arazzo: 1.0.1
info:
  title: Acceldata Dataset Quality Audit
  summary: Resolve a dataset, list its data quality rules, and map its lineage for impact analysis.
  description: >-
    A dataset audit flow that assembles a quality picture for a single dataset.
    The workflow resolves a dataset by source, lists the data quality rules
    monitoring it, and retrieves its lineage graph so downstream consumers
    affected by quality issues can be identified. Every step spells out its
    request inline so the flow can be read and executed without opening the
    underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: acceldataAdocApi
  url: ../openapi/acceldata-adoc-api.yaml
  type: openapi
workflows:
- workflowId: dataset-quality-audit
  summary: Audit a dataset's quality rules and lineage in one pass.
  description: >-
    Finds a dataset on the given source, lists the data quality rules applied
    to it, and retrieves its upstream and downstream lineage graph for impact
    analysis.
  inputs:
    type: object
    required:
    - apiKey
    - source
    properties:
      apiKey:
        type: string
        description: Acceldata API key sent in the X-API-Key header.
      source:
        type: string
        description: Data source platform to filter datasets by (e.g. snowflake).
      lineageDirection:
        type: string
        description: Direction of lineage to retrieve (upstream, downstream, both).
      lineageDepth:
        type: integer
        description: Maximum depth of the lineage graph to return.
  steps:
  - stepId: findDataset
    description: >-
      List datasets on the given source and capture the first dataset id and its
      quality score to anchor the audit.
    operationId: listDatasets
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: source
      in: query
      value: $inputs.source
    - name: limit
      in: query
      value: 1
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      datasetId: $response.body#/data/0/id
      datasetName: $response.body#/data/0/name
      qualityScore: $response.body#/data/0/qualityScore
  - stepId: listRules
    description: >-
      List the data quality rules applied to the resolved dataset to capture how
      it is being monitored.
    operationId: listDataQualityRules
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: dataset_id
      in: query
      value: $steps.findDataset.outputs.datasetId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      ruleCount: $response.body#/total
  - stepId: getLineage
    description: >-
      Retrieve the dataset's lineage graph so upstream sources and downstream
      consumers affected by quality issues can be identified.
    operationId: getDatasetLineage
    parameters:
    - name: X-API-Key
      in: header
      value: $inputs.apiKey
    - name: id
      in: path
      value: $steps.findDataset.outputs.datasetId
    - name: direction
      in: query
      value: $inputs.lineageDirection
    - name: depth
      in: query
      value: $inputs.lineageDepth
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      upstream: $response.body#/upstream
      downstream: $response.body#/downstream
  outputs:
    datasetId: $steps.findDataset.outputs.datasetId
    qualityScore: $steps.findDataset.outputs.qualityScore
    ruleCount: $steps.listRules.outputs.ruleCount
    downstream: $steps.getLineage.outputs.downstream