SharePoint Site Content Inventory

arazzo: 1.0.1
info:
  title: SharePoint Site Content Inventory
  summary: Walk a site from its title down through lists, recent items, and library files.
  description: >-
    The audit walk. Migration planning, governance reviews, and content
    cleanups all start by answering the same question: what is actually in this
    site, and when did anyone last touch it? The workflow labels the run with
    the site title, enumerates the non-hidden lists, drills into one named list
    for its metadata and most recently modified items, and then lists the files
    in a document library folder. It is read-only by design and safe to run
    against production. 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: filesApi
  url: ../openapi/sharepoint-files-api-openapi.yml
  type: openapi
- name: itemsApi
  url: ../openapi/sharepoint-items-api-openapi.yml
  type: openapi
- name: listsApi
  url: ../openapi/sharepoint-lists-api-openapi.yml
  type: openapi
- name: sitesApi
  url: ../openapi/sharepoint-sites-api-openapi.yml
  type: openapi
workflows:
- workflowId: site-content-inventory
  summary: Produce a read-only inventory of a SharePoint site's lists, items, and files.
  description: >-
    Reads the site title, enumerates visible lists, inspects one list and its
    recently modified items, and lists the files in a library folder.
  inputs:
    type: object
    required:
    - listTitle
    - folderUrl
    properties:
      listTitle:
        type: string
        description: Title of the list to drill into (e.g. "Project Tasks").
      folderUrl:
        type: string
        description: >-
          Server-relative document library folder to inventory, e.g.
          "/sites/mysite/Shared Documents".
      listLimit:
        type: integer
        description: Maximum number of lists to enumerate.
        default: 100
      itemSampleSize:
        type: integer
        description: How many recently modified items to sample from the list.
        default: 25
  steps:
  - stepId: labelRun
    description: >-
      Read the site title so the resulting inventory is labelled with the site
      it describes. Cheapest call in the API and worth it for the audit trail.
    operationId: getWebTitle
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      siteTitle: $response.body#/value
  - stepId: enumerateLists
    description: >-
      Enumerate the non-hidden lists and libraries, capturing item counts and
      last-modified dates. This is the breadth pass of the inventory.
    operationId: getLists
    parameters:
    - name: "$select"
      in: query
      value: Id,Title,Description,BaseTemplate,ItemCount,Hidden,LastItemModifiedDate
    - name: "$filter"
      in: query
      value: Hidden eq false
    - name: "$top"
      in: query
      value: $inputs.listLimit
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      lists: $response.body#/value
  - stepId: inspectList
    description: >-
      Drill into the named list for its authoritative metadata, including
      whether versioning is enabled — a detail that materially changes any
      migration or retention plan.
    operationId: getListByTitle
    parameters:
    - name: list_title
      in: path
      value: $inputs.listTitle
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      listId: $response.body#/Id
      itemCount: $response.body#/ItemCount
      baseTemplate: $response.body#/BaseTemplate
      enableVersioning: $response.body#/EnableVersioning
      lastItemModifiedDate: $response.body#/LastItemModifiedDate
  - stepId: sampleRecentItems
    description: >-
      Sample the most recently modified items, newest first. A small sample
      answers the "is anyone still using this?" question without paging the
      whole list.
    operationId: getListItems
    parameters:
    - name: list_title
      in: path
      value: $inputs.listTitle
    - name: "$select"
      in: query
      value: Id,Title,Created,Modified,AuthorId,EditorId
    - name: "$orderby"
      in: query
      value: Modified desc
    - name: "$top"
      in: query
      value: $inputs.itemSampleSize
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      recentItems: $response.body#/value
      mostRecentModified: $response.body#/value/0/Modified
  - stepId: inventoryFiles
    description: >-
      List the files in the document library folder, capturing size, version,
      and check-out state so abandoned or checked-out documents surface before a
      migration rather than during one.
    operationId: getFilesInFolder
    parameters:
    - name: folder_url
      in: path
      value: $inputs.folderUrl
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      files: $response.body#/value
      firstFileUrl: $response.body#/value/0/ServerRelativeUrl
  outputs:
    siteTitle: $steps.labelRun.outputs.siteTitle
    lists: $steps.enumerateLists.outputs.lists
    listId: $steps.inspectList.outputs.listId
    itemCount: $steps.inspectList.outputs.itemCount
    recentItems: $steps.sampleRecentItems.outputs.recentItems
    files: $steps.inventoryFiles.outputs.files