openapi: 3.0.0
info:
version: '2017-03-31'
x-release: v4
title: 'AWS Glue #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.GetCrawler API'
description:
Defines the public endpoint for the Glue service.
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: glue x-origin: - contentType: application/json url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/glue-2017-03-31.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://glue.{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 multi-region endpoint - url: https://glue.{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 multi-region endpoint - url: http://glue.{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 endpoint for China (Beijing) and China (Ningxia) - url: https://glue.{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 endpoint for China (Beijing) and China (Ningxia) security: - hmac: [] tags: - name: '#X Amz Target=AWSGlue.GetCrawler' paths: /#X-Amz-Target=AWSGlue.GetCrawler: 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: GetCrawler description: Retrieves metadata for a specified crawler. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/GetCrawlerResponse' examples: GetCrawler200Example: summary: Default GetCrawler 200 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '480': description: EntityNotFoundException content: application/json: schema: $ref: '#/components/schemas/EntityNotFoundException' examples: GetCrawler480Example: summary: Default GetCrawler 480 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '481': description: OperationTimeoutException content: application/json: schema: $ref: '#/components/schemas/OperationTimeoutException' examples: GetCrawler481Example: summary: Default GetCrawler 481 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GetCrawlerRequest' parameters: - name: X-Amz-Target in: header required: true schema: type: string enum: - AWSGlue.GetCrawler summary: Amazon Glue Get Crawler x-microcks-operation: delay: 0 dispatcher: FALLBACK tags: - '#X Amz Target=AWSGlue.GetCrawler' components: schemas: ScheduleState: type: string enum: - SCHEDULED - NOT_SCHEDULED - TRANSITIONING DescriptionString: type: string minLength: 0 maxLength: 2048 x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\r\n\t]*' MongoDBTarget: type: object properties: ConnectionName: allOf: - $ref: '#/components/schemas/ConnectionName' - description: The name of the connection to use to connect to the Amazon DocumentDB or MongoDB target. Path: allOf: - $ref: '#/components/schemas/Path' - description: The path of the Amazon DocumentDB or MongoDB target (database/collection). ScanAll: allOf: - $ref: '#/components/schemas/NullableBoolean' - description:Indicates whether to scan all the records, or to sample rows from the table. Scanning all the records can take a long time when the table is not a high throughput table.
A value of true means to scan all records, while a value of false means to sample the records. If no value is specified, the value defaults to true.
cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).'
State:
allOf:
- $ref: '#/components/schemas/ScheduleState'
- description: The state of the schedule.
description: A scheduling object using a cron statement to schedule an event.
ClassifierNameList:
type: array
items:
$ref: '#/components/schemas/NameString'
Role:
type: string
CrawlerSecurityConfiguration:
type: string
minLength: 0
maxLength: 128
DatabaseName:
type: string
JdbcMetadataEntry:
type: string
enum:
- COMMENTS
- RAWTYPES
Path:
type: string
CatalogTargetList:
type: array
items:
$ref: '#/components/schemas/CatalogTarget'
RecrawlBehavior:
type: string
enum:
- CRAWL_EVERYTHING
- CRAWL_NEW_FOLDERS_ONLY
- CRAWL_EVENT_MODE
TablePrefix:
type: string
minLength: 0
maxLength: 128
CrawlerState:
type: string
enum:
- READY
- RUNNING
- STOPPING
OperationTimeoutException: {}
CatalogTarget:
type: object
required:
- DatabaseName
- Tables
properties:
DatabaseName:
allOf:
- $ref: '#/components/schemas/NameString'
- description: The name of the database to be synchronized.
Tables:
allOf:
- $ref: '#/components/schemas/CatalogTablesList'
- description: A list of the tables to be synchronized.
ConnectionName:
allOf:
- $ref: '#/components/schemas/ConnectionName'
- description: The name of the connection for an Amazon S3-backed Data Catalog table to be a target of the crawl when using a Catalog connection type paired with a NETWORK Connection type.
EventQueueArn:
allOf:
- $ref: '#/components/schemas/EventQueueArn'
- description: A valid Amazon SQS ARN. For example, arn:aws:sqs:region:account:sqs.
DlqEventQueueArn:
allOf:
- $ref: '#/components/schemas/EventQueueArn'
- description: A valid Amazon dead-letter SQS ARN. For example, arn:aws:sqs:region:account:deadLetterQueue.
description: Specifies an Glue Data Catalog target.
CatalogTablesList:
type: array
items:
$ref: '#/components/schemas/NameString'
minItems: 1
DynamoDBTarget:
type: object
properties:
Path:
allOf:
- $ref: '#/components/schemas/Path'
- description: The name of the DynamoDB table to crawl.
scanAll:
allOf:
- $ref: '#/components/schemas/NullableBoolean'
- description: Indicates whether to scan all the records, or to sample rows from the table. Scanning all the records can take a long time when the table is not a high throughput table.
A value of true means to scan all records, while a value of false means to sample the records. If no value is specified, the value defaults to true.
The percentage of the configured read capacity units to use by the Glue crawler. Read capacity units is a term defined by DynamoDB, and is a numeric value that acts as rate limiter for the number of reads that can be performed on that table per second.
The valid values are null or a value between 0.1 to 1.5. A null value is used when user does not provide a value, and defaults to 0.5 of the configured Read Capacity Unit (for provisioned tables), or 0.25 of the max configured Read Capacity Unit (for tables using on-demand mode).
description: Specifies an Amazon DynamoDB table to crawl. VersionId: type: integer LastCrawlStatus: type: string enum: - SUCCEEDED - CANCELLED - FAILED CrawlerLineageSettings: type: string enum: - ENABLE - DISABLE UpdateBehavior: type: string enum: - LOG - UPDATE_IN_DATABASE ConnectionName: type: string DeltaTarget: type: object properties: DeltaTables: allOf: - $ref: '#/components/schemas/PathList' - description: A list of the Amazon S3 paths to the Delta tables. ConnectionName: allOf: - $ref: '#/components/schemas/ConnectionName' - description: The name of the connection to use to connect to the Delta table target. WriteManifest: allOf: - $ref: '#/components/schemas/NullableBoolean' - description: Specifies whether to write the manifest files to the Delta table path. CreateNativeDeltaTable: allOf: - $ref: '#/components/schemas/NullableBoolean' - description: Specifies whether the crawler will create native tables, to allow integration with query engines that support querying of the Delta transaction log directly. description: Specifies a Delta data store to crawl one or more Delta tables. EventQueueArn: type: string MillisecondsCount: type: integer LogStream: type: string pattern: '[^:*]*' minLength: 1 maxLength: 512 RecrawlPolicy: type: object properties: RecrawlBehavior: allOf: - $ref: '#/components/schemas/RecrawlBehavior' - description:Specifies whether to crawl the entire dataset again or to crawl only folders that were added since the last crawler run.
A value of CRAWL_EVERYTHING specifies crawling the entire dataset again.
A value of CRAWL_NEW_FOLDERS_ONLY specifies crawling only folders that were added since the last crawler run.
A value of CRAWL_EVENT_MODE specifies crawling only the changes identified by Amazon S3 events.
SecurityConfiguration structure to be used by this crawler.
LakeFormationConfiguration:
allOf:
- $ref: '#/components/schemas/LakeFormationConfiguration'
- description: Specifies whether the crawler should use Lake Formation credentials for the crawler instead of the IAM role credentials.
description: Specifies a crawler program that examines a data source and uses classifiers to try to determine its schema. If successful, the crawler records metadata concerning the data source in the Glue Data Catalog.
S3Target:
type: object
properties:
Path:
allOf:
- $ref: '#/components/schemas/Path'
- description: The path to the Amazon S3 target.
Exclusions:
allOf:
- $ref: '#/components/schemas/PathList'
- description: A list of glob patterns used to exclude from the crawl. For more information, see Catalog Tables with a Crawler.
ConnectionName:
allOf:
- $ref: '#/components/schemas/ConnectionName'
- description: The name of a connection which allows a job or crawler to access data in Amazon S3 within an Amazon Virtual Private Cloud environment (Amazon VPC).
SampleSize:
allOf:
- $ref: '#/components/schemas/NullableInteger'
- description: Sets the number of files in each leaf folder to be crawled when crawling sample files in a dataset. If not set, all the files are crawled. A valid value is an integer between 1 and 249.
EventQueueArn:
allOf:
- $ref: '#/components/schemas/EventQueueArn'
- description: A valid Amazon SQS ARN. For example, arn:aws:sqs:region:account:sqs.
DlqEventQueueArn:
allOf:
- $ref: '#/components/schemas/EventQueueArn'
- description: A valid Amazon dead-letter SQS ARN. For example, arn:aws:sqs:region:account:deadLetterQueue.
description: Specifies a data store in Amazon Simple Storage Service (Amazon S3).
NameString:
type: string
minLength: 1
maxLength: 255
x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\t]*'
GetCrawlerResponse:
type: object
properties:
Crawler:
allOf:
- $ref: '#/components/schemas/Crawler'
- description: The metadata for the specified crawler.
Timestamp:
type: string
format: date-time
LakeFormationConfiguration:
type: object
properties:
UseLakeFormationCredentials:
allOf:
- $ref: '#/components/schemas/NullableBoolean'
- description: Specifies whether to use Lake Formation credentials for the crawler instead of the IAM role credentials.
AccountId:
allOf:
- $ref: '#/components/schemas/AccountId'
- description: Required for cross account crawls. For same account crawls as the target data, this can be left as null.
description: Specifies Lake Formation configuration settings for the crawler.
DeltaTargetList:
type: array
items:
$ref: '#/components/schemas/DeltaTarget'
CrawlerTargets:
type: object
properties:
S3Targets:
allOf:
- $ref: '#/components/schemas/S3TargetList'
- description: Specifies Amazon Simple Storage Service (Amazon S3) targets.
JdbcTargets:
allOf:
- $ref: '#/components/schemas/JdbcTargetList'
- description: Specifies JDBC targets.
MongoDBTargets:
allOf:
- $ref: '#/components/schemas/MongoDBTargetList'
- description: Specifies Amazon DocumentDB or MongoDB targets.
DynamoDBTargets:
allOf:
- $ref: '#/components/schemas/DynamoDBTargetList'
- description: Specifies Amazon DynamoDB targets.
CatalogTargets:
allOf:
- $ref: '#/components/schemas/CatalogTargetList'
- description: Specifies Glue Data Catalog targets.
DeltaTargets:
allOf:
- $ref: '#/components/schemas/DeltaTargetList'
- description: Specifies Delta data store targets.
description: Specifies data stores to crawl.
S3TargetList:
type: array
items:
$ref: '#/components/schemas/S3Target'
PathList:
type: array
items:
$ref: '#/components/schemas/Path'
LogGroup:
type: string
pattern: '[\.\-_/#A-Za-z0-9]+'
minLength: 1
maxLength: 512
DynamoDBTargetList:
type: array
items:
$ref: '#/components/schemas/DynamoDBTarget'
LineageConfiguration:
type: object
properties:
CrawlerLineageSettings:
allOf:
- $ref: '#/components/schemas/CrawlerLineageSettings'
- description: 'Specifies whether data lineage is enabled for the crawler. Valid values are:
ENABLE: enables data lineage for the crawler
DISABLE: disables data lineage for the crawler
Specify a value of RAWTYPES or COMMENTS to enable additional metadata in table responses. RAWTYPES provides the native-level datatype. COMMENTS provides comments associated with a column or table in the database.
If you do not need additional metadata, keep the field empty.
description: Specifies a JDBC data store to crawl. CronExpression: type: string parameters: X-Amz-SignedHeaders: name: X-Amz-SignedHeaders in: header schema: type: string required: false X-Amz-Signature: name: X-Amz-Signature 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-Content-Sha256: name: X-Amz-Content-Sha256 in: header schema: type: string required: false X-Amz-Date: name: X-Amz-Date in: header schema: type: string required: false 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 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/glue/ x-hasEquivalentPaths: true