Salesforce Bulk Query

arazzo: 1.0.1
info:
  title: Salesforce Bulk Query
  summary: Run the Bulk API 2.0 query lifecycle — create a query job, poll until JobComplete, and download the result CSV.
  description: >-
    The Bulk API 2.0 query lifecycle for extracting large volumes of data with
    a single SOQL statement. The workflow creates an asynchronous query job,
    polls the job state until it reaches JobComplete (branching to retry while
    InProgress and to fail if the job reports Failed or Aborted), and finally
    retrieves the query results as CSV. 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: salesforceBulkApi
  url: ../openapi/salesforce-bulk-api-2-openapi.yml
  type: openapi
workflows:
- workflowId: bulk-query
  summary: Extract records from Salesforce with a Bulk API 2.0 query job.
  description: >-
    Creates a query job from a SOQL statement, polls until JobComplete, and
    returns the result CSV.
  inputs:
    type: object
    required:
    - query
    properties:
      query:
        type: string
        description: >-
          The SOQL query to run (e.g. SELECT Id, Name, Email FROM Contact WHERE
          CreatedDate = LAST_YEAR).
      operation:
        type: string
        description: >-
          The query operation: query for active records only, or queryAll to
          include soft-deleted and archived records. Defaults to query.
      maxRecords:
        type: integer
        description: Maximum number of records to return when fetching results.
  steps:
  - stepId: createQueryJob
    description: >-
      Create a new Bulk API 2.0 query job from the supplied SOQL statement. The
      job is processed asynchronously.
    operationId: createQueryJob
    requestBody:
      contentType: application/json
      payload:
        operation: query
        query: $inputs.query
        contentType: CSV
        columnDelimiter: COMMA
        lineEnding: LF
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      jobId: $response.body#/id
      state: $response.body#/state
  - stepId: pollJob
    description: >-
      Poll the query job state. When the job reaches JobComplete, continue to
      retrieve results; while still InProgress or UploadComplete, loop back to
      poll again; if the job Failed or Aborted, stop the workflow.
    operationId: getQueryJobInfo
    parameters:
    - name: jobId
      in: path
      value: $steps.createQueryJob.outputs.jobId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      state: $response.body#/state
      numberRecordsProcessed: $response.body#/numberRecordsProcessed
    onSuccess:
    - name: jobComplete
      type: goto
      stepId: getResults
      criteria:
      - condition: $response.body#/state == "JobComplete"
    - name: stillProcessing
      type: goto
      stepId: pollJob
      criteria:
      - condition: $response.body#/state == "InProgress"
    onFailure:
    - name: jobFailed
      type: end
      criteria:
      - condition: $response.body#/state == "Failed"
  - stepId: getResults
    description: >-
      Retrieve the query results as CSV once the job has reached JobComplete.
      The first row is a header of field API names.
    operationId: getQueryJobResults
    parameters:
    - name: jobId
      in: path
      value: $steps.createQueryJob.outputs.jobId
    - name: maxRecords
      in: query
      value: $inputs.maxRecords
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      results: $response.body
  outputs:
    jobId: $steps.createQueryJob.outputs.jobId
    state: $steps.pollJob.outputs.state
    numberRecordsProcessed: $steps.pollJob.outputs.numberRecordsProcessed
    results: $steps.getResults.outputs.results