v1

latestOpenAPI 3.1.0Apache 2.02026-07-245981,1853.0 MB
Scan Jobs

Create Scan Job

Use this API to create a new scan job in the specified data source.

post/api/discovery-scan-config/v2/scan-job

Request body

dataSourceIdstring uuid required

Unique identifier of the data source to scan. This data source must exist and be active.

scanProfileIdstring uuid

Optional scan profile ID to use for this scan job. If provided, must match the data source system type. If not provided, the data source's default scan profile will be used.

classificationProfileIdstring uuid

Classification profile ID for the scan job. Used when classification v2 is disabled. Either this or detectorProfileId should be provided for classification scans.

detectorProfileIdstring uuid

Detector profile ID for the scan job. Used when classification v2 is enabled. Either this or classificationProfileId should be provided for classification scans.

Example request

{
  "dataSourceId": "4f162d7c-a563-4bf1-a7c4-b7899f6dcdef",
  "scanProfileId": "ad390cb4-9ce9-4976-8895-66d724493c7b",
  "classificationProfileId": "cd490cb4-9ce9-4976-8895-66d724493c5d",
  "detectorProfileId": "cd490cb4-9ce9-4976-8895-66d724493c5d"
}

Response

Scan job created successfully

namestring

Name of Scan job

sourceSystemIdstring uuid required

Source System ID for Scan job

scannerIdstring uuid required

Scanner ID for Scan Job

status'QUEUED' | 'PENDING' | 'PROCESSING' | 'COMPLETED' | 'ABORTED' | 'STOPPED_AS_LOAD_ABORTED' | 'CANCELLED' | 'CANCELLING' | 'FAILED' | 'PAUSED' | 'PAUSING' | 'RESUMING' required

Scan job scan status

statusMessagestring

Scan job status message

scanLevel'INCREMENTAL_SCAN' | 'FULL_SCAN' | 'SCAN' | 'SOURCING' | 'CATALOG' | 'CATALOG_SCAN' | 'QUERY' | 'FILE_RETRIEVAL' | 'OFFSET_REPORT' | 'CATALOG_POLICY_SCAN' | 'ASSET_DISCOVERY' | 'DATA_ELEMENT_DISCOVERY' | 'POLICY_ORCHESTRATION_APPLY' | 'POLICY_ORCHESTRATION_UNAPPLY' | 'POLICY_ORCHESTRATION_EDIT' | 'POLICY_ORCHESTRATION_DELETE' | 'ROLE_INGESTION' | 'AI_ASSET_DISCOVERY' | 'GUARDRAIL_POLICY_ENFORCEMENT'

Scan Job scan level

isManualboolean
isVoyagerboolean
jobContextobject
expectedRecordCountinteger

Scan Job expected record count

failedRecordCountinteger

Scan Job failed record count

successRecordCountinteger

Scan Job success record count

cancelledRecordCountinteger

Scan Job cancelled record count

scannedMetadataCountinteger

Scan Job scanned metadata count

uploadedMetadataCountinteger

Scan Job uploaded metadata count

failedIngestionCountinteger

Scan Job failed ingestion count

createdDatestring date-time

Scan Job creation date

createdBystring uuid

User who created Scan Job

jobProgressnumber double

Scan Jobs progress

updatedDatestring date-time

Scan Job updated date

updatedBystring uuid

user who last updated scan job

cancelledBystring uuid

user who cancelled scan job

cancelledDatestring date-time

Scan Job cancelled date

pausedBystring uuid

user who paused scan job

pausedDatestring date-time

Scan Job paused date

resumedBystring uuid

user who resumed scan job

resumedDatestring date-time

Scan Job resumed date

classifiedTermsCountinteger

Scan Job classified terms count

ingestionStatus'AWAITING' | 'PUBLISHING' | 'PUBLISHED' | 'NONE'

Scan Job ingestion status

ingestionDatestring date-time

Scan Job ingestion date

ingestedMetadataVolumeinteger

Scan job ingestion metadata volume in bytes

scannedCountstring

Scan Job Scan count

totalContentSizeinteger

Scan Job total content size in bytes

retryAttemptsinteger

Total Retry Attempts for scan job failures

maxRetriesinteger

Max Retries allowed for scan job failures

idleScanDurationinteger

Idle time of scan when Paused (or) during retry

scanDurationinteger

Actual Scan duration

scanStartedDatestring date-time

Actual Scan start date

idstring uuid
manualboolean
voyagerboolean

Example response

{
  "name": "S3-DS-24thMarch",
  "sourceSystemId": "4f162d7c-a563-4bf1-a7c4-b7899f6dcdef",
  "scannerId": "4f162d7c-a563-4bf1-a7c4-b7899f6dcdef",
  "status": "Completed",
  "statusMessage": "status message",
  "scanLevel": "CATALOG_SCAN",
  "expectedRecordCount": 8,
  "successRecordCount": 8,
  "scannedMetadataCount": 38,
  "uploadedMetadataCount": 38,
  "createdDate": "2022-05-24T14:44:02.596+00:00",
  "createdBy": "2ae93388-bef6-4b84-a612-8a4904b78dac",
  "jobProgress": 100,
  "updatedDate": "2022-05-24T14:44:22.294+00:00",
  "updatedBy": "2ae93388-bef6-4b84-a612-8a4904b78dac",
  "cancelledBy": "2ae93388-bef6-4b84-a612-8a4904b78dac",
  "cancelledDate": "2022-05-24T14:44:22.294+00:00",
  "pausedBy": "2ae93388-bef6-4b84-a612-8a4904b78dac",
  "pausedDate": "2022-05-24T14:44:22.294+00:00",
  "resumedBy": "2ae93388-bef6-4b84-a612-8a4904b78dac",
  "resumedDate": "2022-05-24T14:44:22.294+00:00",
  "classifiedTermsCount": 7,
  "ingestionStatus": "PUBLISHED",
  "ingestionDate": "2022-05-24T14:44:33.803+00:00",
  "ingestedMetadataVolume": 37734,
  "totalContentSize": 295454,
  "scanProfile": {
    "id": "4f162d7c-a563-4bf1-a7c4-b7899f6dcdef",
    "name": "My SQL Scan Profile",
    "scanType": "CATALOG",
    "sourceType": "USER_DEFINED",
    "systemName": "MySQL",
    "scanProfileContext": {
      "type": "MySQL",
      "includes": [
        {
          "database": "OT",
          "table": "Employee",
          "columns": "Name"
        }
      ],
      "excludes": [
        {
          "database": "OT",
          "table": "Credential",
          "columns": "Id"
        }
      ],
      "samplingScan": {
        "enableSampling": false
      },
      "tableLimits": {
        "randomize": false,
        "maxCount": 10
      },
      "tableTypes": [
        "TABLE"
      ],
      "databaseLimits": {
        "randomize": false,
        "maxCount": 1
      }
    },
    "systemType": "RELATIONAL_DATABASE",
    "createdDate": "2021-09-11T01:41:50.143+00:00",
    "displayName": "Amazon Redshift"
  },
  "retryAttempts": 1,
  "maxRetries": 3,
  "idleScanDuration": 377342131,
  "scanDuration": 377342131,
  "scanStartedDate": "2022-05-24T14:44:22.294+00:00"
}