openapi: 3.0.0
info:
version: 2017-07-25
x-release: v4
title: AWS Glue DataBrew Datasets API
description: Glue DataBrew is a visual, cloud-scale data-preparation service. DataBrew simplifies data preparation tasks, targeting data issues that are hard to spot and time-consuming to fix. DataBrew empowers users of all technical levels to visualize the data and perform one-click data transformations, with no coding required.
x-logo:
url: https://api.apis.guru/v2/cache/logo/https_twitter.com_awscloud_profile_image.png
backgroundColor: '#FFFFFF'
termsOfService: https://aws.amazon.com/service-terms/
contact:
name: Mike Ralphson
email: mike.ralphson@gmail.com
url: https://github.com/mermade/aws2openapi
x-twitter: PermittedSoc
license:
name: Apache 2.0 License
url: http://www.apache.org/licenses/
x-providerName: amazonaws.com
x-serviceName: databrew
x-aws-signingName: databrew
x-origin:
- contentType: application/json
url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/databrew-2017-07-25.normal.json
converter:
url: https://github.com/mermade/aws2openapi
version: 1.0.0
x-apisguru-driver: external
x-apiClientRegistration:
url: https://portal.aws.amazon.com/gp/aws/developer/registration/index.html?nc2=h_ct
x-apisguru-categories:
- cloud
x-preferred: true
servers:
- url: http://databrew.{region}.amazonaws.com
variables:
region:
description: The AWS region
enum:
- us-east-1
- us-east-2
- us-west-1
- us-west-2
- us-gov-west-1
- us-gov-east-1
- ca-central-1
- eu-north-1
- eu-west-1
- eu-west-2
- eu-west-3
- eu-central-1
- eu-south-1
- af-south-1
- ap-northeast-1
- ap-northeast-2
- ap-northeast-3
- ap-southeast-1
- ap-southeast-2
- ap-east-1
- ap-south-1
- sa-east-1
- me-south-1
default: us-east-1
description: The AWS Glue DataBrew multi-region endpoint
- url: https://databrew.{region}.amazonaws.com
variables:
region:
description: The AWS region
enum:
- us-east-1
- us-east-2
- us-west-1
- us-west-2
- us-gov-west-1
- us-gov-east-1
- ca-central-1
- eu-north-1
- eu-west-1
- eu-west-2
- eu-west-3
- eu-central-1
- eu-south-1
- af-south-1
- ap-northeast-1
- ap-northeast-2
- ap-northeast-3
- ap-southeast-1
- ap-southeast-2
- ap-east-1
- ap-south-1
- sa-east-1
- me-south-1
default: us-east-1
description: The AWS Glue DataBrew multi-region endpoint
- url: http://databrew.{region}.amazonaws.com.cn
variables:
region:
description: The AWS region
enum:
- cn-north-1
- cn-northwest-1
default: cn-north-1
description: The AWS Glue DataBrew endpoint for China (Beijing) and China (Ningxia)
- url: https://databrew.{region}.amazonaws.com.cn
variables:
region:
description: The AWS region
enum:
- cn-north-1
- cn-northwest-1
default: cn-north-1
description: The AWS Glue DataBrew endpoint for China (Beijing) and China (Ningxia)
security:
- hmac: []
tags:
- name: Datasets
paths:
/datasets:
parameters:
- $ref: '#/components/parameters/X-Amz-Content-Sha256'
- $ref: '#/components/parameters/X-Amz-Date'
- $ref: '#/components/parameters/X-Amz-Algorithm'
- $ref: '#/components/parameters/X-Amz-Credential'
- $ref: '#/components/parameters/X-Amz-Security-Token'
- $ref: '#/components/parameters/X-Amz-Signature'
- $ref: '#/components/parameters/X-Amz-SignedHeaders'
post:
operationId: CreateDataset
description: Creates a new DataBrew dataset.
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/CreateDatasetResponse'
examples:
CreateDataset200Example:
summary: Default CreateDataset 200 response
x-microcks-default: true
value:
status: SUCCEEDED
'480':
description: AccessDeniedException
content:
application/json:
schema:
$ref: '#/components/schemas/AccessDeniedException'
examples:
CreateDataset480Example:
summary: Default CreateDataset 480 response
x-microcks-default: true
value:
status: SUCCEEDED
'481':
description: ConflictException
content:
application/json:
schema:
$ref: '#/components/schemas/ConflictException'
examples:
CreateDataset481Example:
summary: Default CreateDataset 481 response
x-microcks-default: true
value:
status: SUCCEEDED
'482':
description: ServiceQuotaExceededException
content:
application/json:
schema:
$ref: '#/components/schemas/ServiceQuotaExceededException'
examples:
CreateDataset482Example:
summary: Default CreateDataset 482 response
x-microcks-default: true
value:
status: SUCCEEDED
'483':
description: ValidationException
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationException'
examples:
CreateDataset483Example:
summary: Default CreateDataset 483 response
x-microcks-default: true
value:
status: SUCCEEDED
parameters: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- Name
- Input
properties:
Name:
description: The name of the dataset to be created. Valid characters are alphanumeric (A-Z, a-z, 0-9), hyphen (-), period (.), and space.
type: string
minLength: 1
maxLength: 255
Format:
description: The file format of a dataset that is created from an Amazon S3 file or folder.
type: string
enum:
- CSV
- JSON
- PARQUET
- EXCEL
- ORC
FormatOptions:
description: Represents a set of options that define the structure of either comma-separated value (CSV), Excel, or JSON input.
type: object
properties:
Json:
allOf:
- $ref: '#/components/schemas/JsonOptions'
- description: Options that define how JSON input is to be interpreted by DataBrew.
Excel:
allOf:
- $ref: '#/components/schemas/ExcelOptions'
- description: Options that define how Excel input is to be interpreted by DataBrew.
Csv:
allOf:
- $ref: '#/components/schemas/CsvOptions'
- description: Options that define how CSV input is to be interpreted by DataBrew.
Input:
description: Represents information on how DataBrew can find data, in either the Glue Data Catalog or Amazon S3.
type: object
properties:
S3InputDefinition:
allOf:
- $ref: '#/components/schemas/S3Location'
- description: The Amazon S3 location where the data is stored.
DataCatalogInputDefinition:
allOf:
- $ref: '#/components/schemas/DataCatalogInputDefinition'
- description: The Glue Data Catalog parameters for the data.
DatabaseInputDefinition:
allOf:
- $ref: '#/components/schemas/DatabaseInputDefinition'
- description: Connection information for dataset input files stored in a database.
Metadata:
allOf:
- $ref: '#/components/schemas/Metadata'
- description: Contains additional resource information needed for specific datasets.
PathOptions:
description: Represents a set of options that define how DataBrew selects files for a given Amazon S3 path in a dataset.
type: object
properties:
LastModifiedDateCondition:
allOf:
- $ref: '#/components/schemas/FilterExpression'
- description: If provided, this structure defines a date range for matching Amazon S3 objects based on their LastModifiedDate attribute in Amazon S3.
FilesLimit:
allOf:
- $ref: '#/components/schemas/FilesLimit'
- description: If provided, this structure imposes a limit on a number of files that should be selected.
Parameters:
allOf:
- $ref: '#/components/schemas/PathParametersMap'
- description: A structure that maps names of parameters used in the Amazon S3 path of a dataset to their definitions.
Tags:
description: Metadata tags to apply to this dataset.
type: object
minProperties: 1
maxProperties: 200
additionalProperties:
$ref: '#/components/schemas/TagValue'
summary: Amazon Glue DataBrew Create Dataset
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
tags:
- Datasets
get:
operationId: ListDatasets
description: Lists all of the DataBrew datasets.
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetsResponse'
examples:
ListDatasets200Example:
summary: Default ListDatasets 200 response
x-microcks-default: true
value:
status: SUCCEEDED
'480':
description: ValidationException
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationException'
examples:
ListDatasets480Example:
summary: Default ListDatasets 480 response
x-microcks-default: true
value:
status: SUCCEEDED
parameters:
- name: maxResults
in: query
required: false
description: 'The maximum number of results to return in this request. '
schema:
type: integer
minimum: 1
maximum: 100
- name: nextToken
in: query
required: false
description: The token returned by a previous call to retrieve the next set of results.
schema:
type: string
minLength: 1
maxLength: 2000
- name: MaxResults
in: query
schema:
type: string
description: Pagination limit
required: false
- name: NextToken
in: query
schema:
type: string
description: Pagination token
required: false
summary: Amazon Glue DataBrew List Datasets
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
tags:
- Datasets
/datasets/{name}:
parameters:
- $ref: '#/components/parameters/X-Amz-Content-Sha256'
- $ref: '#/components/parameters/X-Amz-Date'
- $ref: '#/components/parameters/X-Amz-Algorithm'
- $ref: '#/components/parameters/X-Amz-Credential'
- $ref: '#/components/parameters/X-Amz-Security-Token'
- $ref: '#/components/parameters/X-Amz-Signature'
- $ref: '#/components/parameters/X-Amz-SignedHeaders'
delete:
operationId: DeleteDataset
description: Deletes a dataset from DataBrew.
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/DeleteDatasetResponse'
examples:
DeleteDataset200Example:
summary: Default DeleteDataset 200 response
x-microcks-default: true
value:
status: SUCCEEDED
'480':
description: ConflictException
content:
application/json:
schema:
$ref: '#/components/schemas/ConflictException'
examples:
DeleteDataset480Example:
summary: Default DeleteDataset 480 response
x-microcks-default: true
value:
status: SUCCEEDED
'481':
description: ResourceNotFoundException
content:
application/json:
schema:
$ref: '#/components/schemas/ResourceNotFoundException'
examples:
DeleteDataset481Example:
summary: Default DeleteDataset 481 response
x-microcks-default: true
value:
status: SUCCEEDED
'482':
description: ValidationException
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationException'
examples:
DeleteDataset482Example:
summary: Default DeleteDataset 482 response
x-microcks-default: true
value:
status: SUCCEEDED
parameters:
- name: name
in: path
required: true
description: The name of the dataset to be deleted.
schema:
type: string
minLength: 1
maxLength: 255
summary: Amazon Glue DataBrew Delete Dataset
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
tags:
- Datasets
get:
operationId: DescribeDataset
description: Returns the definition of a specific DataBrew dataset.
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/DescribeDatasetResponse'
examples:
DescribeDataset200Example:
summary: Default DescribeDataset 200 response
x-microcks-default: true
value:
status: SUCCEEDED
'480':
description: ResourceNotFoundException
content:
application/json:
schema:
$ref: '#/components/schemas/ResourceNotFoundException'
examples:
DescribeDataset480Example:
summary: Default DescribeDataset 480 response
x-microcks-default: true
value:
status: SUCCEEDED
'481':
description: ValidationException
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationException'
examples:
DescribeDataset481Example:
summary: Default DescribeDataset 481 response
x-microcks-default: true
value:
status: SUCCEEDED
parameters:
- name: name
in: path
required: true
description: The name of the dataset to be described.
schema:
type: string
minLength: 1
maxLength: 255
summary: Amazon Glue DataBrew Describe Dataset
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
tags:
- Datasets
put:
operationId: UpdateDataset
description: Modifies the definition of an existing DataBrew dataset.
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/UpdateDatasetResponse'
examples:
UpdateDataset200Example:
summary: Default UpdateDataset 200 response
x-microcks-default: true
value:
status: SUCCEEDED
'480':
description: AccessDeniedException
content:
application/json:
schema:
$ref: '#/components/schemas/AccessDeniedException'
examples:
UpdateDataset480Example:
summary: Default UpdateDataset 480 response
x-microcks-default: true
value:
status: SUCCEEDED
'481':
description: ResourceNotFoundException
content:
application/json:
schema:
$ref: '#/components/schemas/ResourceNotFoundException'
examples:
UpdateDataset481Example:
summary: Default UpdateDataset 481 response
x-microcks-default: true
value:
status: SUCCEEDED
'482':
description: ValidationException
content:
application/json:
schema:
$ref: '#/components/schemas/ValidationException'
examples:
UpdateDataset482Example:
summary: Default UpdateDataset 482 response
x-microcks-default: true
value:
status: SUCCEEDED
parameters:
- name: name
in: path
required: true
description: The name of the dataset to be updated.
schema:
type: string
minLength: 1
maxLength: 255
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- Input
properties:
Format:
description: The file format of a dataset that is created from an Amazon S3 file or folder.
type: string
enum:
- CSV
- JSON
- PARQUET
- EXCEL
- ORC
FormatOptions:
description: Represents a set of options that define the structure of either comma-separated value (CSV), Excel, or JSON input.
type: object
properties:
Json:
allOf:
- $ref: '#/components/schemas/JsonOptions'
- description: Options that define how JSON input is to be interpreted by DataBrew.
Excel:
allOf:
- $ref: '#/components/schemas/ExcelOptions'
- description: Options that define how Excel input is to be interpreted by DataBrew.
Csv:
allOf:
- $ref: '#/components/schemas/CsvOptions'
- description: Options that define how CSV input is to be interpreted by DataBrew.
Input:
description: Represents information on how DataBrew can find data, in either the Glue Data Catalog or Amazon S3.
type: object
properties:
S3InputDefinition:
allOf:
- $ref: '#/components/schemas/S3Location'
- description: The Amazon S3 location where the data is stored.
DataCatalogInputDefinition:
allOf:
- $ref: '#/components/schemas/DataCatalogInputDefinition'
- description: The Glue Data Catalog parameters for the data.
DatabaseInputDefinition:
allOf:
- $ref: '#/components/schemas/DatabaseInputDefinition'
- description: Connection information for dataset input files stored in a database.
Metadata:
allOf:
- $ref: '#/components/schemas/Metadata'
- description: Contains additional resource information needed for specific datasets.
PathOptions:
description: Represents a set of options that define how DataBrew selects files for a given Amazon S3 path in a dataset.
type: object
properties:
LastModifiedDateCondition:
allOf:
- $ref: '#/components/schemas/FilterExpression'
- description: If provided, this structure defines a date range for matching Amazon S3 objects based on their LastModifiedDate attribute in Amazon S3.
FilesLimit:
allOf:
- $ref: '#/components/schemas/FilesLimit'
- description: If provided, this structure imposes a limit on a number of files that should be selected.
Parameters:
allOf:
- $ref: '#/components/schemas/PathParametersMap'
- description: A structure that maps names of parameters used in the Amazon S3 path of a dataset to their definitions.
summary: Amazon Glue DataBrew Update Dataset
x-microcks-operation:
delay: 0
dispatcher: FALLBACK
tags:
- Datasets
components:
schemas:
ValuesMap:
type: object
additionalProperties:
$ref: '#/components/schemas/ConditionValue'
DatetimeFormat:
type: string
minLength: 2
maxLength: 100
FormatOptions:
type: object
properties:
Json:
allOf:
- $ref: '#/components/schemas/JsonOptions'
- description: Options that define how JSON input is to be interpreted by DataBrew.
Excel:
allOf:
- $ref: '#/components/schemas/ExcelOptions'
- description: Options that define how Excel input is to be interpreted by DataBrew.
Csv:
allOf:
- $ref: '#/components/schemas/CsvOptions'
- description: Options that define how CSV input is to be interpreted by DataBrew.
description: Represents a set of options that define the structure of either comma-separated value (CSV), Excel, or JSON input.
FilterExpression:
type: object
required:
- Expression
- ValuesMap
properties:
Expression:
allOf:
- $ref: '#/components/schemas/Expression'
- description: The expression which includes condition names followed by substitution variables, possibly grouped and combined with other conditions. For example, "(starts_with :prefix1 or starts_with :prefix2) and (ends_with :suffix1 or ends_with :suffix2)". Substitution variables should start with ':' symbol.
ValuesMap:
allOf:
- $ref: '#/components/schemas/ValuesMap'
- description: The map of substitution variable names to their values used in this filter expression.
description: 'Represents a structure for defining parameter conditions. Supported conditions are described here: Supported conditions for dynamic datasets in the Glue DataBrew Developer Guide.'
InputFormat:
type: string
enum:
- CSV
- JSON
- PARQUET
- EXCEL
- ORC
Metadata:
type: object
properties:
SourceArn:
allOf:
- $ref: '#/components/schemas/Arn'
- description: The Amazon Resource Name (ARN) associated with the dataset. Currently, DataBrew only supports ARNs from Amazon AppFlow.
description: Contains additional resource information needed for specific datasets.
Delimiter:
type: string
minLength: 1
maxLength: 1
TagValue:
type: string
maxLength: 256
DatabaseTableName:
type: string
minLength: 1
maxLength: 255
SheetIndex:
type: integer
minimum: 0
maximum: 200
Expression:
type: string
pattern: ^[<>0-9A-Za-z_.,:)(!= ]+$
minLength: 4
maxLength: 1024
ParameterType:
type: string
enum:
- Datetime
- Number
- String
LocaleCode:
type: string
pattern: ^[A-Za-z0-9_\.#@\-]+$
minLength: 2
maxLength: 100
BucketOwner:
type: string
pattern: ^[0-9]{12}$
minLength: 12
maxLength: 12
AccountId:
type: string
maxLength: 255
UpdateDatasetResponse:
type: object
required:
- Name
properties:
Name:
allOf:
- $ref: '#/components/schemas/DatasetName'
- description: The name of the dataset that you updated.
CreateDatasetResponse:
type: object
required:
- Name
properties:
Name:
allOf:
- $ref: '#/components/schemas/DatasetName'
- description: The name of the dataset that you created.
SheetNameList:
type: array
items:
$ref: '#/components/schemas/SheetName'
minItems: 1
maxItems: 1
ConflictException: {}
HeaderRow:
type: boolean
DatetimeOptions:
type: object
required:
- Format
properties:
Format:
allOf:
- $ref: '#/components/schemas/DatetimeFormat'
- description: Required option, that defines the datetime format used for a date parameter in the Amazon S3 path. Should use only supported datetime specifiers and separation characters, all literal a-z or A-Z characters should be escaped with single quotes. E.g. "MM.dd.yyyy-'at'-HH:mm".
TimezoneOffset:
allOf:
- $ref: '#/components/schemas/TimezoneOffset'
- description: Optional value for a timezone offset of the datetime parameter value in the Amazon S3 path. Shouldn't be used if Format for this parameter includes timezone fields. If no offset specified, UTC is assumed.
LocaleCode:
allOf:
- $ref: '#/components/schemas/LocaleCode'
- description: Optional value for a non-US locale code, needed for correct interpretation of some date formats.
description: Represents additional options for correct interpretation of datetime parameters used in the Amazon S3 path of a dataset.
S3Location:
type: object
required:
- Bucket
properties:
Bucket:
allOf:
- $ref: '#/components/schemas/Bucket'
- description: The Amazon S3 bucket name.
Key:
allOf:
- $ref: '#/components/schemas/Key'
- description: The unique name of the object in the bucket.
BucketOwner:
allOf:
- $ref: '#/components/schemas/BucketOwner'
- description: The Amazon Web Services account ID of the bucket owner.
description: Represents an Amazon S3 location (bucket name, bucket owner, and object key) where DataBrew can read input data, or write output from a job.
Bucket:
type: string
minLength: 3
maxLength: 63
ServiceQuotaExceededException: {}
FilesLimit:
type: object
required:
- MaxFiles
properties:
MaxFiles:
allOf:
- $ref: '#/components/schemas/MaxFiles'
- description: The number of Amazon S3 files to select.
OrderedBy:
allOf:
- $ref: '#/components/schemas/OrderedBy'
- description: A criteria to use for Amazon S3 files sorting before their selection. By default uses LAST_MODIFIED_DATE as a sorting criteria. Currently it's the only allowed value.
Order:
allOf:
- $ref: '#/components/schemas/Order'
- description: A criteria to use for Amazon S3 files sorting before their selection. By default uses DESCENDING order, i.e. most recent files are selected first. Another possible value is ASCENDING.
description: Represents a limit imposed on number of Amazon S3 files that should be selected for a dataset from a connected Amazon S3 path.
PathParametersMap:
type: object
description: A structure that map names of parameters used in the Amazon S3 path of a dataset to their definitions. A definition includes parameter type and conditions.
minProperties: 1
maxProperties: 10
additionalProperties:
$ref: '#/components/schemas/DatasetParameter'
PathParameterName:
type: string
minLength: 1
maxLength: 255
Key:
type: string
minLength: 1
maxLength: 1280
PathOptions:
type: object
properties:
LastModifiedDateCondition:
allOf:
- $ref: '#/components/schemas/FilterExpression'
- description: If provided, this structure defines a date range for matching Amazon S3 objects based on their LastModifiedDate attribute in Amazon S3.
FilesLimit:
allOf:
- $ref: '#/components/schemas/FilesLimit'
- description: If provided, this structure imposes a limit on a number of files that should be selected.
Parameters:
allOf:
- $ref: '#/components/schemas/PathParametersMap'
- description: A structure that maps names of parameters used in the Amazon S3 path of a dataset to their definitions.
description: Represents a set of options that define how DataBrew selects files for a given Amazon S3 path in a dataset.
DatasetName:
type: string
minLength: 1
maxLength: 255
ConditionValue:
type: string
maxLength: 1024
TimezoneOffset:
type: string
pattern: ^(Z|[-+](\d|\d{2}|\d{2}:?\d{2}))$
minLength: 1
maxLength: 6
SheetIndexList:
type: array
items:
$ref: '#/components/schemas/SheetIndex'
minItems: 1
maxItems: 1
DeleteDatasetResponse:
type: object
required:
- Name
properties:
Name:
allOf:
- $ref: '#/components/schemas/DatasetName'
- description: The name of the dataset that you deleted.
Input:
type: object
properties:
S3InputDefinition:
allOf:
- $ref: '#/components/schemas/S3Location'
- description: The Amazon S3 location where the data is stored.
DataCatalogInputDefinition:
allOf:
- $ref: '#/components/schemas/DataCatalogInputDefinition'
- description: The Glue Data Catalog parameters for the data.
DatabaseInputDefinition:
allOf:
- $ref: '#/components/schemas/DatabaseInputDefinition'
- description: Connection information for dataset input files stored in a database.
Metadata:
allOf:
- $ref: '#/components/schemas/Metadata'
- description: Contains additional resource information needed for specific datasets.
description: Represents information on how DataBrew can find data, in either the Glue Data Catalog or Amazon S3.
Date:
type: string
format: date-time
Order:
type: string
enum:
- DESCENDING
- ASCENDING
TableName:
type: string
minLength: 1
maxLength: 255
JsonOptions:
type: object
properties:
MultiLine:
allOf:
- $ref: '#/components/schemas/MultiLine'
- description: A value that specifies whether JSON input contains embedded new line characters.
description: Represents the JSON-specific options that define how input is to be interpreted by Glue DataBrew.
CreateColumn:
type: boolean
Dataset:
type: object
required:
- Name
- Input
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.
description: Represents a dataset that can be processed by DataBrew.
ResourceNotFoundException: {}
DatabaseInputDefinition:
type: object
required:
- GlueConnectionName
properties:
GlueConnectionName:
allOf:
- $ref: '#/components/schemas/GlueConnectionName'
- description: The Glue Connection that stores the connection information for the target database.
DatabaseTableName:
allOf:
- $ref: '#/components/schemas/DatabaseTableName'
- description: The table within the target database.
TempDirectory:
$ref: '#/components/schemas/S3Location'
QueryString:
allOf:
- $ref: '#/components/schemas/QueryString'
- description: Custom SQL to run against the provided Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
description: Connection information for dataset input files stored in a database.
QueryString:
type: string
minLength: 1
maxLength: 10000
AccessDeniedException: {}
MultiLine:
type: boolean
CreatedBy:
type: string
LastModifiedBy:
type: string
MaxFiles:
type: integer
minimum: 1
OrderedBy:
type: string
enum:
- LAST_MODIFIED_DATE
ListDatasetsResponse:
type: object
required:
- Datasets
properties:
Datasets:
allOf:
- $ref: '#/components/schemas/DatasetList'
- description: A list of datasets that are defined.
NextToken:
allOf:
- $ref: '#/components/schemas/NextToken'
- description: A token that you can use in a subsequent call to retrieve the next set of results.
CsvOptions:
type: object
properties:
Delimiter:
allOf:
- $ref: '#/components/schemas/Delimiter'
- description: A single character that specifies the delimiter being used in the CSV file.
HeaderRow:
allOf:
- $ref: '#/components/schemas/HeaderRow'
- description: A variable that specifies whether the first row in the file is parsed as the header. If this value is false, column names are auto-generated.
description: Represents a set of options that define how DataBrew will read a comma-separated value (CSV) file when creating a dataset from that file.
Arn:
type: string
minLength: 20
maxLength: 2048
NextToken:
type: string
minLength: 1
maxLength: 2000
DatabaseName:
type: string
minLength: 1
maxLength: 255
DatasetList:
type: array
items:
$ref: '#/components/schemas/Dataset'
DescribeDatasetResponse:
type: object
required:
- Name
- Input
properties:
CreatedBy:
allOf:
- $ref: '#/components/schemas/CreatedBy'
- description: The identifier (user name) 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 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:
$ref: '#/components/schemas/FormatOptions'
Input:
$ref: '#/components/schemas/Input'
LastModifiedDate:
allOf:
- $ref: '#/components/schemas/Date'
- description: The date and time that the dataset was last modified.
LastModifiedBy:
allOf:
- $ref: '#/components/schemas/LastModifiedBy'
- description: The identifier (user name) of the user who last modified the dataset.
Source:
allOf:
- $ref: '#/components/schemas/Source'
- description: The location of the data for this dataset, 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 associated with this dataset.
ResourceArn:
allOf:
- $ref: '#/components/schemas/Arn'
- description: The Amazon Resource Name (ARN) of the dataset.
DataCatalogInputDefinition:
type: object
required:
- DatabaseName
- TableName
properties:
CatalogId:
allOf:
- $ref: '#/components/schemas/CatalogId'
- description: The unique identifier of the Amazon Web Services account that holds the Data Catalog that stores the data.
DatabaseName:
allOf:
- $ref: '#/components/schemas/DatabaseName'
- description: The name of a database in the Data Catalog.
TableName:
allOf:
- $ref: '#/components/schemas/TableName'
- description: The name of a database table in the Data Catalog. This table corresponds to a DataBrew dataset.
TempDirectory:
allOf:
- $ref: '#/components/schemas/S3Location'
- description: Represents an Amazon location where DataBrew can store intermediate results.
description: 'Represents how metadata stored in the Glue Data Catalog is defined in a DataBrew dataset. '
Source:
type: string
enum:
- S3
- DATA-CATALOG
- DATABASE
ValidationException: {}
DatasetParameter:
type: object
required:
- Name
- Type
properties:
Name:
allOf:
- $ref: '#/components/schemas/PathParameterName'
- description: The name of the parameter that is used in the dataset's Amazon S3 path.
Type:
allOf:
- $ref: '#/components/schemas/ParameterType'
- description: The type of the dataset parameter, can be one of a 'String', 'Number' or 'Datetime'.
DatetimeOptions:
allOf:
- $ref: '#/components/schemas/DatetimeOptions'
- description: Additional parameter options such as a format and a timezone. Required for datetime parameters.
CreateColumn:
allOf:
- $ref: '#/components/schemas/CreateColumn'
- description: Optional boolean value that defines whether the captured value of this parameter should be used to create a new column in a dataset.
Filter:
allOf:
- $ref: '#/components/schemas/FilterExpression'
- description: The optional filter expression structure to apply additional matching criteria to the parameter.
description: Represents a dataset parameter that defines type and conditions for a parameter in the Amazon S3 path of the dataset.
GlueConnectionName:
type: string
minLength: 1
maxLength: 255
ExcelOptions:
type: object
properties:
SheetNames:
allOf:
- $ref: '#/components/schemas/SheetNameList'
- description: One or more named sheets in the Excel file that will be included in the dataset.
SheetIndexes:
allOf:
- $ref: '#/components/schemas/SheetIndexList'
- description: One or more sheet numbers in the Excel file that will be included in the dataset.
HeaderRow:
allOf:
- $ref: '#/components/schemas/HeaderRow'
- description: A variable that specifies whether the first row in the file is parsed as the header. If this value is false, column names are auto-generated.
description: Represents a set of options that define how DataBrew will interpret a Microsoft Excel file when creating a dataset from that file.
CatalogId:
type: string
minLength: 1
maxLength: 255
TagMap:
type: object
minProperties: 1
maxProperties: 200
additionalProperties:
$ref: '#/components/schemas/TagValue'
SheetName:
type: string
minLength: 1
maxLength: 31
parameters:
X-Amz-Credential:
name: X-Amz-Credential
in: header
schema:
type: string
required: false
X-Amz-Algorithm:
name: X-Amz-Algorithm
in: header
schema:
type: string
required: false
X-Amz-Content-Sha256:
name: X-Amz-Content-Sha256
in: header
schema:
type: string
required: false
X-Amz-Security-Token:
name: X-Amz-Security-Token
in: header
schema:
type: string
required: false
X-Amz-SignedHeaders:
name: X-Amz-SignedHeaders
in: header
schema:
type: string
required: false
X-Amz-Date:
name: X-Amz-Date
in: header
schema:
type: string
required: false
X-Amz-Signature:
name: X-Amz-Signature
in: header
schema:
type: string
required: false
securitySchemes:
hmac:
type: apiKey
name: Authorization
in: header
description: Amazon Signature authorization v4
x-amazon-apigateway-authtype: awsSigv4
externalDocs:
description: Amazon Web Services documentation
url: https://docs.aws.amazon.com/databrew/
x-hasEquivalentPaths: true