@lap v0.3 # Machine-readable API spec. Each @endpoint block is one API call. @api AWS Glue @version 2017-03-31 @auth AWS SigV4 @endpoints 224 @hint download_for_search @toc root(224) @endpoint POST / @desc Creates one or more partitions in a batch operation. @required {DatabaseName: str, TableName: str, PartitionInputList: [PartitionInput]} @optional {CatalogId: str} @returns(200) {Errors: [PartitionError]?} @endpoint POST / @desc Deletes a list of connection definitions from the Data Catalog. @required {ConnectionNameList: [str]} @optional {CatalogId: str} @returns(200) {Succeeded: [str]?, Errors: map?} @endpoint POST / @desc Deletes one or more partitions in a batch operation. @required {DatabaseName: str, TableName: str, PartitionsToDelete: [PartitionValueList]} @optional {CatalogId: str} @returns(200) {Errors: [PartitionError]?} @endpoint POST / @desc Deletes multiple tables at once. After completing this operation, you no longer have access to the table versions and partitions that belong to the deleted table. Glue deletes these "orphaned" resources asynchronously in a timely manner, at the discretion of the service. To ensure the immediate deletion of all related resources, before calling BatchDeleteTable, use DeleteTableVersion or BatchDeleteTableVersion, and DeletePartition or BatchDeletePartition, to delete any resources that belong to the table. @required {DatabaseName: str, TablesToDelete: [str]} @optional {CatalogId: str, TransactionId: str} @returns(200) {Errors: [TableError]?} @endpoint POST / @desc Deletes a specified batch of versions of a table. @required {DatabaseName: str, TableName: str, VersionIds: [str]} @optional {CatalogId: str} @returns(200) {Errors: [TableVersionError]?} @endpoint POST / @desc Retrieves information about a list of blueprints. @required {Names: [str]} @optional {IncludeBlueprint: bool, IncludeParameterSpec: bool} @returns(200) {Blueprints: [Blueprint]?, MissingBlueprints: [str]?} @endpoint POST / @desc Returns a list of resource metadata for a given list of crawler names. After calling the ListCrawlers operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags. @required {CrawlerNames: [str]} @returns(200) {Crawlers: [Crawler]?, CrawlersNotFound: [str]?} @endpoint POST / @desc Retrieves the details for the custom patterns specified by a list of names. @required {Names: [str]} @returns(200) {CustomEntityTypes: [CustomEntityType]?, CustomEntityTypesNotFound: [str]?} @endpoint POST / @desc Retrieves a list of data quality results for the specified result IDs. @required {ResultIds: [str]} @returns(200) {Results: [DataQualityResult], ResultsNotFound: [str]?} @endpoint POST / @desc Returns a list of resource metadata for a given list of development endpoint names. After calling the ListDevEndpoints operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags. @required {DevEndpointNames: [str]} @returns(200) {DevEndpoints: [DevEndpoint]?, DevEndpointsNotFound: [str]?} @endpoint POST / @desc Returns a list of resource metadata for a given list of job names. After calling the ListJobs operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags. @required {JobNames: [str]} @returns(200) {Jobs: [Job]?, JobsNotFound: [str]?} @endpoint POST / @desc Retrieves partitions in a batch request. @required {DatabaseName: str, TableName: str, PartitionsToGet: [PartitionValueList]} @optional {CatalogId: str} @returns(200) {Partitions: [Partition]?, UnprocessedKeys: [PartitionValueList]?} @endpoint POST / @desc Returns the configuration for the specified table optimizers. @required {Entries: [BatchGetTableOptimizerEntry]} @returns(200) {TableOptimizers: [BatchTableOptimizer]?, Failures: [BatchGetTableOptimizerError]?} @endpoint POST / @desc Returns a list of resource metadata for a given list of trigger names. After calling the ListTriggers operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags. @required {TriggerNames: [str]} @returns(200) {Triggers: [Trigger]?, TriggersNotFound: [str]?} @endpoint POST / @desc Returns a list of resource metadata for a given list of workflow names. After calling the ListWorkflows operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags. @required {Names: [str]} @optional {IncludeGraph: bool} @returns(200) {Workflows: [Workflow]?, MissingWorkflows: [str]?} @endpoint POST / @desc Annotate datapoints over time for a specific data quality statistic. @required {InclusionAnnotations: [DatapointInclusionAnnotation]} @optional {ClientToken: str} @returns(200) {FailedInclusionAnnotations: [AnnotationError]?} @endpoint POST / @desc Stops one or more job runs for a specified job definition. @required {JobName: str, JobRunIds: [str]} @returns(200) {SuccessfulSubmissions: [BatchStopJobRunSuccessfulSubmission]?, Errors: [BatchStopJobRunError]?} @endpoint POST / @desc Updates one or more partitions in a batch operation. @required {DatabaseName: str, TableName: str, Entries: [BatchUpdatePartitionRequestEntry]} @optional {CatalogId: str} @returns(200) {Errors: [BatchUpdatePartitionFailureEntry]?} @endpoint POST / @desc Cancels the specified recommendation run that was being used to generate rules. @required {RunId: str} @endpoint POST / @desc Cancels a run where a ruleset is being evaluated against a data source. @required {RunId: str} @endpoint POST / @desc Cancels (stops) a task run. Machine learning task runs are asynchronous tasks that Glue runs on your behalf as part of various machine learning workflows. You can cancel a machine learning task run at any time by calling CancelMLTaskRun with a task run's parent transform's TransformID and the task run's TaskRunId. @required {TransformId: str, TaskRunId: str} @returns(200) {TransformId: str?, TaskRunId: str?, Status: str?} @endpoint POST / @desc Cancels the statement. @required {SessionId: str, Id: int} @optional {RequestOrigin: str} @endpoint POST / @desc Validates the supplied schema. This call has no side effects, it simply validates using the supplied schema using DataFormat as the format. Since it does not take a schema set name, no compatibility checks are performed. @required {DataFormat: str, SchemaDefinition: str} @returns(200) {Valid: bool?, Error: str?} @endpoint POST / @desc Registers a blueprint with Glue. @required {Name: str, BlueprintLocation: str} @optional {Description: str, Tags: map} @returns(200) {Name: str?} @endpoint POST / @desc Creates a classifier in the user's account. This can be a GrokClassifier, an XMLClassifier, a JsonClassifier, or a CsvClassifier, depending on which field of the request is present. @optional {GrokClassifier: CreateGrokClassifierRequest, XMLClassifier: CreateXMLClassifierRequest, JsonClassifier: CreateJsonClassifierRequest, CsvClassifier: CreateCsvClassifierRequest} @endpoint POST / @desc Creates a connection definition in the Data Catalog. Connections used for creating federated resources require the IAM glue:PassConnection permission. @required {ConnectionInput: ConnectionInput} @optional {CatalogId: str, Tags: map} @returns(200) {CreateConnectionStatus: str?} @endpoint POST / @desc Creates a new crawler with specified targets, role, configuration, and optional schedule. At least one crawl target must be specified, in the s3Targets field, the jdbcTargets field, or the DynamoDBTargets field. @required {Name: str, Role: str, Targets: CrawlerTargets} @optional {DatabaseName: str, Description: str, Schedule: str, Classifiers: [str], TablePrefix: str, SchemaChangePolicy: SchemaChangePolicy, RecrawlPolicy: RecrawlPolicy, LineageConfiguration: LineageConfiguration, LakeFormationConfiguration: LakeFormationConfiguration, Configuration: str, CrawlerSecurityConfiguration: str, Tags: map} @endpoint POST / @desc Creates a custom pattern that is used to detect sensitive data across the columns and rows of your structured data. Each custom pattern you create specifies a regular expression and an optional list of context words. If no context words are passed only a regular expression is checked. @required {Name: str, RegexString: str} @optional {ContextWords: [str], Tags: map} @returns(200) {Name: str?} @endpoint POST / @desc Creates a data quality ruleset with DQDL rules applied to a specified Glue table. You create the ruleset using the Data Quality Definition Language (DQDL). For more information, see the Glue developer guide. @required {Name: str, Ruleset: str} @optional {Description: str, Tags: map, TargetTable: DataQualityTargetTable, DataQualitySecurityConfiguration: str, ClientToken: str} @returns(200) {Name: str?} @endpoint POST / @desc Creates a new database in a Data Catalog. @required {DatabaseInput: DatabaseInput} @optional {CatalogId: str, Tags: map} @endpoint POST / @desc Creates a new development endpoint. @required {EndpointName: str, RoleArn: str} @optional {SecurityGroupIds: [str], SubnetId: str, PublicKey: str, PublicKeys: [str], NumberOfNodes: int, WorkerType: str, GlueVersion: str, NumberOfWorkers: int, ExtraPythonLibsS3Path: str, ExtraJarsS3Path: str, SecurityConfiguration: str, Tags: map, Arguments: map} @returns(200) {EndpointName: str?, Status: str?, SecurityGroupIds: [str]?, SubnetId: str?, RoleArn: str?, YarnEndpointAddress: str?, ZeppelinRemoteSparkInterpreterPort: int?, NumberOfNodes: int?, WorkerType: str?, GlueVersion: str?, NumberOfWorkers: int?, AvailabilityZone: str?, VpcId: str?, ExtraPythonLibsS3Path: str?, ExtraJarsS3Path: str?, FailureReason: str?, SecurityConfiguration: str?, CreatedTimestamp: str(timestamp)?, Arguments: map?} @endpoint POST / @desc Creates a new job definition. @required {Name: str, Role: str, Command: JobCommand} @optional {JobMode: str, JobRunQueuingEnabled: bool, Description: str, LogUri: str, ExecutionProperty: ExecutionProperty, DefaultArguments: map, NonOverridableArguments: map, Connections: ConnectionsList, MaxRetries: int, AllocatedCapacity: int, Timeout: int, MaxCapacity: num(f64), SecurityConfiguration: str, Tags: map, NotificationProperty: NotificationProperty, GlueVersion: str, NumberOfWorkers: int, WorkerType: str, CodeGenConfigurationNodes: map, ExecutionClass: str, SourceControlDetails: SourceControlDetails, MaintenanceWindow: str} @returns(200) {Name: str?} @endpoint POST / @desc Creates an Glue machine learning transform. This operation creates the transform and all the necessary parameters to train it. Call this operation as the first step in the process of using a machine learning transform (such as the FindMatches transform) for deduplicating data. You can provide an optional Description, in addition to the parameters that you want to use for your algorithm. You must also specify certain parameters for the tasks that Glue runs on your behalf as part of learning from your data and creating a high-quality machine learning transform. These parameters include Role, and optionally, AllocatedCapacity, Timeout, and MaxRetries. For more information, see Jobs. @required {Name: str, InputRecordTables: [GlueTable], Parameters: TransformParameters, Role: str} @optional {Description: str, GlueVersion: str, MaxCapacity: num(f64), WorkerType: str, NumberOfWorkers: int, Timeout: int, MaxRetries: int, Tags: map, TransformEncryption: TransformEncryption} @returns(200) {TransformId: str?} @endpoint POST / @desc Creates a new partition. @required {DatabaseName: str, TableName: str, PartitionInput: PartitionInput} @optional {CatalogId: str} @endpoint POST / @desc Creates a specified partition index in an existing table. @required {DatabaseName: str, TableName: str, PartitionIndex: PartitionIndex} @optional {CatalogId: str} @endpoint POST / @desc Creates a new registry which may be used to hold a collection of schemas. @required {RegistryName: str} @optional {Description: str, Tags: map} @returns(200) {RegistryArn: str?, RegistryName: str?, Description: str?, Tags: map?} @endpoint POST / @desc Creates a new schema set and registers the schema definition. Returns an error if the schema set already exists without actually registering the version. When the schema set is created, a version checkpoint will be set to the first version. Compatibility mode "DISABLED" restricts any additional schema versions from being added after the first schema version. For all other compatibility modes, validation of compatibility settings will be applied only from the second version onwards when the RegisterSchemaVersion API is used. When this API is called without a RegistryId, this will create an entry for a "default-registry" in the registry database tables, if it is not already present. @required {SchemaName: str, DataFormat: str} @optional {RegistryId: RegistryId, Compatibility: str, Description: str, Tags: map, SchemaDefinition: str} @returns(200) {RegistryName: str?, RegistryArn: str?, SchemaName: str?, SchemaArn: str?, Description: str?, DataFormat: str?, Compatibility: str?, SchemaCheckpoint: int(i64)?, LatestSchemaVersion: int(i64)?, NextSchemaVersion: int(i64)?, SchemaStatus: str?, Tags: map?, SchemaVersionId: str?, SchemaVersionStatus: str?} @endpoint POST / @desc Transforms a directed acyclic graph (DAG) into code. @optional {DagNodes: [CodeGenNode], DagEdges: [CodeGenEdge], Language: str} @returns(200) {PythonScript: str?, ScalaCode: str?} @endpoint POST / @desc Creates a new security configuration. A security configuration is a set of security properties that can be used by Glue. You can use a security configuration to encrypt data at rest. For information about using security configurations in Glue, see Encrypting Data Written by Crawlers, Jobs, and Development Endpoints. @required {Name: str, EncryptionConfiguration: EncryptionConfiguration} @returns(200) {Name: str?, CreatedTimestamp: str(timestamp)?} @endpoint POST / @desc Creates a new session. @required {Id: str, Role: str, Command: SessionCommand} @optional {Description: str, Timeout: int, IdleTimeout: int, DefaultArguments: map, Connections: ConnectionsList, MaxCapacity: num(f64), NumberOfWorkers: int, WorkerType: str, SecurityConfiguration: str, GlueVersion: str, Tags: map, RequestOrigin: str} @returns(200) {Session: Session?{Id: str?, CreatedOn: str(timestamp)?, Status: str?, ErrorMessage: str?, Description: str?, Role: str?, Command: SessionCommand?{Name: str?, PythonVersion: str?}, DefaultArguments: map?, Connections: ConnectionsList?{Connections: [str]?}, Progress: num(f64)?, MaxCapacity: num(f64)?, SecurityConfiguration: str?, GlueVersion: str?, NumberOfWorkers: int?, WorkerType: str?, CompletedOn: str(timestamp)?, ExecutionTime: num(f64)?, DPUSeconds: num(f64)?, IdleTimeout: int?, ProfileName: str?}} @endpoint POST / @desc Creates a new table definition in the Data Catalog. @required {DatabaseName: str, TableInput: TableInput} @optional {CatalogId: str, PartitionIndexes: [PartitionIndex], TransactionId: str, OpenTableFormatInput: OpenTableFormatInput} @endpoint POST / @desc Creates a new table optimizer for a specific function. compaction is the only currently supported optimizer type. @required {CatalogId: str, DatabaseName: str, TableName: str, Type: str, TableOptimizerConfiguration: TableOptimizerConfiguration} @endpoint POST / @desc Creates a new trigger. @required {Name: str, Type: str, Actions: [Action]} @optional {WorkflowName: str, Schedule: str, Predicate: Predicate, Description: str, StartOnCreation: bool, Tags: map, EventBatchingCondition: EventBatchingCondition} @returns(200) {Name: str?} @endpoint POST / @desc Creates an Glue usage profile. @required {Name: str, Configuration: ProfileConfiguration} @optional {Description: str, Tags: map} @returns(200) {Name: str?} @endpoint POST / @desc Creates a new function definition in the Data Catalog. @required {DatabaseName: str, FunctionInput: UserDefinedFunctionInput} @optional {CatalogId: str} @endpoint POST / @desc Creates a new workflow. @required {Name: str} @optional {Description: str, DefaultRunProperties: map, Tags: map, MaxConcurrentRuns: int} @returns(200) {Name: str?} @endpoint POST / @desc Deletes an existing blueprint. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Removes a classifier from the Data Catalog. @required {Name: str} @endpoint POST / @desc Delete the partition column statistics of a column. The Identity and Access Management (IAM) permission required for this operation is DeletePartition. @required {DatabaseName: str, TableName: str, PartitionValues: [str], ColumnName: str} @optional {CatalogId: str} @endpoint POST / @desc Retrieves table statistics of columns. The Identity and Access Management (IAM) permission required for this operation is DeleteTable. @required {DatabaseName: str, TableName: str, ColumnName: str} @optional {CatalogId: str} @endpoint POST / @desc Deletes a connection from the Data Catalog. @required {ConnectionName: str} @optional {CatalogId: str} @endpoint POST / @desc Removes a specified crawler from the Glue Data Catalog, unless the crawler state is RUNNING. @required {Name: str} @endpoint POST / @desc Deletes a custom pattern by specifying its name. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Deletes a data quality ruleset. @required {Name: str} @endpoint POST / @desc Removes a specified database from a Data Catalog. After completing this operation, you no longer have access to the tables (and all table versions and partitions that might belong to the tables) and the user-defined functions in the deleted database. Glue deletes these "orphaned" resources asynchronously in a timely manner, at the discretion of the service. To ensure the immediate deletion of all related resources, before calling DeleteDatabase, use DeleteTableVersion or BatchDeleteTableVersion, DeletePartition or BatchDeletePartition, DeleteUserDefinedFunction, and DeleteTable or BatchDeleteTable, to delete any resources that belong to the database. @required {Name: str} @optional {CatalogId: str} @endpoint POST / @desc Deletes a specified development endpoint. @required {EndpointName: str} @endpoint POST / @desc Deletes a specified job definition. If the job definition is not found, no exception is thrown. @required {JobName: str} @returns(200) {JobName: str?} @endpoint POST / @desc Deletes an Glue machine learning transform. Machine learning transforms are a special type of transform that use machine learning to learn the details of the transformation to be performed by learning from examples provided by humans. These transformations are then saved by Glue. If you no longer need a transform, you can delete it by calling DeleteMLTransforms. However, any Glue jobs that still reference the deleted transform will no longer succeed. @required {TransformId: str} @returns(200) {TransformId: str?} @endpoint POST / @desc Deletes a specified partition. @required {DatabaseName: str, TableName: str, PartitionValues: [str]} @optional {CatalogId: str} @endpoint POST / @desc Deletes a specified partition index from an existing table. @required {DatabaseName: str, TableName: str, IndexName: str} @optional {CatalogId: str} @endpoint POST / @desc Delete the entire registry including schema and all of its versions. To get the status of the delete operation, you can call the GetRegistry API after the asynchronous call. Deleting a registry will deactivate all online operations for the registry such as the UpdateRegistry, CreateSchema, UpdateSchema, and RegisterSchemaVersion APIs. @required {RegistryId: RegistryId} @returns(200) {RegistryName: str?, RegistryArn: str?, Status: str?} @endpoint POST / @desc Deletes a specified policy. @optional {PolicyHashCondition: str, ResourceArn: str} @endpoint POST / @desc Deletes the entire schema set, including the schema set and all of its versions. To get the status of the delete operation, you can call GetSchema API after the asynchronous call. Deleting a registry will deactivate all online operations for the schema, such as the GetSchemaByDefinition, and RegisterSchemaVersion APIs. @required {SchemaId: SchemaId} @returns(200) {SchemaArn: str?, SchemaName: str?, Status: str?} @endpoint POST / @desc Remove versions from the specified schema. A version number or range may be supplied. If the compatibility mode forbids deleting of a version that is necessary, such as BACKWARDS_FULL, an error is returned. Calling the GetSchemaVersions API after this call will list the status of the deleted versions. When the range of version numbers contain check pointed version, the API will return a 409 conflict and will not proceed with the deletion. You have to remove the checkpoint first using the DeleteSchemaCheckpoint API before using this API. You cannot use the DeleteSchemaVersions API to delete the first schema version in the schema set. The first schema version can only be deleted by the DeleteSchema API. This operation will also delete the attached SchemaVersionMetadata under the schema versions. Hard deletes will be enforced on the database. If the compatibility mode forbids deleting of a version that is necessary, such as BACKWARDS_FULL, an error is returned. @required {SchemaId: SchemaId, Versions: str} @returns(200) {SchemaVersionErrors: [SchemaVersionErrorItem]?} @endpoint POST / @desc Deletes a specified security configuration. @required {Name: str} @endpoint POST / @desc Deletes the session. @required {Id: str} @optional {RequestOrigin: str} @returns(200) {Id: str?} @endpoint POST / @desc Removes a table definition from the Data Catalog. After completing this operation, you no longer have access to the table versions and partitions that belong to the deleted table. Glue deletes these "orphaned" resources asynchronously in a timely manner, at the discretion of the service. To ensure the immediate deletion of all related resources, before calling DeleteTable, use DeleteTableVersion or BatchDeleteTableVersion, and DeletePartition or BatchDeletePartition, to delete any resources that belong to the table. @required {DatabaseName: str, Name: str} @optional {CatalogId: str, TransactionId: str} @endpoint POST / @desc Deletes an optimizer and all associated metadata for a table. The optimization will no longer be performed on the table. @required {CatalogId: str, DatabaseName: str, TableName: str, Type: str} @endpoint POST / @desc Deletes a specified version of a table. @required {DatabaseName: str, TableName: str, VersionId: str} @optional {CatalogId: str} @endpoint POST / @desc Deletes a specified trigger. If the trigger is not found, no exception is thrown. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Deletes the Glue specified usage profile. @required {Name: str} @endpoint POST / @desc Deletes an existing function definition from the Data Catalog. @required {DatabaseName: str, FunctionName: str} @optional {CatalogId: str} @endpoint POST / @desc Deletes a workflow. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Retrieves the details of a blueprint. @required {Name: str} @optional {IncludeBlueprint: bool, IncludeParameterSpec: bool} @returns(200) {Blueprint: Blueprint?{Name: str?, Description: str?, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, ParameterSpec: str?, BlueprintLocation: str?, BlueprintServiceLocation: str?, Status: str?, ErrorMessage: str?, LastActiveDefinition: LastActiveDefinition?{Description: str?, LastModifiedOn: str(timestamp)?, ParameterSpec: str?, BlueprintLocation: str?, BlueprintServiceLocation: str?}}} @endpoint POST / @desc Retrieves the details of a blueprint run. @required {BlueprintName: str, RunId: str} @returns(200) {BlueprintRun: BlueprintRun?{BlueprintName: str?, RunId: str?, WorkflowName: str?, State: str?, StartedOn: str(timestamp)?, CompletedOn: str(timestamp)?, ErrorMessage: str?, RollbackErrorMessage: str?, Parameters: str?, RoleArn: str?}} @endpoint POST / @desc Retrieves the details of blueprint runs for a specified blueprint. @required {BlueprintName: str} @optional {NextToken: str, MaxResults: int} @returns(200) {BlueprintRuns: [BlueprintRun]?, NextToken: str?} @endpoint POST / @desc Retrieves the status of a migration operation. @optional {CatalogId: str} @returns(200) {ImportStatus: CatalogImportStatus?{ImportCompleted: bool?, ImportTime: str(timestamp)?, ImportedBy: str?}} @endpoint POST / @desc Retrieve a classifier by name. @required {Name: str} @returns(200) {Classifier: Classifier?{GrokClassifier: GrokClassifier?{Name: str, Classification: str, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, Version: int(i64)?, GrokPattern: str, CustomPatterns: str?}, XMLClassifier: XMLClassifier?{Name: str, Classification: str, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, Version: int(i64)?, RowTag: str?}, JsonClassifier: JsonClassifier?{Name: str, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, Version: int(i64)?, JsonPath: str}, CsvClassifier: CsvClassifier?{Name: str, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, Version: int(i64)?, Delimiter: str?, QuoteSymbol: str?, ContainsHeader: str?, Header: [str]?, DisableValueTrimming: bool?, AllowSingleColumn: bool?, CustomDatatypeConfigured: bool?, CustomDatatypes: [str]?, Serde: str?}}} @endpoint POST / @desc Lists all classifier objects in the Data Catalog. @optional {MaxResults: int, NextToken: str} @returns(200) {Classifiers: [Classifier]?, NextToken: str?} @endpoint POST / @desc Retrieves partition statistics of columns. The Identity and Access Management (IAM) permission required for this operation is GetPartition. @required {DatabaseName: str, TableName: str, PartitionValues: [str], ColumnNames: [str]} @optional {CatalogId: str} @returns(200) {ColumnStatisticsList: [ColumnStatistics]?, Errors: [ColumnError]?} @endpoint POST / @desc Retrieves table statistics of columns. The Identity and Access Management (IAM) permission required for this operation is GetTable. @required {DatabaseName: str, TableName: str, ColumnNames: [str]} @optional {CatalogId: str} @returns(200) {ColumnStatisticsList: [ColumnStatistics]?, Errors: [ColumnError]?} @endpoint POST / @desc Get the associated metadata/information for a task run, given a task run ID. @required {ColumnStatisticsTaskRunId: str} @returns(200) {ColumnStatisticsTaskRun: ColumnStatisticsTaskRun?{CustomerId: str?, ColumnStatisticsTaskRunId: str?, DatabaseName: str?, TableName: str?, ColumnNameList: [str]?, CatalogID: str?, Role: str?, SampleSize: num(f64)?, SecurityConfiguration: str?, NumberOfWorkers: int?, WorkerType: str?, Status: str?, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, StartTime: str(timestamp)?, EndTime: str(timestamp)?, ErrorMessage: str?, DPUSeconds: num(f64)?}} @endpoint POST / @desc Retrieves information about all runs associated with the specified table. @required {DatabaseName: str, TableName: str} @optional {MaxResults: int, NextToken: str} @returns(200) {ColumnStatisticsTaskRuns: [ColumnStatisticsTaskRun]?, NextToken: str?} @endpoint POST / @desc Retrieves a connection definition from the Data Catalog. @required {Name: str} @optional {CatalogId: str, HidePassword: bool} @returns(200) {Connection: Connection?{Name: str?, Description: str?, ConnectionType: str?, MatchCriteria: [str]?, ConnectionProperties: map?, PhysicalConnectionRequirements: PhysicalConnectionRequirements?{SubnetId: str?, SecurityGroupIdList: [str]?, AvailabilityZone: str?}, CreationTime: str(timestamp)?, LastUpdatedTime: str(timestamp)?, LastUpdatedBy: str?, Status: str?, StatusReason: str?, LastConnectionValidationTime: str(timestamp)?, AuthenticationConfiguration: AuthenticationConfiguration?{AuthenticationType: str?, SecretArn: str?, OAuth2Properties: OAuth2Properties?{OAuth2GrantType: str?, OAuth2ClientApplication: OAuth2ClientApplication?, TokenUrl: str?, TokenUrlParametersMap: map?}}}} @endpoint POST / @desc Retrieves a list of connection definitions from the Data Catalog. @optional {CatalogId: str, Filter: GetConnectionsFilter, HidePassword: bool, NextToken: str, MaxResults: int} @returns(200) {ConnectionList: [Connection]?, NextToken: str?} @endpoint POST / @desc Retrieves metadata for a specified crawler. @required {Name: str} @returns(200) {Crawler: Crawler?{Name: str?, Role: str?, Targets: CrawlerTargets?{S3Targets: [S3Target]?, JdbcTargets: [JdbcTarget]?, MongoDBTargets: [MongoDBTarget]?, DynamoDBTargets: [DynamoDBTarget]?, CatalogTargets: [CatalogTarget]?, DeltaTargets: [DeltaTarget]?, IcebergTargets: [IcebergTarget]?, HudiTargets: [HudiTarget]?}, DatabaseName: str?, Description: str?, Classifiers: [str]?, RecrawlPolicy: RecrawlPolicy?{RecrawlBehavior: str?}, SchemaChangePolicy: SchemaChangePolicy?{UpdateBehavior: str?, DeleteBehavior: str?}, LineageConfiguration: LineageConfiguration?{CrawlerLineageSettings: str?}, State: str?, TablePrefix: str?, Schedule: Schedule?{ScheduleExpression: str?, State: str?}, CrawlElapsedTime: int(i64)?, CreationTime: str(timestamp)?, LastUpdated: str(timestamp)?, LastCrawl: LastCrawlInfo?{Status: str?, ErrorMessage: str?, LogGroup: str?, LogStream: str?, MessagePrefix: str?, StartTime: str(timestamp)?}, Version: int(i64)?, Configuration: str?, CrawlerSecurityConfiguration: str?, LakeFormationConfiguration: LakeFormationConfiguration?{UseLakeFormationCredentials: bool?, AccountId: str?}}} @endpoint POST / @desc Retrieves metrics about specified crawlers. @optional {CrawlerNameList: [str], MaxResults: int, NextToken: str} @returns(200) {CrawlerMetricsList: [CrawlerMetrics]?, NextToken: str?} @endpoint POST / @desc Retrieves metadata for all crawlers defined in the customer account. @optional {MaxResults: int, NextToken: str} @returns(200) {Crawlers: [Crawler]?, NextToken: str?} @endpoint POST / @desc Retrieves the details of a custom pattern by specifying its name. @required {Name: str} @returns(200) {Name: str?, RegexString: str?, ContextWords: [str]?} @endpoint POST / @desc Retrieves the security configuration for a specified catalog. @optional {CatalogId: str} @returns(200) {DataCatalogEncryptionSettings: DataCatalogEncryptionSettings?{EncryptionAtRest: EncryptionAtRest?{CatalogEncryptionMode: str, SseAwsKmsKeyId: str?, CatalogEncryptionServiceRole: str?}, ConnectionPasswordEncryption: ConnectionPasswordEncryption?{ReturnConnectionPasswordEncrypted: bool, AwsKmsKeyId: str?}}} @endpoint POST / @desc Retrieve the training status of the model along with more information (CompletedOn, StartedOn, FailureReason). @required {ProfileId: str} @optional {StatisticId: str} @returns(200) {Status: str?, StartedOn: str(timestamp)?, CompletedOn: str(timestamp)?, FailureReason: str?} @endpoint POST / @desc Retrieve a statistic's predictions for a given Profile ID. @required {StatisticId: str, ProfileId: str} @returns(200) {CompletedOn: str(timestamp)?, Model: [StatisticModelResult]?} @endpoint POST / @desc Retrieves the result of a data quality rule evaluation. @required {ResultId: str} @returns(200) {ResultId: str?, ProfileId: str?, Score: num(f64)?, DataSource: DataSource?{GlueTable: GlueTable{DatabaseName: str, TableName: str, CatalogId: str?, ConnectionName: str?, AdditionalOptions: map?}}, RulesetName: str?, EvaluationContext: str?, StartedOn: str(timestamp)?, CompletedOn: str(timestamp)?, JobName: str?, JobRunId: str?, RulesetEvaluationRunId: str?, RuleResults: [DataQualityRuleResult]?, AnalyzerResults: [DataQualityAnalyzerResult]?, Observations: [DataQualityObservation]?} @endpoint POST / @desc Gets the specified recommendation run that was used to generate rules. @required {RunId: str} @returns(200) {RunId: str?, DataSource: DataSource?{GlueTable: GlueTable{DatabaseName: str, TableName: str, CatalogId: str?, ConnectionName: str?, AdditionalOptions: map?}}, Role: str?, NumberOfWorkers: int?, Timeout: int?, Status: str?, ErrorString: str?, StartedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, CompletedOn: str(timestamp)?, ExecutionTime: int?, RecommendedRuleset: str?, CreatedRulesetName: str?, DataQualitySecurityConfiguration: str?} @endpoint POST / @desc Returns an existing ruleset by identifier or name. @required {Name: str} @returns(200) {Name: str?, Description: str?, Ruleset: str?, TargetTable: DataQualityTargetTable?{TableName: str, DatabaseName: str, CatalogId: str?}, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, RecommendationRunId: str?, DataQualitySecurityConfiguration: str?} @endpoint POST / @desc Retrieves a specific run where a ruleset is evaluated against a data source. @required {RunId: str} @returns(200) {RunId: str?, DataSource: DataSource?{GlueTable: GlueTable{DatabaseName: str, TableName: str, CatalogId: str?, ConnectionName: str?, AdditionalOptions: map?}}, Role: str?, NumberOfWorkers: int?, Timeout: int?, AdditionalRunOptions: DataQualityEvaluationRunAdditionalRunOptions?{CloudWatchMetricsEnabled: bool?, ResultsS3Prefix: str?, CompositeRuleEvaluationMethod: str?}, Status: str?, ErrorString: str?, StartedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, CompletedOn: str(timestamp)?, ExecutionTime: int?, RulesetNames: [str]?, ResultIds: [str]?, AdditionalDataSources: map?} @endpoint POST / @desc Retrieves the definition of a specified database. @required {Name: str} @optional {CatalogId: str} @returns(200) {Database: Database?{Name: str, Description: str?, LocationUri: str?, Parameters: map?, CreateTime: str(timestamp)?, CreateTableDefaultPermissions: [PrincipalPermissions]?, TargetDatabase: DatabaseIdentifier?{CatalogId: str?, DatabaseName: str?, Region: str?}, CatalogId: str?, FederatedDatabase: FederatedDatabase?{Identifier: str?, ConnectionName: str?}}} @endpoint POST / @desc Retrieves all databases defined in a given Data Catalog. @optional {CatalogId: str, NextToken: str, MaxResults: int, ResourceShareType: str, AttributesToGet: [str]} @returns(200) {DatabaseList: [Database], NextToken: str?} @endpoint POST / @desc Transforms a Python script into a directed acyclic graph (DAG). @optional {PythonScript: str} @returns(200) {DagNodes: [CodeGenNode]?, DagEdges: [CodeGenEdge]?} @endpoint POST / @desc Retrieves information about a specified development endpoint. When you create a development endpoint in a virtual private cloud (VPC), Glue returns only a private IP address, and the public IP address field is not populated. When you create a non-VPC development endpoint, Glue returns only a public IP address. @required {EndpointName: str} @returns(200) {DevEndpoint: DevEndpoint?{EndpointName: str?, RoleArn: str?, SecurityGroupIds: [str]?, SubnetId: str?, YarnEndpointAddress: str?, PrivateAddress: str?, ZeppelinRemoteSparkInterpreterPort: int?, PublicAddress: str?, Status: str?, WorkerType: str?, GlueVersion: str?, NumberOfWorkers: int?, NumberOfNodes: int?, AvailabilityZone: str?, VpcId: str?, ExtraPythonLibsS3Path: str?, ExtraJarsS3Path: str?, FailureReason: str?, LastUpdateStatus: str?, CreatedTimestamp: str(timestamp)?, LastModifiedTimestamp: str(timestamp)?, PublicKey: str?, PublicKeys: [str]?, SecurityConfiguration: str?, Arguments: map?}} @endpoint POST / @desc Retrieves all the development endpoints in this Amazon Web Services account. When you create a development endpoint in a virtual private cloud (VPC), Glue returns only a private IP address and the public IP address field is not populated. When you create a non-VPC development endpoint, Glue returns only a public IP address. @optional {MaxResults: int, NextToken: str} @returns(200) {DevEndpoints: [DevEndpoint]?, NextToken: str?} @endpoint POST / @desc Retrieves an existing job definition. @required {JobName: str} @returns(200) {Job: Job?{Name: str?, JobMode: str?, JobRunQueuingEnabled: bool?, Description: str?, LogUri: str?, Role: str?, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, ExecutionProperty: ExecutionProperty?{MaxConcurrentRuns: int?}, Command: JobCommand?{Name: str?, ScriptLocation: str?, PythonVersion: str?, Runtime: str?}, DefaultArguments: map?, NonOverridableArguments: map?, Connections: ConnectionsList?{Connections: [str]?}, MaxRetries: int?, AllocatedCapacity: int?, Timeout: int?, MaxCapacity: num(f64)?, WorkerType: str?, NumberOfWorkers: int?, SecurityConfiguration: str?, NotificationProperty: NotificationProperty?{NotifyDelayAfter: int?}, GlueVersion: str?, CodeGenConfigurationNodes: map?, ExecutionClass: str?, SourceControlDetails: SourceControlDetails?{Provider: str?, Repository: str?, Owner: str?, Branch: str?, Folder: str?, LastCommitId: str?, AuthStrategy: str?, AuthToken: str?}, MaintenanceWindow: str?, ProfileName: str?}} @endpoint POST / @desc Returns information on a job bookmark entry. For more information about enabling and using job bookmarks, see: Tracking processed data using job bookmarks Job parameters used by Glue Job structure @required {JobName: str} @optional {RunId: str} @returns(200) {JobBookmarkEntry: JobBookmarkEntry?{JobName: str?, Version: int?, Run: int?, Attempt: int?, PreviousRunId: str?, RunId: str?, JobBookmark: str?}} @endpoint POST / @desc Retrieves the metadata for a given job run. Job run history is accessible for 90 days for your workflow and job run. @required {JobName: str, RunId: str} @optional {PredecessorsIncluded: bool} @returns(200) {JobRun: JobRun?{Id: str?, Attempt: int?, PreviousRunId: str?, TriggerName: str?, JobName: str?, JobMode: str?, JobRunQueuingEnabled: bool?, StartedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, CompletedOn: str(timestamp)?, JobRunState: str?, Arguments: map?, ErrorMessage: str?, PredecessorRuns: [Predecessor]?, AllocatedCapacity: int?, ExecutionTime: int?, Timeout: int?, MaxCapacity: num(f64)?, WorkerType: str?, NumberOfWorkers: int?, SecurityConfiguration: str?, LogGroupName: str?, NotificationProperty: NotificationProperty?{NotifyDelayAfter: int?}, GlueVersion: str?, DPUSeconds: num(f64)?, ExecutionClass: str?, MaintenanceWindow: str?, ProfileName: str?, StateDetail: str?}} @endpoint POST / @desc Retrieves metadata for all runs of a given job definition. @required {JobName: str} @optional {NextToken: str, MaxResults: int} @returns(200) {JobRuns: [JobRun]?, NextToken: str?} @endpoint POST / @desc Retrieves all current job definitions. @optional {NextToken: str, MaxResults: int} @returns(200) {Jobs: [Job]?, NextToken: str?} @endpoint POST / @desc Gets details for a specific task run on a machine learning transform. Machine learning task runs are asynchronous tasks that Glue runs on your behalf as part of various machine learning workflows. You can check the stats of any task run by calling GetMLTaskRun with the TaskRunID and its parent transform's TransformID. @required {TransformId: str, TaskRunId: str} @returns(200) {TransformId: str?, TaskRunId: str?, Status: str?, LogGroupName: str?, Properties: TaskRunProperties?{TaskType: str?, ImportLabelsTaskRunProperties: ImportLabelsTaskRunProperties?{InputS3Path: str?, Replace: bool?}, ExportLabelsTaskRunProperties: ExportLabelsTaskRunProperties?{OutputS3Path: str?}, LabelingSetGenerationTaskRunProperties: LabelingSetGenerationTaskRunProperties?{OutputS3Path: str?}, FindMatchesTaskRunProperties: FindMatchesTaskRunProperties?{JobId: str?, JobName: str?, JobRunId: str?}}, ErrorString: str?, StartedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, CompletedOn: str(timestamp)?, ExecutionTime: int?} @endpoint POST / @desc Gets a list of runs for a machine learning transform. Machine learning task runs are asynchronous tasks that Glue runs on your behalf as part of various machine learning workflows. You can get a sortable, filterable list of machine learning task runs by calling GetMLTaskRuns with their parent transform's TransformID and other optional parameters as documented in this section. This operation returns a list of historic runs and must be paginated. @required {TransformId: str} @optional {NextToken: str, MaxResults: int, Filter: TaskRunFilterCriteria, Sort: TaskRunSortCriteria} @returns(200) {TaskRuns: [TaskRun]?, NextToken: str?} @endpoint POST / @desc Gets an Glue machine learning transform artifact and all its corresponding metadata. Machine learning transforms are a special type of transform that use machine learning to learn the details of the transformation to be performed by learning from examples provided by humans. These transformations are then saved by Glue. You can retrieve their metadata by calling GetMLTransform. @required {TransformId: str} @returns(200) {TransformId: str?, Name: str?, Description: str?, Status: str?, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, InputRecordTables: [GlueTable]?, Parameters: TransformParameters?{TransformType: str, FindMatchesParameters: FindMatchesParameters?{PrimaryKeyColumnName: str?, PrecisionRecallTradeoff: num(f64)?, AccuracyCostTradeoff: num(f64)?, EnforceProvidedLabels: bool?}}, EvaluationMetrics: EvaluationMetrics?{TransformType: str, FindMatchesMetrics: FindMatchesMetrics?{AreaUnderPRCurve: num(f64)?, Precision: num(f64)?, Recall: num(f64)?, F1: num(f64)?, ConfusionMatrix: ConfusionMatrix?{NumTruePositives: int(i64)?, NumFalsePositives: int(i64)?, NumTrueNegatives: int(i64)?, NumFalseNegatives: int(i64)?}, ColumnImportances: [ColumnImportance]?}}, LabelCount: int?, Schema: [SchemaColumn]?, Role: str?, GlueVersion: str?, MaxCapacity: num(f64)?, WorkerType: str?, NumberOfWorkers: int?, Timeout: int?, MaxRetries: int?, TransformEncryption: TransformEncryption?{MlUserDataEncryption: MLUserDataEncryption?{MlUserDataEncryptionMode: str, KmsKeyId: str?}, TaskRunSecurityConfigurationName: str?}} @endpoint POST / @desc Gets a sortable, filterable list of existing Glue machine learning transforms. Machine learning transforms are a special type of transform that use machine learning to learn the details of the transformation to be performed by learning from examples provided by humans. These transformations are then saved by Glue, and you can retrieve their metadata by calling GetMLTransforms. @optional {NextToken: str, MaxResults: int, Filter: TransformFilterCriteria, Sort: TransformSortCriteria} @returns(200) {Transforms: [MLTransform], NextToken: str?} @endpoint POST / @desc Creates mappings. @required {Source: CatalogEntry} @optional {Sinks: [CatalogEntry], Location: Location} @returns(200) {Mapping: [MappingEntry]} @endpoint POST / @desc Retrieves information about a specified partition. @required {DatabaseName: str, TableName: str, PartitionValues: [str]} @optional {CatalogId: str} @returns(200) {Partition: Partition?{Values: [str]?, DatabaseName: str?, TableName: str?, CreationTime: str(timestamp)?, LastAccessTime: str(timestamp)?, StorageDescriptor: StorageDescriptor?{Columns: [Column]?, Location: str?, AdditionalLocations: [str]?, InputFormat: str?, OutputFormat: str?, Compressed: bool?, NumberOfBuckets: int?, SerdeInfo: SerDeInfo?{Name: str?, SerializationLibrary: str?, Parameters: map?}, BucketColumns: [str]?, SortColumns: [Order]?, Parameters: map?, SkewedInfo: SkewedInfo?{SkewedColumnNames: [str]?, SkewedColumnValues: [str]?, SkewedColumnValueLocationMaps: map?}, StoredAsSubDirectories: bool?, SchemaReference: SchemaReference?{SchemaId: SchemaId?, SchemaVersionId: str?, SchemaVersionNumber: int(i64)?}}, Parameters: map?, LastAnalyzedTime: str(timestamp)?, CatalogId: str?}} @endpoint POST / @desc Retrieves the partition indexes associated with a table. @required {DatabaseName: str, TableName: str} @optional {CatalogId: str, NextToken: str} @returns(200) {PartitionIndexDescriptorList: [PartitionIndexDescriptor]?, NextToken: str?} @endpoint POST / @desc Retrieves information about the partitions in a table. @required {DatabaseName: str, TableName: str} @optional {CatalogId: str, Expression: str, NextToken: str, Segment: Segment, MaxResults: int, ExcludeColumnSchema: bool, TransactionId: str, QueryAsOfTime: str(timestamp)} @returns(200) {Partitions: [Partition]?, NextToken: str?} @endpoint POST / @desc Gets code to perform a specified mapping. @required {Mapping: [MappingEntry], Source: CatalogEntry} @optional {Sinks: [CatalogEntry], Location: Location, Language: str, AdditionalPlanOptionsMap: map} @returns(200) {PythonScript: str?, ScalaCode: str?} @endpoint POST / @desc Describes the specified registry in detail. @required {RegistryId: RegistryId} @returns(200) {RegistryName: str?, RegistryArn: str?, Description: str?, Status: str?, CreatedTime: str?, UpdatedTime: str?} @endpoint POST / @desc Retrieves the resource policies set on individual resources by Resource Access Manager during cross-account permission grants. Also retrieves the Data Catalog resource policy. If you enabled metadata encryption in Data Catalog settings, and you do not have permission on the KMS key, the operation can't return the Data Catalog resource policy. @optional {NextToken: str, MaxResults: int} @returns(200) {GetResourcePoliciesResponseList: [GluePolicy]?, NextToken: str?} @endpoint POST / @desc Retrieves a specified resource policy. @optional {ResourceArn: str} @returns(200) {PolicyInJson: str?, PolicyHash: str?, CreateTime: str(timestamp)?, UpdateTime: str(timestamp)?} @endpoint POST / @desc Describes the specified schema in detail. @required {SchemaId: SchemaId} @returns(200) {RegistryName: str?, RegistryArn: str?, SchemaName: str?, SchemaArn: str?, Description: str?, DataFormat: str?, Compatibility: str?, SchemaCheckpoint: int(i64)?, LatestSchemaVersion: int(i64)?, NextSchemaVersion: int(i64)?, SchemaStatus: str?, CreatedTime: str?, UpdatedTime: str?} @endpoint POST / @desc Retrieves a schema by the SchemaDefinition. The schema definition is sent to the Schema Registry, canonicalized, and hashed. If the hash is matched within the scope of the SchemaName or ARN (or the default registry, if none is supplied), that schema’s metadata is returned. Otherwise, a 404 or NotFound error is returned. Schema versions in Deleted statuses will not be included in the results. @required {SchemaId: SchemaId, SchemaDefinition: str} @returns(200) {SchemaVersionId: str?, SchemaArn: str?, DataFormat: str?, Status: str?, CreatedTime: str?} @endpoint POST / @desc Get the specified schema by its unique ID assigned when a version of the schema is created or registered. Schema versions in Deleted status will not be included in the results. @optional {SchemaId: SchemaId, SchemaVersionId: str, SchemaVersionNumber: SchemaVersionNumber} @returns(200) {SchemaVersionId: str?, SchemaDefinition: str?, DataFormat: str?, SchemaArn: str?, VersionNumber: int(i64)?, Status: str?, CreatedTime: str?} @endpoint POST / @desc Fetches the schema version difference in the specified difference type between two stored schema versions in the Schema Registry. This API allows you to compare two schema versions between two schema definitions under the same schema. @required {SchemaId: SchemaId, FirstSchemaVersionNumber: SchemaVersionNumber, SecondSchemaVersionNumber: SchemaVersionNumber, SchemaDiffType: str} @returns(200) {Diff: str?} @endpoint POST / @desc Retrieves a specified security configuration. @required {Name: str} @returns(200) {SecurityConfiguration: SecurityConfiguration?{Name: str?, CreatedTimeStamp: str(timestamp)?, EncryptionConfiguration: EncryptionConfiguration?{S3Encryption: [S3Encryption]?, CloudWatchEncryption: CloudWatchEncryption?{CloudWatchEncryptionMode: str?, KmsKeyArn: str?}, JobBookmarksEncryption: JobBookmarksEncryption?{JobBookmarksEncryptionMode: str?, KmsKeyArn: str?}}}} @endpoint POST / @desc Retrieves a list of all security configurations. @optional {MaxResults: int, NextToken: str} @returns(200) {SecurityConfigurations: [SecurityConfiguration]?, NextToken: str?} @endpoint POST / @desc Retrieves the session. @required {Id: str} @optional {RequestOrigin: str} @returns(200) {Session: Session?{Id: str?, CreatedOn: str(timestamp)?, Status: str?, ErrorMessage: str?, Description: str?, Role: str?, Command: SessionCommand?{Name: str?, PythonVersion: str?}, DefaultArguments: map?, Connections: ConnectionsList?{Connections: [str]?}, Progress: num(f64)?, MaxCapacity: num(f64)?, SecurityConfiguration: str?, GlueVersion: str?, NumberOfWorkers: int?, WorkerType: str?, CompletedOn: str(timestamp)?, ExecutionTime: num(f64)?, DPUSeconds: num(f64)?, IdleTimeout: int?, ProfileName: str?}} @endpoint POST / @desc Retrieves the statement. @required {SessionId: str, Id: int} @optional {RequestOrigin: str} @returns(200) {Statement: Statement?{Id: int?, Code: str?, State: str?, Output: StatementOutput?{Data: StatementOutputData?{TextPlain: str?}, ExecutionCount: int?, Status: str?, ErrorName: str?, ErrorValue: str?, Traceback: [str]?}, Progress: num(f64)?, StartedOn: int(i64)?, CompletedOn: int(i64)?}} @endpoint POST / @desc Retrieves the Table definition in a Data Catalog for a specified table. @required {DatabaseName: str, Name: str} @optional {CatalogId: str, TransactionId: str, QueryAsOfTime: str(timestamp), IncludeStatusDetails: bool} @returns(200) {Table: Table?{Name: str, DatabaseName: str?, Description: str?, Owner: str?, CreateTime: str(timestamp)?, UpdateTime: str(timestamp)?, LastAccessTime: str(timestamp)?, LastAnalyzedTime: str(timestamp)?, Retention: int?, StorageDescriptor: StorageDescriptor?{Columns: [Column]?, Location: str?, AdditionalLocations: [str]?, InputFormat: str?, OutputFormat: str?, Compressed: bool?, NumberOfBuckets: int?, SerdeInfo: SerDeInfo?{Name: str?, SerializationLibrary: str?, Parameters: map?}, BucketColumns: [str]?, SortColumns: [Order]?, Parameters: map?, SkewedInfo: SkewedInfo?{SkewedColumnNames: [str]?, SkewedColumnValues: [str]?, SkewedColumnValueLocationMaps: map?}, StoredAsSubDirectories: bool?, SchemaReference: SchemaReference?{SchemaId: SchemaId?, SchemaVersionId: str?, SchemaVersionNumber: int(i64)?}}, PartitionKeys: [Column]?, ViewOriginalText: str?, ViewExpandedText: str?, TableType: str?, Parameters: map?, CreatedBy: str?, IsRegisteredWithLakeFormation: bool?, TargetTable: TableIdentifier?{CatalogId: str?, DatabaseName: str?, Name: str?, Region: str?}, CatalogId: str?, VersionId: str?, FederatedTable: FederatedTable?{Identifier: str?, DatabaseIdentifier: str?, ConnectionName: str?}, ViewDefinition: ViewDefinition?{IsProtected: bool?, Definer: str?, SubObjects: [str]?, Representations: [ViewRepresentation]?}, IsMultiDialectView: bool?, Status: TableStatus?{RequestedBy: str?, UpdatedBy: str?, RequestTime: str(timestamp)?, UpdateTime: str(timestamp)?, Action: str?, State: str?, Error: ErrorDetail?{ErrorCode: str?, ErrorMessage: str?}, Details: StatusDetails?{RequestedChange: any?, ViewValidations: [ViewValidation]?}}}} @endpoint POST / @desc Returns the configuration of all optimizers associated with a specified table. @required {CatalogId: str, DatabaseName: str, TableName: str, Type: str} @returns(200) {CatalogId: str?, DatabaseName: str?, TableName: str?, TableOptimizer: TableOptimizer?{type: str?, configuration: TableOptimizerConfiguration?{roleArn: str?, enabled: bool?}, lastRun: TableOptimizerRun?{eventType: str?, startTimestamp: str(timestamp)?, endTimestamp: str(timestamp)?, metrics: RunMetrics?{NumberOfBytesCompacted: str?, NumberOfFilesCompacted: str?, NumberOfDpus: str?, JobDurationInHour: str?}, error: str?}}} @endpoint POST / @desc Retrieves a specified version of a table. @required {DatabaseName: str, TableName: str} @optional {CatalogId: str, VersionId: str} @returns(200) {TableVersion: TableVersion?{Table: Table?{Name: str, DatabaseName: str?, Description: str?, Owner: str?, CreateTime: str(timestamp)?, UpdateTime: str(timestamp)?, LastAccessTime: str(timestamp)?, LastAnalyzedTime: str(timestamp)?, Retention: int?, StorageDescriptor: StorageDescriptor?{Columns: [Column]?, Location: str?, AdditionalLocations: [str]?, InputFormat: str?, OutputFormat: str?, Compressed: bool?, NumberOfBuckets: int?, SerdeInfo: SerDeInfo?, BucketColumns: [str]?, SortColumns: [Order]?, Parameters: map?, SkewedInfo: SkewedInfo?, StoredAsSubDirectories: bool?, SchemaReference: SchemaReference?}, PartitionKeys: [Column]?, ViewOriginalText: str?, ViewExpandedText: str?, TableType: str?, Parameters: map?, CreatedBy: str?, IsRegisteredWithLakeFormation: bool?, TargetTable: TableIdentifier?{CatalogId: str?, DatabaseName: str?, Name: str?, Region: str?}, CatalogId: str?, VersionId: str?, FederatedTable: FederatedTable?{Identifier: str?, DatabaseIdentifier: str?, ConnectionName: str?}, ViewDefinition: ViewDefinition?{IsProtected: bool?, Definer: str?, SubObjects: [str]?, Representations: [ViewRepresentation]?}, IsMultiDialectView: bool?, Status: TableStatus?{RequestedBy: str?, UpdatedBy: str?, RequestTime: str(timestamp)?, UpdateTime: str(timestamp)?, Action: str?, State: str?, Error: ErrorDetail?, Details: StatusDetails?}}, VersionId: str?}} @endpoint POST / @desc Retrieves a list of strings that identify available versions of a specified table. @required {DatabaseName: str, TableName: str} @optional {CatalogId: str, NextToken: str, MaxResults: int} @returns(200) {TableVersions: [TableVersion]?, NextToken: str?} @endpoint POST / @desc Retrieves the definitions of some or all of the tables in a given Database. @required {DatabaseName: str} @optional {CatalogId: str, Expression: str, NextToken: str, MaxResults: int, TransactionId: str, QueryAsOfTime: str(timestamp), IncludeStatusDetails: bool, AttributesToGet: [str]} @returns(200) {TableList: [Table]?, NextToken: str?} @endpoint POST / @desc Retrieves a list of tags associated with a resource. @required {ResourceArn: str} @returns(200) {Tags: map?} @endpoint POST / @desc Retrieves the definition of a trigger. @required {Name: str} @returns(200) {Trigger: Trigger?{Name: str?, WorkflowName: str?, Id: str?, Type: str?, State: str?, Description: str?, Schedule: str?, Actions: [Action]?, Predicate: Predicate?{Logical: str?, Conditions: [Condition]?}, EventBatchingCondition: EventBatchingCondition?{BatchSize: int, BatchWindow: int?}}} @endpoint POST / @desc Gets all the triggers associated with a job. @optional {NextToken: str, DependentJobName: str, MaxResults: int} @returns(200) {Triggers: [Trigger]?, NextToken: str?} @endpoint POST / @desc Retrieves partition metadata from the Data Catalog that contains unfiltered metadata. For IAM authorization, the public IAM action associated with this API is glue:GetPartition. @required {CatalogId: str, DatabaseName: str, TableName: str, PartitionValues: [str], SupportedPermissionTypes: [str]} @optional {Region: str, AuditContext: AuditContext, QuerySessionContext: QuerySessionContext} @returns(200) {Partition: Partition?{Values: [str]?, DatabaseName: str?, TableName: str?, CreationTime: str(timestamp)?, LastAccessTime: str(timestamp)?, StorageDescriptor: StorageDescriptor?{Columns: [Column]?, Location: str?, AdditionalLocations: [str]?, InputFormat: str?, OutputFormat: str?, Compressed: bool?, NumberOfBuckets: int?, SerdeInfo: SerDeInfo?{Name: str?, SerializationLibrary: str?, Parameters: map?}, BucketColumns: [str]?, SortColumns: [Order]?, Parameters: map?, SkewedInfo: SkewedInfo?{SkewedColumnNames: [str]?, SkewedColumnValues: [str]?, SkewedColumnValueLocationMaps: map?}, StoredAsSubDirectories: bool?, SchemaReference: SchemaReference?{SchemaId: SchemaId?, SchemaVersionId: str?, SchemaVersionNumber: int(i64)?}}, Parameters: map?, LastAnalyzedTime: str(timestamp)?, CatalogId: str?}, AuthorizedColumns: [str]?, IsRegisteredWithLakeFormation: bool?} @endpoint POST / @desc Retrieves partition metadata from the Data Catalog that contains unfiltered metadata. For IAM authorization, the public IAM action associated with this API is glue:GetPartitions. @required {CatalogId: str, DatabaseName: str, TableName: str, SupportedPermissionTypes: [str]} @optional {Region: str, Expression: str, AuditContext: AuditContext, NextToken: str, Segment: Segment, MaxResults: int, QuerySessionContext: QuerySessionContext} @returns(200) {UnfilteredPartitions: [UnfilteredPartition]?, NextToken: str?} @endpoint POST / @desc Allows a third-party analytical engine to retrieve unfiltered table metadata from the Data Catalog. For IAM authorization, the public IAM action associated with this API is glue:GetTable. @required {CatalogId: str, DatabaseName: str, Name: str, SupportedPermissionTypes: [str]} @optional {Region: str, AuditContext: AuditContext, ParentResourceArn: str, RootResourceArn: str, SupportedDialect: SupportedDialect, Permissions: [str], QuerySessionContext: QuerySessionContext} @returns(200) {Table: Table?{Name: str, DatabaseName: str?, Description: str?, Owner: str?, CreateTime: str(timestamp)?, UpdateTime: str(timestamp)?, LastAccessTime: str(timestamp)?, LastAnalyzedTime: str(timestamp)?, Retention: int?, StorageDescriptor: StorageDescriptor?{Columns: [Column]?, Location: str?, AdditionalLocations: [str]?, InputFormat: str?, OutputFormat: str?, Compressed: bool?, NumberOfBuckets: int?, SerdeInfo: SerDeInfo?{Name: str?, SerializationLibrary: str?, Parameters: map?}, BucketColumns: [str]?, SortColumns: [Order]?, Parameters: map?, SkewedInfo: SkewedInfo?{SkewedColumnNames: [str]?, SkewedColumnValues: [str]?, SkewedColumnValueLocationMaps: map?}, StoredAsSubDirectories: bool?, SchemaReference: SchemaReference?{SchemaId: SchemaId?, SchemaVersionId: str?, SchemaVersionNumber: int(i64)?}}, PartitionKeys: [Column]?, ViewOriginalText: str?, ViewExpandedText: str?, TableType: str?, Parameters: map?, CreatedBy: str?, IsRegisteredWithLakeFormation: bool?, TargetTable: TableIdentifier?{CatalogId: str?, DatabaseName: str?, Name: str?, Region: str?}, CatalogId: str?, VersionId: str?, FederatedTable: FederatedTable?{Identifier: str?, DatabaseIdentifier: str?, ConnectionName: str?}, ViewDefinition: ViewDefinition?{IsProtected: bool?, Definer: str?, SubObjects: [str]?, Representations: [ViewRepresentation]?}, IsMultiDialectView: bool?, Status: TableStatus?{RequestedBy: str?, UpdatedBy: str?, RequestTime: str(timestamp)?, UpdateTime: str(timestamp)?, Action: str?, State: str?, Error: ErrorDetail?{ErrorCode: str?, ErrorMessage: str?}, Details: StatusDetails?{RequestedChange: any?, ViewValidations: [ViewValidation]?}}}, AuthorizedColumns: [str]?, IsRegisteredWithLakeFormation: bool?, CellFilters: [ColumnRowFilter]?, QueryAuthorizationId: str?, IsMultiDialectView: bool?, ResourceArn: str?, IsProtected: bool?, Permissions: [str]?, RowFilter: str?} @endpoint POST / @desc Retrieves information about the specified Glue usage profile. @required {Name: str} @returns(200) {Name: str?, Description: str?, Configuration: ProfileConfiguration?{SessionConfiguration: map?, JobConfiguration: map?}, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?} @endpoint POST / @desc Retrieves a specified function definition from the Data Catalog. @required {DatabaseName: str, FunctionName: str} @optional {CatalogId: str} @returns(200) {UserDefinedFunction: UserDefinedFunction?{FunctionName: str?, DatabaseName: str?, ClassName: str?, OwnerName: str?, OwnerType: str?, CreateTime: str(timestamp)?, ResourceUris: [ResourceUri]?, CatalogId: str?}} @endpoint POST / @desc Retrieves multiple function definitions from the Data Catalog. @required {Pattern: str} @optional {CatalogId: str, DatabaseName: str, NextToken: str, MaxResults: int} @returns(200) {UserDefinedFunctions: [UserDefinedFunction]?, NextToken: str?} @endpoint POST / @desc Retrieves resource metadata for a workflow. @required {Name: str} @optional {IncludeGraph: bool} @returns(200) {Workflow: Workflow?{Name: str?, Description: str?, DefaultRunProperties: map?, CreatedOn: str(timestamp)?, LastModifiedOn: str(timestamp)?, LastRun: WorkflowRun?{Name: str?, WorkflowRunId: str?, PreviousRunId: str?, WorkflowRunProperties: map?, StartedOn: str(timestamp)?, CompletedOn: str(timestamp)?, Status: str?, ErrorMessage: str?, Statistics: WorkflowRunStatistics?{TotalActions: int?, TimeoutActions: int?, FailedActions: int?, StoppedActions: int?, SucceededActions: int?, RunningActions: int?, ErroredActions: int?, WaitingActions: int?}, Graph: WorkflowGraph?{Nodes: [Node]?, Edges: [Edge]?}, StartingEventBatchCondition: StartingEventBatchCondition?{BatchSize: int?, BatchWindow: int?}}, Graph: WorkflowGraph?{Nodes: [Node]?, Edges: [Edge]?}, MaxConcurrentRuns: int?, BlueprintDetails: BlueprintDetails?{BlueprintName: str?, RunId: str?}}} @endpoint POST / @desc Retrieves the metadata for a given workflow run. Job run history is accessible for 90 days for your workflow and job run. @required {Name: str, RunId: str} @optional {IncludeGraph: bool} @returns(200) {Run: WorkflowRun?{Name: str?, WorkflowRunId: str?, PreviousRunId: str?, WorkflowRunProperties: map?, StartedOn: str(timestamp)?, CompletedOn: str(timestamp)?, Status: str?, ErrorMessage: str?, Statistics: WorkflowRunStatistics?{TotalActions: int?, TimeoutActions: int?, FailedActions: int?, StoppedActions: int?, SucceededActions: int?, RunningActions: int?, ErroredActions: int?, WaitingActions: int?}, Graph: WorkflowGraph?{Nodes: [Node]?, Edges: [Edge]?}, StartingEventBatchCondition: StartingEventBatchCondition?{BatchSize: int?, BatchWindow: int?}}} @endpoint POST / @desc Retrieves the workflow run properties which were set during the run. @required {Name: str, RunId: str} @returns(200) {RunProperties: map?} @endpoint POST / @desc Retrieves metadata for all runs of a given workflow. @required {Name: str} @optional {IncludeGraph: bool, NextToken: str, MaxResults: int} @returns(200) {Runs: [WorkflowRun]?, NextToken: str?} @endpoint POST / @desc Imports an existing Amazon Athena Data Catalog to Glue. @optional {CatalogId: str} @endpoint POST / @desc Lists all the blueprint names in an account. @optional {NextToken: str, MaxResults: int, Tags: map} @returns(200) {Blueprints: [str]?, NextToken: str?} @endpoint POST / @desc List all task runs for a particular account. @optional {MaxResults: int, NextToken: str} @returns(200) {ColumnStatisticsTaskRunIds: [str]?, NextToken: str?} @endpoint POST / @desc Retrieves the names of all crawler resources in this Amazon Web Services account, or the resources with the specified tag. This operation allows you to see which resources are available in your account, and their names. This operation takes the optional Tags field, which you can use as a filter on the response so that tagged resources can be retrieved as a group. If you choose to use tags filtering, only resources with the tag are retrieved. @optional {MaxResults: int, NextToken: str, Tags: map} @returns(200) {CrawlerNames: [str]?, NextToken: str?} @endpoint POST / @desc Returns all the crawls of a specified crawler. Returns only the crawls that have occurred since the launch date of the crawler history feature, and only retains up to 12 months of crawls. Older crawls will not be returned. You may use this API to: Retrive all the crawls of a specified crawler. Retrieve all the crawls of a specified crawler within a limited count. Retrieve all the crawls of a specified crawler in a specific time range. Retrieve all the crawls of a specified crawler with a particular state, crawl ID, or DPU hour value. @required {CrawlerName: str} @optional {MaxResults: int, Filters: [CrawlsFilter], NextToken: str} @returns(200) {Crawls: [CrawlerHistory]?, NextToken: str?} @endpoint POST / @desc Lists all the custom patterns that have been created. @optional {NextToken: str, MaxResults: int, Tags: map} @returns(200) {CustomEntityTypes: [CustomEntityType]?, NextToken: str?} @endpoint POST / @desc Returns all data quality execution results for your account. @optional {Filter: DataQualityResultFilterCriteria, NextToken: str, MaxResults: int} @returns(200) {Results: [DataQualityResultDescription], NextToken: str?} @endpoint POST / @desc Lists the recommendation runs meeting the filter criteria. @optional {Filter: DataQualityRuleRecommendationRunFilter, NextToken: str, MaxResults: int} @returns(200) {Runs: [DataQualityRuleRecommendationRunDescription]?, NextToken: str?} @endpoint POST / @desc Lists all the runs meeting the filter criteria, where a ruleset is evaluated against a data source. @optional {Filter: DataQualityRulesetEvaluationRunFilter, NextToken: str, MaxResults: int} @returns(200) {Runs: [DataQualityRulesetEvaluationRunDescription]?, NextToken: str?} @endpoint POST / @desc Returns a paginated list of rulesets for the specified list of Glue tables. @optional {NextToken: str, MaxResults: int, Filter: DataQualityRulesetFilterCriteria, Tags: map} @returns(200) {Rulesets: [DataQualityRulesetListDetails]?, NextToken: str?} @endpoint POST / @desc Retrieve annotations for a data quality statistic. @optional {StatisticId: str, ProfileId: str, TimestampFilter: TimestampFilter, MaxResults: int, NextToken: str} @returns(200) {Annotations: [StatisticAnnotation]?, NextToken: str?} @endpoint POST / @desc Retrieves a list of data quality statistics. @optional {StatisticId: str, ProfileId: str, TimestampFilter: TimestampFilter, MaxResults: int, NextToken: str} @returns(200) {Statistics: [StatisticSummary]?, NextToken: str?} @endpoint POST / @desc Retrieves the names of all DevEndpoint resources in this Amazon Web Services account, or the resources with the specified tag. This operation allows you to see which resources are available in your account, and their names. This operation takes the optional Tags field, which you can use as a filter on the response so that tagged resources can be retrieved as a group. If you choose to use tags filtering, only resources with the tag are retrieved. @optional {NextToken: str, MaxResults: int, Tags: map} @returns(200) {DevEndpointNames: [str]?, NextToken: str?} @endpoint POST / @desc Retrieves the names of all job resources in this Amazon Web Services account, or the resources with the specified tag. This operation allows you to see which resources are available in your account, and their names. This operation takes the optional Tags field, which you can use as a filter on the response so that tagged resources can be retrieved as a group. If you choose to use tags filtering, only resources with the tag are retrieved. @optional {NextToken: str, MaxResults: int, Tags: map} @returns(200) {JobNames: [str]?, NextToken: str?} @endpoint POST / @desc Retrieves a sortable, filterable list of existing Glue machine learning transforms in this Amazon Web Services account, or the resources with the specified tag. This operation takes the optional Tags field, which you can use as a filter of the responses so that tagged resources can be retrieved as a group. If you choose to use tag filtering, only resources with the tags are retrieved. @optional {NextToken: str, MaxResults: int, Filter: TransformFilterCriteria, Sort: TransformSortCriteria, Tags: map} @returns(200) {TransformIds: [str], NextToken: str?} @endpoint POST / @desc Returns a list of registries that you have created, with minimal registry information. Registries in the Deleting status will not be included in the results. Empty results will be returned if there are no registries available. @optional {MaxResults: int, NextToken: str} @returns(200) {Registries: [RegistryListItem]?, NextToken: str?} @endpoint POST / @desc Returns a list of schema versions that you have created, with minimal information. Schema versions in Deleted status will not be included in the results. Empty results will be returned if there are no schema versions available. @required {SchemaId: SchemaId} @optional {MaxResults: int, NextToken: str} @returns(200) {Schemas: [SchemaVersionListItem]?, NextToken: str?} @endpoint POST / @desc Returns a list of schemas with minimal details. Schemas in Deleting status will not be included in the results. Empty results will be returned if there are no schemas available. When the RegistryId is not provided, all the schemas across registries will be part of the API response. @optional {RegistryId: RegistryId, MaxResults: int, NextToken: str} @returns(200) {Schemas: [SchemaListItem]?, NextToken: str?} @endpoint POST / @desc Retrieve a list of sessions. @optional {NextToken: str, MaxResults: int, Tags: map, RequestOrigin: str} @returns(200) {Ids: [str]?, Sessions: [Session]?, NextToken: str?} @endpoint POST / @desc Lists statements for the session. @required {SessionId: str} @optional {RequestOrigin: str, NextToken: str} @returns(200) {Statements: [Statement]?, NextToken: str?} @endpoint POST / @desc Lists the history of previous optimizer runs for a specific table. @required {CatalogId: str, DatabaseName: str, TableName: str, Type: str} @optional {MaxResults: int, NextToken: str} @returns(200) {CatalogId: str?, DatabaseName: str?, TableName: str?, NextToken: str?, TableOptimizerRuns: [TableOptimizerRun]?} @endpoint POST / @desc Retrieves the names of all trigger resources in this Amazon Web Services account, or the resources with the specified tag. This operation allows you to see which resources are available in your account, and their names. This operation takes the optional Tags field, which you can use as a filter on the response so that tagged resources can be retrieved as a group. If you choose to use tags filtering, only resources with the tag are retrieved. @optional {NextToken: str, DependentJobName: str, MaxResults: int, Tags: map} @returns(200) {TriggerNames: [str]?, NextToken: str?} @endpoint POST / @desc List all the Glue usage profiles. @optional {NextToken: str, MaxResults: int} @returns(200) {Profiles: [UsageProfileDefinition]?, NextToken: str?} @endpoint POST / @desc Lists names of workflows created in the account. @optional {NextToken: str, MaxResults: int} @returns(200) {Workflows: [str]?, NextToken: str?} @endpoint POST / @desc Sets the security configuration for a specified catalog. After the configuration has been set, the specified encryption is applied to every catalog write thereafter. @required {DataCatalogEncryptionSettings: DataCatalogEncryptionSettings} @optional {CatalogId: str} @endpoint POST / @desc Annotate all datapoints for a Profile. @required {ProfileId: str, InclusionAnnotation: str} @endpoint POST / @desc Sets the Data Catalog resource policy for access control. @required {PolicyInJson: str} @optional {ResourceArn: str, PolicyHashCondition: str, PolicyExistsCondition: str, EnableHybrid: str} @returns(200) {PolicyHash: str?} @endpoint POST / @desc Puts the metadata key value pair for a specified schema version ID. A maximum of 10 key value pairs will be allowed per schema version. They can be added over one or more calls. @required {MetadataKeyValue: MetadataKeyValuePair} @optional {SchemaId: SchemaId, SchemaVersionNumber: SchemaVersionNumber, SchemaVersionId: str} @returns(200) {SchemaArn: str?, SchemaName: str?, RegistryName: str?, LatestVersion: bool?, VersionNumber: int(i64)?, SchemaVersionId: str?, MetadataKey: str?, MetadataValue: str?} @endpoint POST / @desc Puts the specified workflow run properties for the given workflow run. If a property already exists for the specified run, then it overrides the value otherwise adds the property to existing properties. @required {Name: str, RunId: str, RunProperties: map} @endpoint POST / @desc Queries for the schema version metadata information. @optional {SchemaId: SchemaId, SchemaVersionNumber: SchemaVersionNumber, SchemaVersionId: str, MetadataList: [MetadataKeyValuePair], MaxResults: int, NextToken: str} @returns(200) {MetadataInfoMap: map?, SchemaVersionId: str?, NextToken: str?} @endpoint POST / @desc Adds a new version to the existing schema. Returns an error if new version of schema does not meet the compatibility requirements of the schema set. This API will not create a new schema set and will return a 404 error if the schema set is not already present in the Schema Registry. If this is the first schema definition to be registered in the Schema Registry, this API will store the schema version and return immediately. Otherwise, this call has the potential to run longer than other operations due to compatibility modes. You can call the GetSchemaVersion API with the SchemaVersionId to check compatibility modes. If the same schema definition is already stored in Schema Registry as a version, the schema ID of the existing schema is returned to the caller. @required {SchemaId: SchemaId, SchemaDefinition: str} @returns(200) {SchemaVersionId: str?, VersionNumber: int(i64)?, Status: str?} @endpoint POST / @desc Removes a key value pair from the schema version metadata for the specified schema version ID. @required {MetadataKeyValue: MetadataKeyValuePair} @optional {SchemaId: SchemaId, SchemaVersionNumber: SchemaVersionNumber, SchemaVersionId: str} @returns(200) {SchemaArn: str?, SchemaName: str?, RegistryName: str?, LatestVersion: bool?, VersionNumber: int(i64)?, SchemaVersionId: str?, MetadataKey: str?, MetadataValue: str?} @endpoint POST / @desc Resets a bookmark entry. For more information about enabling and using job bookmarks, see: Tracking processed data using job bookmarks Job parameters used by Glue Job structure @required {JobName: str} @optional {RunId: str} @returns(200) {JobBookmarkEntry: JobBookmarkEntry?{JobName: str?, Version: int?, Run: int?, Attempt: int?, PreviousRunId: str?, RunId: str?, JobBookmark: str?}} @endpoint POST / @desc Restarts selected nodes of a previous partially completed workflow run and resumes the workflow run. The selected nodes and all nodes that are downstream from the selected nodes are run. @required {Name: str, RunId: str, NodeIds: [str]} @returns(200) {RunId: str?, NodeIds: [str]?} @endpoint POST / @desc Executes the statement. @required {SessionId: str, Code: str} @optional {RequestOrigin: str} @returns(200) {Id: int?} @endpoint POST / @desc Searches a set of tables based on properties in the table metadata as well as on the parent database. You can search against text or filter conditions. You can only get tables that you have access to based on the security policies defined in Lake Formation. You need at least a read-only access to the table for it to be returned. If you do not have access to all the columns in the table, these columns will not be searched against when returning the list of tables back to you. If you have access to the columns but not the data in the columns, those columns and the associated metadata for those columns will be included in the search. @optional {CatalogId: str, NextToken: str, Filters: [PropertyPredicate], SearchText: str, SortCriteria: [SortCriterion], MaxResults: int, ResourceShareType: str, IncludeStatusDetails: bool} @returns(200) {NextToken: str?, TableList: [Table]?} @endpoint POST / @desc Starts a new run of the specified blueprint. @required {BlueprintName: str, RoleArn: str} @optional {Parameters: str} @returns(200) {RunId: str?} @endpoint POST / @desc Starts a column statistics task run, for a specified table and columns. @required {DatabaseName: str, TableName: str, Role: str} @optional {ColumnNameList: [str], SampleSize: num(f64), CatalogID: str, SecurityConfiguration: str} @returns(200) {ColumnStatisticsTaskRunId: str?} @endpoint POST / @desc Starts a crawl using the specified crawler, regardless of what is scheduled. If the crawler is already running, returns a CrawlerRunningException. @required {Name: str} @endpoint POST / @desc Changes the schedule state of the specified crawler to SCHEDULED, unless the crawler is already running or the schedule state is already SCHEDULED. @required {CrawlerName: str} @endpoint POST / @desc Starts a recommendation run that is used to generate rules when you don't know what rules to write. Glue Data Quality analyzes the data and comes up with recommendations for a potential ruleset. You can then triage the ruleset and modify the generated ruleset to your liking. Recommendation runs are automatically deleted after 90 days. @required {DataSource: DataSource, Role: str} @optional {NumberOfWorkers: int, Timeout: int, CreatedRulesetName: str, DataQualitySecurityConfiguration: str, ClientToken: str} @returns(200) {RunId: str?} @endpoint POST / @desc Once you have a ruleset definition (either recommended or your own), you call this operation to evaluate the ruleset against a data source (Glue table). The evaluation computes results which you can retrieve with the GetDataQualityResult API. @required {DataSource: DataSource, Role: str, RulesetNames: [str]} @optional {NumberOfWorkers: int, Timeout: int, ClientToken: str, AdditionalRunOptions: DataQualityEvaluationRunAdditionalRunOptions, AdditionalDataSources: map} @returns(200) {RunId: str?} @endpoint POST / @desc Begins an asynchronous task to export all labeled data for a particular transform. This task is the only label-related API call that is not part of the typical active learning workflow. You typically use StartExportLabelsTaskRun when you want to work with all of your existing labels at the same time, such as when you want to remove or change labels that were previously submitted as truth. This API operation accepts the TransformId whose labels you want to export and an Amazon Simple Storage Service (Amazon S3) path to export the labels to. The operation returns a TaskRunId. You can check on the status of your task run by calling the GetMLTaskRun API. @required {TransformId: str, OutputS3Path: str} @returns(200) {TaskRunId: str?} @endpoint POST / @desc Enables you to provide additional labels (examples of truth) to be used to teach the machine learning transform and improve its quality. This API operation is generally used as part of the active learning workflow that starts with the StartMLLabelingSetGenerationTaskRun call and that ultimately results in improving the quality of your machine learning transform. After the StartMLLabelingSetGenerationTaskRun finishes, Glue machine learning will have generated a series of questions for humans to answer. (Answering these questions is often called 'labeling' in the machine learning workflows). In the case of the FindMatches transform, these questions are of the form, “What is the correct way to group these rows together into groups composed entirely of matching records?” After the labeling process is finished, users upload their answers/labels with a call to StartImportLabelsTaskRun. After StartImportLabelsTaskRun finishes, all future runs of the machine learning transform use the new and improved labels and perform a higher-quality transformation. By default, StartMLLabelingSetGenerationTaskRun continually learns from and combines all labels that you upload unless you set Replace to true. If you set Replace to true, StartImportLabelsTaskRun deletes and forgets all previously uploaded labels and learns only from the exact set that you upload. Replacing labels can be helpful if you realize that you previously uploaded incorrect labels, and you believe that they are having a negative effect on your transform quality. You can check on the status of your task run by calling the GetMLTaskRun operation. @required {TransformId: str, InputS3Path: str} @optional {ReplaceAllLabels: bool} @returns(200) {TaskRunId: str?} @endpoint POST / @desc Starts a job run using a job definition. @required {JobName: str} @optional {JobRunQueuingEnabled: bool, JobRunId: str, Arguments: map, AllocatedCapacity: int, Timeout: int, MaxCapacity: num(f64), SecurityConfiguration: str, NotificationProperty: NotificationProperty, WorkerType: str, NumberOfWorkers: int, ExecutionClass: str} @returns(200) {JobRunId: str?} @endpoint POST / @desc Starts a task to estimate the quality of the transform. When you provide label sets as examples of truth, Glue machine learning uses some of those examples to learn from them. The rest of the labels are used as a test to estimate quality. Returns a unique identifier for the run. You can call GetMLTaskRun to get more information about the stats of the EvaluationTaskRun. @required {TransformId: str} @returns(200) {TaskRunId: str?} @endpoint POST / @desc Starts the active learning workflow for your machine learning transform to improve the transform's quality by generating label sets and adding labels. When the StartMLLabelingSetGenerationTaskRun finishes, Glue will have generated a "labeling set" or a set of questions for humans to answer. In the case of the FindMatches transform, these questions are of the form, “What is the correct way to group these rows together into groups composed entirely of matching records?” After the labeling process is finished, you can upload your labels with a call to StartImportLabelsTaskRun. After StartImportLabelsTaskRun finishes, all future runs of the machine learning transform will use the new and improved labels and perform a higher-quality transformation. @required {TransformId: str, OutputS3Path: str} @returns(200) {TaskRunId: str?} @endpoint POST / @desc Starts an existing trigger. See Triggering Jobs for information about how different types of trigger are started. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Starts a new run of the specified workflow. @required {Name: str} @optional {RunProperties: map} @returns(200) {RunId: str?} @endpoint POST / @desc Stops a task run for the specified table. @required {DatabaseName: str, TableName: str} @endpoint POST / @desc If the specified crawler is running, stops the crawl. @required {Name: str} @endpoint POST / @desc Sets the schedule state of the specified crawler to NOT_SCHEDULED, but does not stop the crawler if it is already running. @required {CrawlerName: str} @endpoint POST / @desc Stops the session. @required {Id: str} @optional {RequestOrigin: str} @returns(200) {Id: str?} @endpoint POST / @desc Stops a specified trigger. @required {Name: str} @returns(200) {Name: str?} @endpoint POST / @desc Stops the execution of the specified workflow run. @required {Name: str, RunId: str} @endpoint POST / @desc Adds tags to a resource. A tag is a label you can assign to an Amazon Web Services resource. In Glue, you can tag only certain resources. For information about what resources you can tag, see Amazon Web Services Tags in Glue. @required {ResourceArn: str, TagsToAdd: map} @endpoint POST / @desc Removes tags from a resource. @required {ResourceArn: str, TagsToRemove: [str]} @endpoint POST / @desc Updates a registered blueprint. @required {Name: str, BlueprintLocation: str} @optional {Description: str} @returns(200) {Name: str?} @endpoint POST / @desc Modifies an existing classifier (a GrokClassifier, an XMLClassifier, a JsonClassifier, or a CsvClassifier, depending on which field is present). @optional {GrokClassifier: UpdateGrokClassifierRequest, XMLClassifier: UpdateXMLClassifierRequest, JsonClassifier: UpdateJsonClassifierRequest, CsvClassifier: UpdateCsvClassifierRequest} @endpoint POST / @desc Creates or updates partition statistics of columns. The Identity and Access Management (IAM) permission required for this operation is UpdatePartition. @required {DatabaseName: str, TableName: str, PartitionValues: [str], ColumnStatisticsList: [ColumnStatistics]} @optional {CatalogId: str} @returns(200) {Errors: [ColumnStatisticsError]?} @endpoint POST / @desc Creates or updates table statistics of columns. The Identity and Access Management (IAM) permission required for this operation is UpdateTable. @required {DatabaseName: str, TableName: str, ColumnStatisticsList: [ColumnStatistics]} @optional {CatalogId: str} @returns(200) {Errors: [ColumnStatisticsError]?} @endpoint POST / @desc Updates a connection definition in the Data Catalog. @required {Name: str, ConnectionInput: ConnectionInput} @optional {CatalogId: str} @endpoint POST / @desc Updates a crawler. If a crawler is running, you must stop it using StopCrawler before updating it. @required {Name: str} @optional {Role: str, DatabaseName: str, Description: str, Targets: CrawlerTargets, Schedule: str, Classifiers: [str], TablePrefix: str, SchemaChangePolicy: SchemaChangePolicy, RecrawlPolicy: RecrawlPolicy, LineageConfiguration: LineageConfiguration, LakeFormationConfiguration: LakeFormationConfiguration, Configuration: str, CrawlerSecurityConfiguration: str} @endpoint POST / @desc Updates the schedule of a crawler using a cron expression. @required {CrawlerName: str} @optional {Schedule: str} @endpoint POST / @desc Updates the specified data quality ruleset. @required {Name: str} @optional {Description: str, Ruleset: str} @returns(200) {Name: str?, Description: str?, Ruleset: str?} @endpoint POST / @desc Updates an existing database definition in a Data Catalog. @required {Name: str, DatabaseInput: DatabaseInput} @optional {CatalogId: str} @endpoint POST / @desc Updates a specified development endpoint. @required {EndpointName: str} @optional {PublicKey: str, AddPublicKeys: [str], DeletePublicKeys: [str], CustomLibraries: DevEndpointCustomLibraries, UpdateEtlLibraries: bool, DeleteArguments: [str], AddArguments: map} @endpoint POST / @desc Updates an existing job definition. The previous job definition is completely overwritten by this information. @required {JobName: str, JobUpdate: JobUpdate} @returns(200) {JobName: str?} @endpoint POST / @desc Synchronizes a job from the source control repository. This operation takes the job artifacts that are located in the remote repository and updates the Glue internal stores with these artifacts. This API supports optional parameters which take in the repository information. @optional {JobName: str, Provider: str, RepositoryName: str, RepositoryOwner: str, BranchName: str, Folder: str, CommitId: str, AuthStrategy: str, AuthToken: str} @returns(200) {JobName: str?} @endpoint POST / @desc Updates an existing machine learning transform. Call this operation to tune the algorithm parameters to achieve better results. After calling this operation, you can call the StartMLEvaluationTaskRun operation to assess how well your new parameters achieved your goals (such as improving the quality of your machine learning transform, or making it more cost-effective). @required {TransformId: str} @optional {Name: str, Description: str, Parameters: TransformParameters, Role: str, GlueVersion: str, MaxCapacity: num(f64), WorkerType: str, NumberOfWorkers: int, Timeout: int, MaxRetries: int} @returns(200) {TransformId: str?} @endpoint POST / @desc Updates a partition. @required {DatabaseName: str, TableName: str, PartitionValueList: [str], PartitionInput: PartitionInput} @optional {CatalogId: str} @endpoint POST / @desc Updates an existing registry which is used to hold a collection of schemas. The updated properties relate to the registry, and do not modify any of the schemas within the registry. @required {RegistryId: RegistryId, Description: str} @returns(200) {RegistryName: str?, RegistryArn: str?} @endpoint POST / @desc Updates the description, compatibility setting, or version checkpoint for a schema set. For updating the compatibility setting, the call will not validate compatibility for the entire set of schema versions with the new compatibility setting. If the value for Compatibility is provided, the VersionNumber (a checkpoint) is also required. The API will validate the checkpoint version number for consistency. If the value for the VersionNumber (checkpoint) is provided, Compatibility is optional and this can be used to set/reset a checkpoint for the schema. This update will happen only if the schema is in the AVAILABLE state. @required {SchemaId: SchemaId} @optional {SchemaVersionNumber: SchemaVersionNumber, Compatibility: str, Description: str} @returns(200) {SchemaArn: str?, SchemaName: str?, RegistryName: str?} @endpoint POST / @desc Synchronizes a job to the source control repository. This operation takes the job artifacts from the Glue internal stores and makes a commit to the remote repository that is configured on the job. This API supports optional parameters which take in the repository information. @optional {JobName: str, Provider: str, RepositoryName: str, RepositoryOwner: str, BranchName: str, Folder: str, CommitId: str, AuthStrategy: str, AuthToken: str} @returns(200) {JobName: str?} @endpoint POST / @desc Updates a metadata table in the Data Catalog. @required {DatabaseName: str, TableInput: TableInput} @optional {CatalogId: str, SkipArchive: bool, TransactionId: str, VersionId: str, ViewUpdateAction: str, Force: bool} @endpoint POST / @desc Updates the configuration for an existing table optimizer. @required {CatalogId: str, DatabaseName: str, TableName: str, Type: str, TableOptimizerConfiguration: TableOptimizerConfiguration} @endpoint POST / @desc Updates a trigger definition. @required {Name: str, TriggerUpdate: TriggerUpdate} @returns(200) {Trigger: Trigger?{Name: str?, WorkflowName: str?, Id: str?, Type: str?, State: str?, Description: str?, Schedule: str?, Actions: [Action]?, Predicate: Predicate?{Logical: str?, Conditions: [Condition]?}, EventBatchingCondition: EventBatchingCondition?{BatchSize: int, BatchWindow: int?}}} @endpoint POST / @desc Update an Glue usage profile. @required {Name: str, Configuration: ProfileConfiguration} @optional {Description: str} @returns(200) {Name: str?} @endpoint POST / @desc Updates an existing function definition in the Data Catalog. @required {DatabaseName: str, FunctionName: str, FunctionInput: UserDefinedFunctionInput} @optional {CatalogId: str} @endpoint POST / @desc Updates an existing workflow. @required {Name: str} @optional {Description: str, DefaultRunProperties: map, MaxConcurrentRuns: int} @returns(200) {Name: str?} @end