Amazon Glue DataBrew · JSON Structure

Glue Databrew Job Structure

Represents all of the attributes of a DataBrew job.

Type: object Properties: 24 Required: 1
Data AnalyticsData PreparationETLMachine Learning

Job is a JSON Structure definition published by Amazon Glue DataBrew, describing 24 properties, of which 1 is required. It conforms to the https://json-structure.org/meta/core/v0/# meta-schema.

Properties

AccountId CreatedBy CreateDate DatasetName EncryptionKeyArn EncryptionMode Name Type LastModifiedBy LastModifiedDate LogSubscription MaxCapacity MaxRetries Outputs DataCatalogOutputs DatabaseOutputs ProjectName RecipeReference ResourceArn RoleArn Timeout Tags JobSample ValidationConfigurations

Meta-schema: https://json-structure.org/meta/core/v0/#

JSON Structure

Raw ↑
{
  "$schema": "https://json-structure.org/meta/core/v0/#",
  "$id": "https://raw.githubusercontent.com/api-evangelist/amazon-glue-databrew/refs/heads/main/json-structure/glue-databrew-job-structure.json",
  "name": "Job",
  "description": "Represents all of the attributes of a DataBrew job.",
  "type": "object",
  "properties": {
    "AccountId": {
      "allOf": [
        {
          "$ref": "#/components/schemas/AccountId"
        },
        {
          "description": "The ID of the Amazon Web Services account that owns the job."
        }
      ]
    },
    "CreatedBy": {
      "allOf": [
        {
          "$ref": "#/components/schemas/CreatedBy"
        },
        {
          "description": "The Amazon Resource Name (ARN) of the user who created the job."
        }
      ]
    },
    "CreateDate": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Date"
        },
        {
          "description": "The date and time that the job was created."
        }
      ]
    },
    "DatasetName": {
      "allOf": [
        {
          "$ref": "#/components/schemas/DatasetName"
        },
        {
          "description": "A dataset that the job is to process."
        }
      ]
    },
    "EncryptionKeyArn": {
      "allOf": [
        {
          "$ref": "#/components/schemas/EncryptionKeyArn"
        },
        {
          "description": "The Amazon Resource Name (ARN) of an encryption key that is used to protect the job output. For more information, see <a href=\"https://docs.aws.amazon.com/databrew/latest/dg/encryption-security-configuration.html\">Encrypting data written by DataBrew jobs</a> "
        }
      ]
    },
    "EncryptionMode": {
      "allOf": [
        {
          "$ref": "#/components/schemas/EncryptionMode"
        },
        {
          "description": "<p>The encryption mode for the job, which can be one of the following:</p> <ul> <li> <p> <code>SSE-KMS</code> - Server-side encryption with keys managed by KMS.</p> </li> <li> <p> <code>SSE-S3</code> - Server-side encryption with keys managed by Amazon S3.</p> </li> </ul>"
        }
      ]
    },
    "Name": {
      "allOf": [
        {
          "$ref": "#/components/schemas/JobName"
        },
        {
          "description": "The unique name of the job."
        }
      ]
    },
    "Type": {
      "allOf": [
        {
          "$ref": "#/components/schemas/JobType"
        },
        {
          "description": "<p>The job type of the job, which must be one of the following:</p> <ul> <li> <p> <code>PROFILE</code> - A job to analyze a dataset, to determine its size, data types, data distribution, and more.</p> </li> <li> <p> <code>RECIPE</code> - A job to apply one or more transformations to a dataset.</p> </li> </ul>"
        }
      ]
    },
    "LastModifiedBy": {
      "allOf": [
        {
          "$ref": "#/components/schemas/LastModifiedBy"
        },
        {
          "description": "The Amazon Resource Name (ARN) of the user who last modified the job."
        }
      ]
    },
    "LastModifiedDate": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Date"
        },
        {
          "description": "The modification date and time of the job."
        }
      ]
    },
    "LogSubscription": {
      "allOf": [
        {
          "$ref": "#/components/schemas/LogSubscription"
        },
        {
          "description": "The current status of Amazon CloudWatch logging for the job."
        }
      ]
    },
    "MaxCapacity": {
      "allOf": [
        {
          "$ref": "#/components/schemas/MaxCapacity"
        },
        {
          "description": "The maximum number of nodes that can be consumed when the job processes data."
        }
      ]
    },
    "MaxRetries": {
      "allOf": [
        {
          "$ref": "#/components/schemas/MaxRetries"
        },
        {
          "description": "The maximum number of times to retry the job after a job run fails."
        }
      ]
    },
    "Outputs": {
      "allOf": [
        {
          "$ref": "#/components/schemas/OutputList"
        },
        {
          "description": "One or more artifacts that represent output from running the job."
        }
      ]
    },
    "DataCatalogOutputs": {
      "allOf": [
        {
          "$ref": "#/components/schemas/DataCatalogOutputList"
        },
        {
          "description": "One or more artifacts that represent the Glue Data Catalog output from running the job."
        }
      ]
    },
    "DatabaseOutputs": {
      "allOf": [
        {
          "$ref": "#/components/schemas/DatabaseOutputList"
        },
        {
          "description": "Represents a list of JDBC database output objects which defines the output destination for a DataBrew recipe job to write into."
        }
      ]
    },
    "ProjectName": {
      "allOf": [
        {
          "$ref": "#/components/schemas/ProjectName"
        },
        {
          "description": "The name of the project that the job is associated with."
        }
      ]
    },
    "RecipeReference": {
      "allOf": [
        {
          "$ref": "#/components/schemas/RecipeReference"
        },
        {
          "description": "A set of steps that the job runs."
        }
      ]
    },
    "ResourceArn": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Arn"
        },
        {
          "description": "The unique Amazon Resource Name (ARN) for the job."
        }
      ]
    },
    "RoleArn": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Arn"
        },
        {
          "description": "The Amazon Resource Name (ARN) of the role to be assumed for this job."
        }
      ]
    },
    "Timeout": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Timeout"
        },
        {
          "description": "The job's timeout in minutes. A job that attempts to run longer than this timeout period ends with a status of <code>TIMEOUT</code>."
        }
      ]
    },
    "Tags": {
      "allOf": [
        {
          "$ref": "#/components/schemas/TagMap"
        },
        {
          "description": "Metadata tags that have been applied to the job."
        }
      ]
    },
    "JobSample": {
      "allOf": [
        {
          "$ref": "#/components/schemas/JobSample"
        },
        {
          "description": "A sample configuration for profile jobs only, which determines the number of rows on which the profile job is run. If a <code>JobSample</code> value isn't provided, the default value is used. The default value is CUSTOM_ROWS for the mode parameter and 20,000 for the size parameter."
        }
      ]
    },
    "ValidationConfigurations": {
      "allOf": [
        {
          "$ref": "#/components/schemas/ValidationConfigurationList"
        },
        {
          "description": "List of validation configurations that are applied to the profile job."
        }
      ]
    }
  },
  "required": [
    "Name"
  ]
}