Dataset

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/amazon-glue-databrew/refs/heads/main/json-schema/glue-databrew-dataset-schema.json",
  "title": "Dataset",
  "description": "Represents a dataset that can be processed by DataBrew.",
  "type": "object",
  "properties": {
    "AccountId": {
      "allOf": [
        {
          "$ref": "#/components/schemas/AccountId"
        },
        {
          "description": "The ID of the Amazon Web Services account that owns the dataset."
        }
      ]
    },
    "CreatedBy": {
      "allOf": [
        {
          "$ref": "#/components/schemas/CreatedBy"
        },
        {
          "description": "The Amazon Resource Name (ARN) of the user who created the dataset."
        }
      ]
    },
    "CreateDate": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Date"
        },
        {
          "description": "The date and time that the dataset was created."
        }
      ]
    },
    "Name": {
      "allOf": [
        {
          "$ref": "#/components/schemas/DatasetName"
        },
        {
          "description": "The unique name of the dataset."
        }
      ]
    },
    "Format": {
      "allOf": [
        {
          "$ref": "#/components/schemas/InputFormat"
        },
        {
          "description": "The file format of a dataset that is created from an Amazon S3 file or folder."
        }
      ]
    },
    "FormatOptions": {
      "allOf": [
        {
          "$ref": "#/components/schemas/FormatOptions"
        },
        {
          "description": "A set of options that define how DataBrew interprets the data in the dataset."
        }
      ]
    },
    "Input": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Input"
        },
        {
          "description": "Information on how DataBrew can find the dataset, in either the Glue Data Catalog or Amazon S3."
        }
      ]
    },
    "LastModifiedDate": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Date"
        },
        {
          "description": "The last modification date and time of the dataset."
        }
      ]
    },
    "LastModifiedBy": {
      "allOf": [
        {
          "$ref": "#/components/schemas/LastModifiedBy"
        },
        {
          "description": "The Amazon Resource Name (ARN) of the user who last modified the dataset."
        }
      ]
    },
    "Source": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Source"
        },
        {
          "description": "The location of the data for the dataset, either Amazon S3 or the Glue Data Catalog."
        }
      ]
    },
    "PathOptions": {
      "allOf": [
        {
          "$ref": "#/components/schemas/PathOptions"
        },
        {
          "description": "A set of options that defines how DataBrew interprets an Amazon S3 path of the dataset."
        }
      ]
    },
    "Tags": {
      "allOf": [
        {
          "$ref": "#/components/schemas/TagMap"
        },
        {
          "description": "Metadata tags that have been applied to the dataset."
        }
      ]
    },
    "ResourceArn": {
      "allOf": [
        {
          "$ref": "#/components/schemas/Arn"
        },
        {
          "description": "The unique Amazon Resource Name (ARN) for the dataset."
        }
      ]
    }
  },
  "required": [
    "Name",
    "Input"
  ]
}