Acceldata Asset Sampling API

openapi: 3.2.0
info:
  title: Catalog Asset Sampling API
  version: '1.0'
  description: API for managing the ADOC data catalog, including assets, asset metadata, tags, labels, sampling, lineage, and watched assets, as well as data reliability policies (data quality, reconciliation, data drift, schema drift, and related rule types) and their executions. Covers discovering and searching assets, retrieving asset configuration and activity, and creating, scheduling, and running policies against catalog assets.
tags:
- name: Asset Sampling
paths:
  /catalog-server/api/assets/{id}/sample/async:
    post:
      operationId: requestAssetSampleAsync
      tags:
      - Asset Sampling
      summary: Request an async sample of asset data
      description: 'This endpoint initiates an asynchronous request to retrieve sample data of a specified asset by its `id`. If the sample data is not cached, the API returns a job execution status of IN_PROGRESS along with a `requestId`. The client needs to poll the `catalog-server/api/assets/sample/result/{requestId}` endpoint until the job execution status is SUCCESSFUL. Once the result is cached or the job status is SUCCESSFUL, the API retrieves the first 100 rows of the asset''s sample data.


        **Authorization**: requires `ASSET_VIEW`.


        ### Request Body


        Optional `SampleDataWithTransformUDFsRequest`:


        - `invalidateCache` (boolean): Specifies whether the cache should be invalidated. If set to `true`, the API bypasses any cached sample data and initiates a fresh sample generation. If set to `false`, cached data (if available) will be used.

        - Transform UDF fields may also be supplied to apply transformations during sampling.


        ### Response


        Returns `SampleDataApiResponse` with job status and, when complete, sample rows.'
      parameters:
      - name: id
        in: path
        description: Asset ID
        required: true
        schema:
          type: integer
      - name: accessKey
        in: header
        description: API access key generated from ADOC UI
        required: true
        schema:
          type: string
      - name: secretKey
        in: header
        description: API secret key generated from ADOC UI
        required: true
        schema:
          type: string
      - name: Accept
        in: header
        description: Always set to application/json
        required: true
        schema:
          type: string
      - name: Content-Type
        in: header
        description: Always set to application/json
        required: true
        schema:
          type: string
      requestBody:
        description: 'Sample data request with optional transform UDFs and `invalidateCache` flag.

          Schema: `SampleDataWithTransformUDFsRequest`.'
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SampleDataWithTransformUDFsRequest'
      responses:
        '200':
          description: Sample data response with job status and optional sample rows
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SampleDataApiResponse'
  /catalog-server/api/assets/sample/result/{requestId}:
    get:
      operationId: getAssetSampleResult
      tags:
      - Asset Sampling
      summary: Get sample data result
      description: 'This endpoint retrieves the status and results of a sample data request, triggered by the `POST /catalog-server/api/assets/{id}/sample/async` endpoint.


        This process involves the following steps:


        1. **Poll for Status**: Use the `requestId` to poll the status of the job by making GET requests to the endpoint `catalog-server/api/assets/sample/result/{requestId}`.

        2. **Retrieve Sample Data**: Continue polling until the job execution status is `SUCCESSFUL`. Once successful, the API will retrieve and return the first 100 rows of the asset''s sample data.


        **Authorization**: requires `ASSET_VIEW`.


        ### Response


        Returns `SampleDataApiResponse` containing execution status and sample data when available.'
      parameters:
      - name: requestId
        in: path
        description: Sample request ID
        required: true
        schema:
          type: string
      - name: accessKey
        in: header
        description: API access key generated from ADOC UI
        required: true
        schema:
          type: string
      - name: secretKey
        in: header
        description: API secret key generated from ADOC UI
        required: true
        schema:
          type: string
      - name: Accept
        in: header
        description: Always set to application/json
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Sample data result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SampleDataApiResponse'
        '404':
          description: 'Dataplane job not found for requestId: {requestId}'
components:
  schemas:
    PolicyTransformUDF:
      type: object
      title: io.ad.catalog.api.model.quality.PolicyTransformUDF
      required:
      - assetId
      - name
      - parameters
      - udfId
      properties:
        assetId:
          type: integer
        columnNames:
          type:
          - array
          - 'null'
          items:
            type: string
        id:
          type: integer
        name:
          type: string
        parameters:
          type: array
          items:
            $ref: '#/components/schemas/UdfVariable'
        ruleId:
          type: integer
        udfId:
          type: integer
    SampleDataWithTransformUDFsRequest:
      type: object
      title: io.ad.catalog.api.model.quality.SampleDataWithTransformUDFsRequest
      required:
      - enableSyncForPushdown
      - filterAssetSelections
      - invalidateCache
      - transformUDFs
      properties:
        enableSyncForPushdown:
          type: boolean
        filter:
          type:
          - string
          - 'null'
        filterAssetSelections:
          type: boolean
        invalidateCache:
          type: boolean
        transformUDFs:
          type: array
          items:
            $ref: '#/components/schemas/PolicyTransformUDF'
    Any:
      type: object
      title: kotlin.Any
    File:
      type: object
      title: java.io.File
      required:
      - path
      - status
      - prefixLength
      - filePath
      properties:
        path:
          type: string
        status:
          type: string
          enum:
          - INVALID
          - CHECKED
        prefixLength:
          type: integer
        filePath:
          type: array
          items:
            type: object
    UdfVariable:
      type: object
      title: io.ad.catalog.api.model.UdfVariable
      required:
      - key
      properties:
        isColumnVariable:
          type: boolean
        key:
          type: string
        value:
          type:
          - string
          - 'null'
    SampleDataApiResponse:
      type: object
      title: io.ad.torch.client.analysis.models.SampleDataApiResponse
      properties:
        errorMsg:
          type:
          - string
          - 'null'
        executionId:
          type:
          - string
          - 'null'
        file:
          oneOf:
          - $ref: '#/components/schemas/File'
          - type: 'null'
        jobExecutionStatus:
          type:
          - string
          - 'null'
          enum:
          - WAITING
          - SKIPPED
          - SUBMITTED
          - QUEUED
          - IN_PROGRESS
          - ABORTED
          - FAILED
          - POSTPROCESSING
          - ANOMALY_DETECTION
          - EXECUTION_RESULT
          - SUCCESSFUL
        requestId:
          type:
          - string
          - 'null'
        sampleData:
          type:
          - object
          - 'null'
          additionalProperties:
            $ref: '#/components/schemas/Any'