id: https://api-evangelist.github.io/amazon-datazone/vocabulary/amazon-datazone-vocabulary.yaml
name: Amazon DataZone Vocabulary
description: Controlled vocabulary for Amazon DataZone covering domains, projects, assets, subscriptions, and data governance concepts.
version: 1.0.0
specificationVersion: 1.0.0

tags:
  - AWS
  - Data Catalog
  - Data Governance
  - Data Management

operational:
  resources:
    - term: Domain
      definition: A DataZone organizational boundary containing a data catalog, governance policies, and data sharing infrastructure
    - term: Project
      definition: A container within a domain for organizing data assets, environments, and team members around a business purpose
    - term: Asset
      definition: A cataloged data resource (table, file, API, report) published in the DataZone data catalog for discovery
    - term: Listing
      definition: A published version of a data asset made available for subscription in the DataZone business catalog
    - term: Subscription
      definition: An approved access grant allowing a project to use a subscribed data asset
    - term: SubscriptionRequest
      definition: A request submitted by a data consumer to gain access to a data asset listing
    - term: Environment
      definition: A configured data access environment within a project providing tools like Athena, Glue, or Redshift
    - term: EnvironmentProfile
      definition: A reusable template for creating environments with predefined configurations and tooling

  actions:
    - term: CreateDomain
      definition: Provision a new DataZone domain as the governance and catalog boundary
    - term: CreateProject
      definition: Create a project within a domain to organize data and team access
    - term: CreateAsset
      definition: Catalog a data resource in the DataZone data catalog
    - term: PublishListing
      definition: Make a cataloged asset available for subscription in the business catalog
    - term: CreateSubscriptionRequest
      definition: Request access to a published data asset with business justification
    - term: ApproveSubscriptionRequest
      definition: Grant a subscription request to give the requesting project access to data
    - term: RevokeSubscription
      definition: Remove previously granted data access from a subscribing project

  domainStatuses:
    - term: AVAILABLE
      definition: Domain is operational and ready for use
    - term: CREATING
      definition: Domain is being provisioned
    - term: CREATION_FAILED
      definition: Domain provisioning failed
    - term: DELETING
      definition: Domain is being removed
    - term: DELETED
      definition: Domain has been deleted

  subscriptionStatuses:
    - term: PENDING
      definition: Subscription request has been submitted and awaits review
    - term: ACCEPTED
      definition: Subscription request was approved and access is being provisioned
    - term: REJECTED
      definition: Subscription request was declined by the data owner

capability:
  personas:
    - term: Data Domain Owner
      definition: Owner responsible for domain governance policies, user access, and catalog standards
    - term: Data Producer
      definition: Data owner who publishes and maintains data assets in the DataZone catalog
    - term: Data Consumer
      definition: Analyst or engineer who discovers, requests, and uses cataloged data assets

  workflows:
    - term: Set Up Data Domain
      definition: Initializing a DataZone domain with projects and environments for data sharing
    - term: Publish Data Asset
      definition: Cataloging and publishing a data asset for discovery by other teams
    - term: Request Data Access
      definition: Discovering, requesting, and receiving access to a published data asset

crossReference:
  awsServices:
    - term: AWS Glue
      definition: DataZone integrates with Glue Data Catalog to auto-discover and catalog Glue tables
      url: https://aws.amazon.com/glue/
    - term: Amazon Redshift
      definition: DataZone can catalog Redshift tables and govern data sharing between Redshift clusters
      url: https://aws.amazon.com/redshift/
    - term: Amazon Athena
      definition: DataZone environments can provision Athena for querying cataloged S3 data
      url: https://aws.amazon.com/athena/
    - term: Amazon S3
      definition: DataZone catalogs data assets stored in Amazon S3 and manages access through subscriptions
      url: https://aws.amazon.com/s3/
    - term: AWS Lake Formation
      definition: DataZone uses Lake Formation for fine-grained data access control on subscribed assets
      url: https://aws.amazon.com/lake-formation/
    - term: AWS IAM
      definition: IAM roles provide the execution context for DataZone domain operations and resource access
      url: https://aws.amazon.com/iam/