Boomi DataHub Review Data Quality

arazzo: 1.0.1
info:
  title: Boomi DataHub Review Data Quality
  summary: Pick a repository, list golden records for a domain, and review quarantined records.
  description: >-
    A master-data health check. The workflow lists the available DataHub
    repositories to select one, lists the golden records for a chosen domain
    (universe) to sample the authoritative master data, and then lists the
    quarantine entries for that same domain to surface records blocked by data
    quality issues. Every step spells out its request inline so the review can be
    read and executed without opening the underlying OpenAPI description.
  version: 1.0.0
  x-realizes-capability-ids:
  - BC-610.20
  - BC-610.30
  x-capability-derivation:
    method: 'deterministic join: sourceDescriptions -> per-tag OpenAPI -> tag/capability edge. No classification at this step.'
    min_confidence: 0.7
    sources:
    - capability_id: BC-610.20
      capability_name: Master Data Management
      spec: boomi-repositories-api-openapi.yml
      confidence: 0.8
    - capability_id: BC-610.30
      capability_name: Data Quality Management
      spec: boomi-quarantine-api-openapi.yml
      confidence: 0.7
    model: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0
sourceDescriptions:
- name: goldenRecordsApi
  url: ../openapi/boomi-golden-records-api-openapi.yml
  type: openapi
- name: quarantineApi
  url: ../openapi/boomi-quarantine-api-openapi.yml
  type: openapi
- name: repositoriesApi
  url: ../openapi/boomi-repositories-api-openapi.yml
  type: openapi
workflows:
- workflowId: datahub-review-data-quality
  summary: Select a repository, sample its golden records for a domain, and review quarantined records.
  description: >-
    Lists DataHub repositories to resolve the first available repository, lists
    the golden records for the supplied domain, and lists the quarantine entries
    for that domain to review data quality.
  inputs:
    type: object
    required:
    - universeId
    properties:
      universeId:
        type: string
        description: The ID of the master data domain (universe) to review.
      pageSize:
        type: integer
        description: Number of golden records to sample per page.
  steps:
  - stepId: selectRepository
    description: >-
      List the available DataHub repositories and select the first one for
      review.
    operationId: listRepositories
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      repositoryId: $response.body#/repositories/0/id
  - stepId: sampleGoldenRecords
    description: >-
      List the golden records for the chosen domain to sample the authoritative
      master data.
    operationId: listGoldenRecords
    parameters:
    - name: repositoryId
      in: path
      value: $steps.selectRepository.outputs.repositoryId
    - name: universeId
      in: path
      value: $inputs.universeId
    - name: pageSize
      in: query
      value: $inputs.pageSize
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      records: $response.body#/records
      nextPageToken: $response.body#/nextPageToken
  - stepId: reviewQuarantine
    description: >-
      List the quarantine entries for the same domain to surface records blocked
      by data quality or matching issues.
    operationId: listQuarantineEntries
    parameters:
    - name: repositoryId
      in: path
      value: $steps.selectRepository.outputs.repositoryId
    - name: universeId
      in: path
      value: $inputs.universeId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      quarantinedRecords: $response.body#/records
  outputs:
    repositoryId: $steps.selectRepository.outputs.repositoryId
    goldenRecords: $steps.sampleGoldenRecords.outputs.records
    quarantinedRecords: $steps.reviewQuarantine.outputs.quarantinedRecords