# yaml-language-server: $schema=../../../schemas/@aws-mdaa/dataops-dms.json
# Name of the DataOps Project 
projectName: hda-project

# Contains all DMS related configuration
dms:
  # The role DMS tasks will run as. This role will require prior access to AWS-service based endpoints.
  # Access to secrets referenced in the config will be granted automatically.
  # Role must also have an assume role trust policy to the regional DMS service name: dms.<region>.amazonaws.com
  dmsRoleArn: ssm-org:/shared/generated-role/dms/arn

  # Replication instances which will be provisioned by the config
  replicationInstances:
    # Each instance has a unique name in the config
    test-instance:
      # The instance class.
      # See https://docs.aws.amazon.com/dms/latest/userguide/CHAP_ReplicationInstance.Types.html for options
      instanceClass: dms.c5.large
      # The VPC Id on which the replication instance will be deployed
      vpcId: "{{context:vpc_id}}"
      # The subnets to which the replication instance will be connected.
      subnetIds:
        - "{{context:subnet_id1}}"
        - "{{context:subnet_id2}}"
  
  # Endpoints which will be created by the config
  endpoints:
    # Each endpoint has a unique name
    test-source:
      # The type of endpoint--one of 'source' or 'target'
      endpointType: source
      # The endpoint engine name. 
      # One of mysql | oracle | postgres | mariadb | aurora | aurora-postgresql | 
      # opensearch | redshift | redshift-serverless |s3 | db2 | azuredb | sybase | 
      # dynamodb | mongodb | kinesis | kafka | elasticsearch | docdb | sqlserver | neptune | postgres
      engineName: postgres
      # Name of the database
      databaseName: "{{context:dms-source-db}}"
      # The appropriate settings for the provided engine name.
      postgreSqlSettings:
        # Arn of the secret from which credentials will be read.
        # The DMS role will be granted access to retrieve the secret
        secretsManagerSecretArn: "{{context:dms-rds-secrets-arn}}"
        # The DMS role will be granted decrypt access to this key
        secretsManagerSecretKMSArn: "{{context:dms-rds-secrets-kms-arn}}"
    test-target:
      endpointType: target
      engineName: s3
      s3Settings:
        bucketName: ssm-org:/shared/datalake/bucket/staging/name
        bucketFolder: landing
        includeOpForFullLoad: true
        datePartitionEnabled: true
        cdcInsertsAndUpdates: true
        dataFormat: parquet
        enableStatistics: true
        addColumnName: true
        parquetVersion: parquet-2-0
        serverSideEncryptionKmsKeyId: ssm-org:/shared/datalake/kms/arn

  # Replication tasks which will be created by the config.
  replicationTasks:
    # Each replication task has a unique name
    test-task:
      # The name of the replication instance to be used from the 'replicationInstances' section of the config
      replicationInstance: test-instance
      # The name of the source endpoint to be used from the 'endpoints' section of the config
      sourceEndpoint: test-source
      # The name of the target endpoint to be used from the 'endpoints' section of the config
      targetEndpoint: test-target
      # The type of migration
      # One of `full-load` | `cdc` | `full-load-and-cdc`
      migrationType: full-load-and-cdc
      # Table mappings config to be used
      # Will be passed directly to the task config.
      tableMappings:
        # same content as patients_mappings.json
        rules: [
          {
            "rule-type": "selection",
            "rule-id": "1",
            "rule-name": "patients",
            "object-locator": {
              "schema-name": "public",
              "table-name": "patient"
            },
            "rule-action": "include"
          },
          {
            "rule-type": "transformation",
            "rule-id": "2",
            "rule-name": "cdc timestamp seq",
            "rule-target": "column",
            "object-locator": {
              "schema-name": "%",
              "table-name": "%"
            },
            "rule-action": "add-column",
            "value": "CDC_TIMESTAMP_SEQ",
            "expression": "$AR_H_TIMESTAMP",
            "data-type": {
              "type": "datetime",
              "precision": 6
            }
          },
          {
            "rule-type": "transformation",
            "rule-id": "3",
            "rule-name": "cdc operation",
            "rule-target": "column",
            "object-locator": {
              "schema-name": "%",
              "table-name": "%"
            },
            "rule-action": "add-column",
            "value": "CDC_OPERATION",
            "expression": "$AR_H_OPERATION",
            "data-type": {
              "type": "string",
              "length": 50
            }
          },
          {
            "rule-type": "transformation",
            "rule-id": "4",
            "rule-name": "convert column names to uppercase",
            "rule-action": "convert-uppercase",
            "rule-target": "column",
            "object-locator": {
              "schema-name": "%",
              "table-name": "%",
              "column-name": "%"
            }
          }
        ]
      # Further settings
      replicationTaskSettings:
        Logging:
          EnableLogging: true