalog:
            module_path: "@aws-mdaa/glue-catalog"

          # This module will ensure that LakeFormation is configured to
          # automatically generate IAMAllowedPrincipal grants on new databases and tables.
          # This effectively delegates all Glue resource access controls
          # to IAM.
          # NOTE: Account-level module — can only be deployed once per AWS account.
          lakeformation-settings:
            module_path: "@aws-mdaa/lakeformation-settings"
            module_configs:
              - ./datalake/lakeformation-settings.yaml

          # This module will create an Athena Workgroup which can be used to query
          # the data lake.
          athena:
            module_path: "@aws-mdaa/athena-workgroup"
            module_configs:
              - ./datalake/athena.yaml

          # This module will create a secure S3-based bucket for use as a Cloudtrail Inventory target.
          audit: 
            module_path: "@aws-mdaa/audit" 
            module_configs:
              - ./governance/audit.yaml 
          
          # This module will create a secure S3-based Audit Trail.
          audit-trail: 
            module_path: "@aws-mdaa/audit-trail" 
            module_configs:
              - ./governance/audit-trail.yaml

  # The named of the domain. In this case, we are building a 'dataops' domain.
  dataops:
    # One or more environments may be specified, typically along the lines of 'dev', 'test', and/or 'prod'
    environments:
      # The environment name will be incorporated into resource name by the default naming implementation.
      dev:
        # The target deployment account can be specified per environment.
        # If 'default' or not specified, the account configured in the environment will be assumed.
        account: default
        # The list of modules which will be deployed. A module points to a specific MDAA CDK App, and
        # specifies a deployment configuration file if required.
        modules:
          # This module will create DataOps Project resources which can be shared
          # across multiple
          example-project:
            module_path: "@aws-mdaa/dataops-project"
            module_configs:
              - ./dataops/project.yaml
          example-crawler:
            module_path: "@aws-mdaa/dataops-crawler"
            module_configs:
              - ./dataops/crawler.yaml
            postdeploy:
              command: "./dataops/create_table.sh {{org}} {{region}}"
              exit_if_fail: true
          example-data-quality:
            module_path: "@aws-mdaa/dataops-data-quality"
            module_configs:
              - ./dataops/data-quality.yaml