Microsoft Purview Scanning API

openapi: 3.1.0
info:
  title: Microsoft Purview Scanning API
  description: >-
    APIs for configuring and managing scans of data sources to automatically
    discover and catalog data assets. Supports registering data sources and
    scheduling automated scans across your data estate.
  version: 2023-09-01
  contact:
    name: Microsoft Purview Support
    url: https://learn.microsoft.com/en-us/purview/
  license:
    name: Microsoft API License
    url: https://azure.microsoft.com/en-us/support/legal/
servers:
  - url: https://{accountName}.scan.purview.azure.com
    description: Microsoft Purview Scanning API endpoint
    variables:
      accountName:
        description: The name of the Microsoft Purview account
        default: myaccount
security:
  - oauth2: []
tags:
  - name: Classification Rules
    description: Operations for managing classification rules
  - name: Data Sources
    description: Operations for managing data source registrations
  - name: Scan Result
    description: Operations for running scans and viewing scan results
  - name: Scan Rulesets
    description: Operations for managing scan rulesets
  - name: Scans
    description: Operations for managing scan configurations
  - name: Triggers
    description: Operations for managing scan triggers and schedules
paths:
  /scan/datasources/{dataSourceName}:
    put:
      operationId: createOrReplaceDataSource
      summary: Microsoft Purview Create or replace a data source
      description: Creates or replaces a data source registration in the Purview account.
      tags:
        - Data Sources
      parameters:
        - name: dataSourceName
          in: path
          required: true
          description: The name of the data source
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DataSource'
      responses:
        '200':
          description: Data source updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataSource'
        '201':
          description: Data source created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataSource'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
    get:
      operationId: getDataSource
      summary: Microsoft Purview Get a data source
      description: Gets a data source by name.
      tags:
        - Data Sources
      parameters:
        - name: dataSourceName
          in: path
          required: true
          description: The name of the data source
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Data source retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataSource'
        '401':
          description: Unauthorized
        '404':
          description: Data source not found
    delete:
      operationId: deleteDataSource
      summary: Microsoft Purview Delete a data source
      description: Deletes a data source registration.
      tags:
        - Data Sources
      parameters:
        - name: dataSourceName
          in: path
          required: true
          description: The name of the data source
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Data source deleted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataSource'
        '401':
          description: Unauthorized
        '404':
          description: Data source not found
  /scan/datasources:
    get:
      operationId: listDataSources
      summary: Microsoft Purview List data sources
      description: Lists data sources in Data catalog.
      tags:
        - Data Sources
      parameters:
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Data sources listed successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DataSourceList'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}:
    put:
      operationId: createOrReplaceScan
      summary: Microsoft Purview Create or replace a scan
      description: Creates or replaces an instance of a scan for a given data source.
      tags:
        - Scans
      parameters:
        - name: dataSourceName
          in: path
          required: true
          description: The name of the data source
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          description: The name of the scan
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Scan'
      responses:
        '200':
          description: Scan updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Scan'
        '201':
          description: Scan created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Scan'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
    get:
      operationId: getScan
      summary: Microsoft Purview Get a scan
      description: Gets a scan information for a given data source.
      tags:
        - Scans
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Scan'
        '401':
          description: Unauthorized
        '404':
          description: Scan not found
    delete:
      operationId: deleteScan
      summary: Microsoft Purview Delete a scan
      description: Deletes the scan associated with the data source.
      tags:
        - Scans
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan deleted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Scan'
        '401':
          description: Unauthorized
        '404':
          description: Scan not found
  /scan/datasources/{dataSourceName}/scans:
    get:
      operationId: listScansByDataSource
      summary: Microsoft Purview List scans by data source
      description: Lists scans in a data source.
      tags:
        - Scans
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scans listed successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanList'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}/runs/{runId}:
    put:
      operationId: runScan
      summary: Microsoft Purview Run a scan
      description: Runs the scan for a data source.
      tags:
        - Scan Result
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: runId
          in: path
          required: true
          description: The unique identifier for the scan run
          schema:
            type: string
            format: uuid
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
        - name: scanLevel
          in: query
          description: The level of scan (Full or Incremental)
          schema:
            type: string
            enum: [Full, Incremental]
      responses:
        '202':
          description: Scan run accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OperationResponse'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}/runs/{runId}/:cancel:
    post:
      operationId: cancelScan
      summary: Microsoft Purview Cancel a scan run
      description: Cancels a running scan.
      tags:
        - Scan Result
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: runId
          in: path
          required: true
          schema:
            type: string
            format: uuid
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '202':
          description: Scan cancellation accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OperationResponse'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}/runs:
    get:
      operationId: listScanHistory
      summary: Microsoft Purview List scan history
      description: Lists the scan history of a scan.
      tags:
        - Scan Result
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan history retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanResultList'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}/triggers/default:
    put:
      operationId: createOrReplaceTrigger
      summary: Microsoft Purview Create or replace a scan trigger
      description: Creates or replaces an instance of a trigger for scheduling scans.
      tags:
        - Triggers
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Trigger'
      responses:
        '200':
          description: Trigger updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Trigger'
        '201':
          description: Trigger created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Trigger'
        '401':
          description: Unauthorized
    get:
      operationId: getTrigger
      summary: Microsoft Purview Get a scan trigger
      description: Gets trigger information for a scan.
      tags:
        - Triggers
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Trigger retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Trigger'
        '401':
          description: Unauthorized
        '404':
          description: Trigger not found
    delete:
      operationId: deleteTrigger
      summary: Microsoft Purview Delete a scan trigger
      description: Deletes the trigger associated with the scan.
      tags:
        - Triggers
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Trigger deleted successfully
        '401':
          description: Unauthorized
        '404':
          description: Trigger not found
  /scan/datasources/{dataSourceName}/scans/{scanName}/triggers/default/:enable:
    post:
      operationId: enableTrigger
      summary: Microsoft Purview Enable a scan trigger
      description: Enables a trigger for scheduled scanning.
      tags:
        - Triggers
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Trigger enabled successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Trigger'
        '401':
          description: Unauthorized
  /scan/datasources/{dataSourceName}/scans/{scanName}/triggers/default/:disable:
    post:
      operationId: disableTrigger
      summary: Microsoft Purview Disable a scan trigger
      description: Disables a trigger for scheduled scanning.
      tags:
        - Triggers
      parameters:
        - name: dataSourceName
          in: path
          required: true
          schema:
            type: string
        - name: scanName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Trigger disabled successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Trigger'
        '401':
          description: Unauthorized
  /scan/classificationrules/{classificationRuleName}:
    put:
      operationId: createOrReplaceClassificationRule
      summary: Microsoft Purview Create or replace a classification rule
      description: Creates or replaces a classification rule.
      tags:
        - Classification Rules
      parameters:
        - name: classificationRuleName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ClassificationRule'
      responses:
        '200':
          description: Classification rule updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassificationRule'
        '201':
          description: Classification rule created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassificationRule'
        '401':
          description: Unauthorized
    get:
      operationId: getClassificationRule
      summary: Microsoft Purview Get a classification rule
      description: Gets a classification rule by name.
      tags:
        - Classification Rules
      parameters:
        - name: classificationRuleName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Classification rule retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassificationRule'
        '401':
          description: Unauthorized
        '404':
          description: Classification rule not found
    delete:
      operationId: deleteClassificationRule
      summary: Microsoft Purview Delete a classification rule
      description: Deletes a classification rule.
      tags:
        - Classification Rules
      parameters:
        - name: classificationRuleName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Classification rule deleted successfully
        '401':
          description: Unauthorized
        '404':
          description: Classification rule not found
  /scan/classificationrules:
    get:
      operationId: listClassificationRules
      summary: Microsoft Purview List classification rules
      description: Lists classification rules in the account.
      tags:
        - Classification Rules
      parameters:
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Classification rules listed successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ClassificationRuleList'
        '401':
          description: Unauthorized
  /scan/scanrulesets/{scanRulesetName}:
    put:
      operationId: createOrReplaceScanRuleset
      summary: Microsoft Purview Create or replace a scan ruleset
      description: Creates or replaces a scan ruleset.
      tags:
        - Scan Rulesets
      parameters:
        - name: scanRulesetName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScanRuleset'
      responses:
        '200':
          description: Scan ruleset updated successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanRuleset'
        '201':
          description: Scan ruleset created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanRuleset'
        '401':
          description: Unauthorized
    get:
      operationId: getScanRuleset
      summary: Microsoft Purview Get a scan ruleset
      description: Gets a scan ruleset by name.
      tags:
        - Scan Rulesets
      parameters:
        - name: scanRulesetName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan ruleset retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanRuleset'
        '401':
          description: Unauthorized
        '404':
          description: Scan ruleset not found
    delete:
      operationId: deleteScanRuleset
      summary: Microsoft Purview Delete a scan ruleset
      description: Deletes a scan ruleset.
      tags:
        - Scan Rulesets
      parameters:
        - name: scanRulesetName
          in: path
          required: true
          schema:
            type: string
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan ruleset deleted successfully
        '401':
          description: Unauthorized
  /scan/scanrulesets:
    get:
      operationId: listScanRulesets
      summary: Microsoft Purview List scan rulesets
      description: Lists scan rulesets in the account.
      tags:
        - Scan Rulesets
      parameters:
        - name: api-version
          in: query
          required: true
          schema:
            type: string
            default: '2023-09-01'
      responses:
        '200':
          description: Scan rulesets listed successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScanRulesetList'
        '401':
          description: Unauthorized
components:
  securitySchemes:
    oauth2:
      type: oauth2
      description: Azure Active Directory OAuth2 authentication
      flows:
        clientCredentials:
          tokenUrl: https://login.microsoftonline.com/{tenantId}/oauth2/v2.0/token
          scopes:
            https://purview.azure.net/.default: Access Microsoft Purview
  schemas:
    DataSource:
      type: object
      description: A registered data source
      properties:
        id:
          type: string
          readOnly: true
        name:
          type: string
        kind:
          type: string
          description: The data source type
          enum:
            - AzureSubscription
            - AzureResourceGroup
            - AzureSynapseWorkspace
            - AzureSynapse
            - AdlsGen1
            - AdlsGen2
            - AmazonAccount
            - AmazonS3
            - AmazonSql
            - AzureCosmosDb
            - AzureDataExplorer
            - AzureFileService
            - AzureSqlDatabase
            - AzureSqlDatabaseManagedInstance
            - AzureSqlDataWarehouse
            - AzureMySql
            - AzurePostgreSql
            - AzureStorage
            - Teradata
            - Oracle
            - SapS4Hana
            - SapEcc
            - PowerBI
        properties:
          type: object
          description: Data source properties
          properties:
            endpoint:
              type: string
            resourceGroup:
              type: string
            subscriptionId:
              type: string
            location:
              type: string
            resourceName:
              type: string
            resourceId:
              type: string
            collection:
              $ref: '#/components/schemas/CollectionReference'
            dataSourceCollectionMovingState:
              type: integer
              format: int32
            createdAt:
              type: string
              format: date-time
            lastModifiedAt:
              type: string
              format: date-time
        scans:
          type: array
          items:
            $ref: '#/components/schemas/Scan'
    DataSourceList:
      type: object
      properties:
        value:
          type: array
          items:
            $ref: '#/components/schemas/DataSource'
        nextLink:
          type: string
        count:
          type: integer
          format: int64
    Scan:
      type: object
      description: A scan configuration
      properties:
        id:
          type: string
          readOnly: true
        name:
          type: string
        kind:
          type: string
          description: The scan type
        properties:
          type: object
          properties:
            scanRulesetName:
              type: string
            scanRulesetType:
              type: string
              enum: [Custom, System]
            collection:
              $ref: '#/components/schemas/CollectionReference'
            connectedVia:
              $ref: '#/components/schemas/ConnectedVia'
            createdAt:
              type: string
              format: date-time
            lastModifiedAt:
              type: string
              format: date-time
            lastScheduled:
              type: string
              format: date-time
    ScanList:
      type: object
      properties:
        value:
          type: array
          items:
            $ref: '#/components/schemas/Scan'
        nextLink:
          type: string
        count:
          type: integer
          format: int64
    ScanResult:
      type: object
      description: The result of a scan run
      properties:
        parentId:
          type: string
        id:
          type: string
        resourceId:
          type: string
        status:
          type: string
          enum: [Accepted, InProgress, TransientFailure, Succeeded, Failed, Canceled]
        assetsDiscovered:
          type: integer
          format: int64
        assetsClassified:
          type: integer
          format: int64
        diagnostics:
          type: object
        startTime:
          type: string
          format: date-time
        endTime:
          type: string
          format: date-time
        scanRulesetVersion:
          type: integer
          format: int32
        scanRulesetType:
          type: string
          enum: [Custom, System]
        scanLevelType:
          type: string
          enum: [Full, Incremental]
        errorMessage:
          type: string
    ScanResultList:
      type: object
      properties:
        value:
          type: array
          items:
            $ref: '#/components/schemas/ScanResult'
        nextLink:
          type: string
        count:
          type: integer
          format: int64
    Trigger:
      type: object
      description: A scan trigger for scheduling automated scans
      properties:
        id:
          type: string
          readOnly: true
        name:
          type: string
        properties:
          type: object
          properties:
            recurrence:
              $ref: '#/components/schemas/TriggerRecurrence'
            recurrenceInterval:
              type: string
            createdAt:
              type: string
              format: date-time
            lastModifiedAt:
              type: string
              format: date-time
            lastScheduled:
              type: string
              format: date-time
            scanLevel:
              type: string
              enum: [Full, Incremental]
            incrementalScanStartTime:
              type: string
              format: date-time
    TriggerRecurrence:
      type: object
      properties:
        frequency:
          type: string
          enum: [Week, Month, Day]
        interval:
          type: integer
          format: int32
        startTime:
          type: string
          format: date-time
        endTime:
          type: string
          format: date-time
        schedule:
          $ref: '#/components/schemas/RecurrenceSchedule'
        timeZone:
          type: string
    RecurrenceSchedule:
      type: object
      properties:
        hours:
          type: array
          items:
            type: integer
            format: int32
        minutes:
          type: array
          items:
            type: integer
            format: int32
        weekDays:
          type: array
          items:
            type: string
            enum: [Sunday, Monday, Tuesday, Wednesday, Thursday, Friday, Saturday]
        monthDays:
          type: array
          items:
            type: integer
            format: int32
    ClassificationRule:
      type: object
      description: A classification rule definition
      properties:
        id:
          type: string
          readOnly: true
        name:
          type: string
        kind:
          type: string
          enum: [Custom, System]
        properties:
          type: object
          properties:
            description:
              type: string
            classificationName:
              type: string
            ruleStatus:
              type: string
              enum: [Enabled, Disabled]
            createdAt:
              type: string
              format: date-time
            lastModifiedAt:
              type: string
              format: date-time
            version:
              type: integer
              format: int32
            dataPatterns:
              type: array
              items:
                $ref: '#/components/schemas/ClassificationRulePattern'
            columnPatterns:
              type: array
              items:
                $ref: '#/components/schemas/ClassificationRulePattern'
    ClassificationRuleList:
      type: object
      properties:
        value:
          type: array
          items:
            $ref: '#/components/schemas/ClassificationRule'
        nextLink:
          type: string
        count:
          type: integer
          format: int64
    ClassificationRulePattern:
      type: object
      properties:
        kind:
          type: string
          enum: [Regex]
        pattern:
          type: string
    ScanRuleset:
      type: object
      description: A scan ruleset configuration
      properties:
        id:
          type: string
          readOnly: true
        name:
          type: string
        kind:
          type: string
        properties:
          type: object
          properties:
            description:
              type: string
            includedCustomClassificationRuleNames:
              type: array
              items:
                type: string
            createdAt:
              type: string
              format: date-time
            lastModifiedAt:
              type: string
              format: date-time
    ScanRulesetList:
      type: object
      properties:
        value:
          type: array
          items:
            $ref: '#/components/schemas/ScanRuleset'
        

# --- truncated at 32 KB (32 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/microsoft-purview/refs/heads/main/openapi/microsoft-purview-scanning-openapi.yml