2024/08/08 - AWS Glue - 15 updated api methods
Changes This release adds support to retrieve the validation status when creating or updating Glue Data Catalog Views. Also added is support for BasicCatalogTarget partition keys.
{'Jobs': {'CodeGenConfigurationNodes': {'CatalogTarget': {'PartitionKeys': [['string']]}}}}
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.
See also: AWS API Documentation
Request Syntax
client.batch_get_jobs(
JobNames=[
'string',
]
)
list
[REQUIRED]
A list of job names, which might be the names returned from the ListJobs operation.
(string) --
dict
Response Syntax
{
'Jobs': [
{
'Name': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'Description': 'string',
'LogUri': 'string',
'Role': 'string',
'CreatedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'ExecutionProperty': {
'MaxConcurrentRuns': 123
},
'Command': {
'Name': 'string',
'ScriptLocation': 'string',
'PythonVersion': 'string',
'Runtime': 'string'
},
'DefaultArguments': {
'string': 'string'
},
'NonOverridableArguments': {
'string': 'string'
},
'Connections': {
'Connections': [
'string',
]
},
'MaxRetries': 123,
'AllocatedCapacity': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'CodeGenConfigurationNodes': {
'string': {
'AthenaConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'ConnectionTable': 'string',
'SchemaName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'JDBCConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'FilterPredicate': 'string',
'PartitionColumn': 'string',
'LowerBound': 123,
'UpperBound': 123,
'NumPartitions': 123,
'JobBookmarkKeys': [
'string',
],
'JobBookmarkKeysSortOrder': 'string',
'DataTypeMapping': {
'string': 'DATE'|'STRING'|'TIMESTAMP'|'INT'|'FLOAT'|'LONG'|'BIGDECIMAL'|'BYTE'|'SHORT'|'DOUBLE'
}
},
'ConnectionTable': 'string',
'Query': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'RedshiftSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string'
},
'S3CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'S3CsvSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'Separator': 'comma'|'ctrla'|'pipe'|'semicolon'|'tab',
'Escaper': 'string',
'QuoteChar': 'quote'|'quillemet'|'single_quote'|'disabled',
'Multiline': True|False,
'WithHeader': True|False,
'WriteHeader': True|False,
'SkipFirst': True|False,
'OptimizePerformance': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3JsonSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'JsonPath': 'string',
'Multiline': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3ParquetSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'RelationalCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'DynamoDBCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'JDBCConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectionTable': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Database': 'string',
'Table': 'string'
},
'RedshiftTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string',
'UpsertRedshiftOptions': {
'TableLocation': 'string',
'ConnectionName': 'string',
'UpsertKeys': [
'string',
]
}
},
'S3CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3GlueParquetTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'S3DirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'string',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'ApplyMapping': {
'Name': 'string',
'Inputs': [
'string',
],
'Mapping': [
{
'ToKey': 'string',
'FromPath': [
'string',
],
'FromType': 'string',
'ToType': 'string',
'Dropped': True|False,
'Children': {'... recursive ...'}
},
]
},
'SelectFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'DropFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'RenameField': {
'Name': 'string',
'Inputs': [
'string',
],
'SourcePath': [
'string',
],
'TargetPath': [
'string',
]
},
'Spigot': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Topk': 123,
'Prob': 123.0
},
'Join': {
'Name': 'string',
'Inputs': [
'string',
],
'JoinType': 'equijoin'|'left'|'right'|'outer'|'leftsemi'|'leftanti',
'Columns': [
{
'From': 'string',
'Keys': [
[
'string',
],
]
},
]
},
'SplitFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'SelectFromCollection': {
'Name': 'string',
'Inputs': [
'string',
],
'Index': 123
},
'FillMissingValues': {
'Name': 'string',
'Inputs': [
'string',
],
'ImputedPath': 'string',
'FilledPath': 'string'
},
'Filter': {
'Name': 'string',
'Inputs': [
'string',
],
'LogicalOperator': 'AND'|'OR',
'Filters': [
{
'Operation': 'EQ'|'LT'|'GT'|'LTE'|'GTE'|'REGEX'|'ISNULL',
'Negated': True|False,
'Values': [
{
'Type': 'COLUMNEXTRACTED'|'CONSTANT',
'Value': [
'string',
]
},
]
},
]
},
'CustomCode': {
'Name': 'string',
'Inputs': [
'string',
],
'Code': 'string',
'ClassName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkSQL': {
'Name': 'string',
'Inputs': [
'string',
],
'SqlQuery': 'string',
'SqlAliases': [
{
'From': 'string',
'Alias': 'string'
},
],
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'DirectKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DirectKafkaSource': {
'Name': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'WindowSize': 123,
'DetectSchema': True|False,
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKafkaSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DropNullFields': {
'Name': 'string',
'Inputs': [
'string',
],
'NullCheckBoxList': {
'IsEmpty': True|False,
'IsNullString': True|False,
'IsNegOne': True|False
},
'NullTextList': [
{
'Value': 'string',
'Datatype': {
'Id': 'string',
'Label': 'string'
}
},
]
},
'Merge': {
'Name': 'string',
'Inputs': [
'string',
],
'Source': 'string',
'PrimaryKeys': [
[
'string',
],
]
},
'Union': {
'Name': 'string',
'Inputs': [
'string',
],
'UnionType': 'ALL'|'DISTINCT'
},
'PIIDetection': {
'Name': 'string',
'Inputs': [
'string',
],
'PiiType': 'RowAudit'|'RowMasking'|'ColumnAudit'|'ColumnMasking',
'EntityTypesToDetect': [
'string',
],
'OutputColumnName': 'string',
'SampleFraction': 123.0,
'ThresholdFraction': 123.0,
'MaskValue': 'string'
},
'Aggregate': {
'Name': 'string',
'Inputs': [
'string',
],
'Groups': [
[
'string',
],
],
'Aggs': [
{
'Column': [
'string',
],
'AggFunc': 'avg'|'countDistinct'|'count'|'first'|'last'|'kurtosis'|'max'|'min'|'skewness'|'stddev_samp'|'stddev_pop'|'sum'|'sumDistinct'|'var_samp'|'var_pop'
},
]
},
'DropDuplicates': {
'Name': 'string',
'Inputs': [
'string',
],
'Columns': [
[
'string',
],
]
},
'GovernedCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'GovernedCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'MicrosoftSQLServerCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MicrosoftSQLServerCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'DynamicTransform': {
'Name': 'string',
'TransformName': 'string',
'Inputs': [
'string',
],
'Parameters': [
{
'Name': 'string',
'Type': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'ValidationRule': 'string',
'ValidationMessage': 'string',
'Value': [
'string',
],
'ListType': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'IsOptional': True|False
},
],
'FunctionName': 'string',
'Path': 'string',
'Version': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'EvaluateDataQuality': {
'Name': 'string',
'Inputs': [
'string',
],
'Ruleset': 'string',
'Output': 'PrimaryInput'|'EvaluationResults',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'S3CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalHudiOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3HudiDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Compression': 'gzip'|'lzo'|'uncompressed'|'snappy',
'PartitionKeys': [
[
'string',
],
],
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'DirectJDBCSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'ConnectionName': 'string',
'ConnectionType': 'sqlserver'|'mysql'|'oracle'|'postgresql'|'redshift',
'RedshiftTmpDir': 'string'
},
'S3CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalDeltaOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3DeltaDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'uncompressed'|'snappy',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'AmazonRedshiftSource': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
}
},
'AmazonRedshiftTarget': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'EvaluateDataQualityMultiFrame': {
'Name': 'string',
'Inputs': [
'string',
],
'AdditionalDataSources': {
'string': 'string'
},
'Ruleset': 'string',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'AdditionalOptions': {
'string': 'string'
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'Recipe': {
'Name': 'string',
'Inputs': [
'string',
],
'RecipeReference': {
'RecipeArn': 'string',
'RecipeVersion': 'string'
},
'RecipeSteps': [
{
'Action': {
'Operation': 'string',
'Parameters': {
'string': 'string'
}
},
'ConditionExpressions': [
{
'Condition': 'string',
'Value': 'string',
'TargetColumn': 'string'
},
]
},
]
},
'SnowflakeSource': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SnowflakeTarget': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'ConnectorDataSource': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'ConnectorDataTarget': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'Inputs': [
'string',
]
}
}
},
'ExecutionClass': 'FLEX'|'STANDARD',
'SourceControlDetails': {
'Provider': 'GITHUB'|'GITLAB'|'BITBUCKET'|'AWS_CODE_COMMIT',
'Repository': 'string',
'Owner': 'string',
'Branch': 'string',
'Folder': 'string',
'LastCommitId': 'string',
'AuthStrategy': 'PERSONAL_ACCESS_TOKEN'|'AWS_SECRETS_MANAGER',
'AuthToken': 'string'
},
'MaintenanceWindow': 'string',
'ProfileName': 'string'
},
],
'JobsNotFound': [
'string',
]
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/BatchGetJobs>`_
{'ConnectionInput': {'ConnectionType': {'VIEW_VALIDATION_ATHENA',
'VIEW_VALIDATION_REDSHIFT'}}}
Creates a connection definition in the Data Catalog.
Connections used for creating federated resources require the IAM glue:PassConnection permission.
See also: AWS API Documentation
Request Syntax
client.create_connection(
CatalogId='string',
ConnectionInput={
'Name': 'string',
'Description': 'string',
'ConnectionType': 'JDBC'|'SFTP'|'MONGODB'|'KAFKA'|'NETWORK'|'MARKETPLACE'|'CUSTOM'|'SALESFORCE'|'VIEW_VALIDATION_REDSHIFT'|'VIEW_VALIDATION_ATHENA',
'MatchCriteria': [
'string',
],
'ConnectionProperties': {
'string': 'string'
},
'PhysicalConnectionRequirements': {
'SubnetId': 'string',
'SecurityGroupIdList': [
'string',
],
'AvailabilityZone': 'string'
},
'AuthenticationConfiguration': {
'AuthenticationType': 'BASIC'|'OAUTH2'|'CUSTOM',
'SecretArn': 'string',
'OAuth2Properties': {
'OAuth2GrantType': 'AUTHORIZATION_CODE'|'CLIENT_CREDENTIALS'|'JWT_BEARER',
'OAuth2ClientApplication': {
'UserManagedClientApplicationClientId': 'string',
'AWSManagedClientApplicationReference': 'string'
},
'TokenUrl': 'string',
'TokenUrlParametersMap': {
'string': 'string'
},
'AuthorizationCodeProperties': {
'AuthorizationCode': 'string',
'RedirectUri': 'string'
}
}
},
'ValidateCredentials': True|False
},
Tags={
'string': 'string'
}
)
string
The ID of the Data Catalog in which to create the connection. If none is provided, the Amazon Web Services account ID is used by default.
dict
[REQUIRED]
A ConnectionInput object defining the connection to create.
Name (string) -- [REQUIRED]
The name of the connection.
Description (string) --
The description of the connection.
ConnectionType (string) -- [REQUIRED]
The type of the connection. Currently, these types are supported:
JDBC - Designates a connection to a database through Java Database Connectivity (JDBC). JDBC Connections use the following ConnectionParameters.
Required: All of ( HOST, PORT, JDBC_ENGINE) or JDBC_CONNECTION_URL.
Required: All of ( USERNAME, PASSWORD) or SECRET_ID.
Optional: JDBC_ENFORCE_SSL, CUSTOM_JDBC_CERT, CUSTOM_JDBC_CERT_STRING, SKIP_CUSTOM_JDBC_CERT_VALIDATION. These parameters are used to configure SSL with JDBC.
KAFKA - Designates a connection to an Apache Kafka streaming platform. KAFKA Connections use the following ConnectionParameters.
Required: KAFKA_BOOTSTRAP_SERVERS.
Optional: KAFKA_SSL_ENABLED, KAFKA_CUSTOM_CERT, KAFKA_SKIP_CUSTOM_CERT_VALIDATION. These parameters are used to configure SSL with KAFKA.
Optional: KAFKA_CLIENT_KEYSTORE, KAFKA_CLIENT_KEYSTORE_PASSWORD, KAFKA_CLIENT_KEY_PASSWORD, ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD, ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD. These parameters are used to configure TLS client configuration with SSL in KAFKA.
Optional: KAFKA_SASL_MECHANISM. Can be specified as SCRAM-SHA-512, GSSAPI, or AWS_MSK_IAM.
Optional: KAFKA_SASL_SCRAM_USERNAME, KAFKA_SASL_SCRAM_PASSWORD, ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD. These parameters are used to configure SASL/SCRAM-SHA-512 authentication with KAFKA.
Optional: KAFKA_SASL_GSSAPI_KEYTAB, KAFKA_SASL_GSSAPI_KRB5_CONF, KAFKA_SASL_GSSAPI_SERVICE, KAFKA_SASL_GSSAPI_PRINCIPAL. These parameters are used to configure SASL/GSSAPI authentication with KAFKA.
MONGODB - Designates a connection to a MongoDB document database. MONGODB Connections use the following ConnectionParameters.
Required: CONNECTION_URL.
Required: All of ( USERNAME, PASSWORD) or SECRET_ID.
SALESFORCE - Designates a connection to Salesforce using OAuth authencation.
Requires the AuthenticationConfiguration member to be configured.
VIEW_VALIDATION_REDSHIFT - Designates a connection used for view validation by Amazon Redshift.
VIEW_VALIDATION_ATHENA - Designates a connection used for view validation by Amazon Athena.
NETWORK - Designates a network connection to a data source within an Amazon Virtual Private Cloud environment (Amazon VPC). NETWORK Connections do not require ConnectionParameters. Instead, provide a PhysicalConnectionRequirements.
MARKETPLACE - Uses configuration settings contained in a connector purchased from Amazon Web Services Marketplace to read from and write to data stores that are not natively supported by Glue. MARKETPLACE Connections use the following ConnectionParameters.
Required: CONNECTOR_TYPE, CONNECTOR_URL, CONNECTOR_CLASS_NAME, CONNECTION_URL.
Required for JDBC CONNECTOR_TYPE connections: All of ( USERNAME, PASSWORD) or SECRET_ID.
CUSTOM - Uses configuration settings contained in a custom connector to read from and write to data stores that are not natively supported by Glue.
SFTP is not supported.
For more information about how optional ConnectionProperties are used to configure features in Glue, consult Glue connection properties.
For more information about how optional ConnectionProperties are used to configure features in Glue Studio, consult Using connectors and connections.
MatchCriteria (list) --
A list of criteria that can be used in selecting this connection.
(string) --
ConnectionProperties (dict) -- [REQUIRED]
These key-value pairs define parameters for the connection.
(string) --
(string) --
PhysicalConnectionRequirements (dict) --
The physical connection requirements, such as virtual private cloud (VPC) and SecurityGroup, that are needed to successfully make this connection.
SubnetId (string) --
The subnet ID used by the connection.
SecurityGroupIdList (list) --
The security group ID list used by the connection.
(string) --
AvailabilityZone (string) --
The connection's Availability Zone.
AuthenticationConfiguration (dict) --
The authentication properties of the connection. Used for a Salesforce connection.
AuthenticationType (string) --
A structure containing the authentication configuration in the CreateConnection request.
SecretArn (string) --
The secret manager ARN to store credentials in the CreateConnection request.
OAuth2Properties (dict) --
The properties for OAuth2 authentication in the CreateConnection request.
OAuth2GrantType (string) --
The OAuth2 grant type in the CreateConnection request. For example, AUTHORIZATION_CODE, JWT_BEARER, or CLIENT_CREDENTIALS.
OAuth2ClientApplication (dict) --
The client application type in the CreateConnection request. For example, AWS_MANAGED or USER_MANAGED.
UserManagedClientApplicationClientId (string) --
The client application clientID if the ClientAppType is USER_MANAGED.
AWSManagedClientApplicationReference (string) --
The reference to the SaaS-side client app that is Amazon Web Services managed.
TokenUrl (string) --
The URL of the provider's authentication server, to exchange an authorization code for an access token.
TokenUrlParametersMap (dict) --
A map of parameters that are added to the token GET request.
(string) --
(string) --
AuthorizationCodeProperties (dict) --
The set of properties required for the the OAuth2 AUTHORIZATION_CODE grant type.
AuthorizationCode (string) --
An authorization code to be used in the third leg of the AUTHORIZATION_CODE grant workflow. This is a single-use code which becomes invalid once exchanged for an access token, thus it is acceptable to have this value as a request parameter.
RedirectUri (string) --
The redirect URI where the user gets redirected to by authorization server when issuing an authorization code. The URI is subsequently used when the authorization code is exchanged for an access token.
ValidateCredentials (boolean) --
A flag to validate the credentials during create connection. Used for a Salesforce connection. Default is true.
dict
The tags you assign to the connection.
(string) --
(string) --
dict
Response Syntax
{
'CreateConnectionStatus': 'READY'|'IN_PROGRESS'|'FAILED'
}
Response Structure
(dict) --
CreateConnectionStatus (string) --
The status of the connection creation request. The request can take some time for certain authentication types, for example when creating an OAuth connection with token exchange over VPC.
{'CodeGenConfigurationNodes': {'CatalogTarget': {'PartitionKeys': [['string']]}}}
Creates a new job definition.
See also: AWS API Documentation
Request Syntax
client.create_job(
Name='string',
JobMode='SCRIPT'|'VISUAL'|'NOTEBOOK',
Description='string',
LogUri='string',
Role='string',
ExecutionProperty={
'MaxConcurrentRuns': 123
},
Command={
'Name': 'string',
'ScriptLocation': 'string',
'PythonVersion': 'string',
'Runtime': 'string'
},
DefaultArguments={
'string': 'string'
},
NonOverridableArguments={
'string': 'string'
},
Connections={
'Connections': [
'string',
]
},
MaxRetries=123,
AllocatedCapacity=123,
Timeout=123,
MaxCapacity=123.0,
SecurityConfiguration='string',
Tags={
'string': 'string'
},
NotificationProperty={
'NotifyDelayAfter': 123
},
GlueVersion='string',
NumberOfWorkers=123,
WorkerType='Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
CodeGenConfigurationNodes={
'string': {
'AthenaConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'ConnectionTable': 'string',
'SchemaName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'JDBCConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'FilterPredicate': 'string',
'PartitionColumn': 'string',
'LowerBound': 123,
'UpperBound': 123,
'NumPartitions': 123,
'JobBookmarkKeys': [
'string',
],
'JobBookmarkKeysSortOrder': 'string',
'DataTypeMapping': {
'string': 'DATE'|'STRING'|'TIMESTAMP'|'INT'|'FLOAT'|'LONG'|'BIGDECIMAL'|'BYTE'|'SHORT'|'DOUBLE'
}
},
'ConnectionTable': 'string',
'Query': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'RedshiftSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string'
},
'S3CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'S3CsvSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'Separator': 'comma'|'ctrla'|'pipe'|'semicolon'|'tab',
'Escaper': 'string',
'QuoteChar': 'quote'|'quillemet'|'single_quote'|'disabled',
'Multiline': True|False,
'WithHeader': True|False,
'WriteHeader': True|False,
'SkipFirst': True|False,
'OptimizePerformance': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3JsonSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'JsonPath': 'string',
'Multiline': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3ParquetSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'RelationalCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'DynamoDBCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'JDBCConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectionTable': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Database': 'string',
'Table': 'string'
},
'RedshiftTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string',
'UpsertRedshiftOptions': {
'TableLocation': 'string',
'ConnectionName': 'string',
'UpsertKeys': [
'string',
]
}
},
'S3CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3GlueParquetTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'S3DirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'string',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'ApplyMapping': {
'Name': 'string',
'Inputs': [
'string',
],
'Mapping': [
{
'ToKey': 'string',
'FromPath': [
'string',
],
'FromType': 'string',
'ToType': 'string',
'Dropped': True|False,
'Children': {'... recursive ...'}
},
]
},
'SelectFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'DropFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'RenameField': {
'Name': 'string',
'Inputs': [
'string',
],
'SourcePath': [
'string',
],
'TargetPath': [
'string',
]
},
'Spigot': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Topk': 123,
'Prob': 123.0
},
'Join': {
'Name': 'string',
'Inputs': [
'string',
],
'JoinType': 'equijoin'|'left'|'right'|'outer'|'leftsemi'|'leftanti',
'Columns': [
{
'From': 'string',
'Keys': [
[
'string',
],
]
},
]
},
'SplitFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'SelectFromCollection': {
'Name': 'string',
'Inputs': [
'string',
],
'Index': 123
},
'FillMissingValues': {
'Name': 'string',
'Inputs': [
'string',
],
'ImputedPath': 'string',
'FilledPath': 'string'
},
'Filter': {
'Name': 'string',
'Inputs': [
'string',
],
'LogicalOperator': 'AND'|'OR',
'Filters': [
{
'Operation': 'EQ'|'LT'|'GT'|'LTE'|'GTE'|'REGEX'|'ISNULL',
'Negated': True|False,
'Values': [
{
'Type': 'COLUMNEXTRACTED'|'CONSTANT',
'Value': [
'string',
]
},
]
},
]
},
'CustomCode': {
'Name': 'string',
'Inputs': [
'string',
],
'Code': 'string',
'ClassName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkSQL': {
'Name': 'string',
'Inputs': [
'string',
],
'SqlQuery': 'string',
'SqlAliases': [
{
'From': 'string',
'Alias': 'string'
},
],
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'DirectKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DirectKafkaSource': {
'Name': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'WindowSize': 123,
'DetectSchema': True|False,
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKafkaSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DropNullFields': {
'Name': 'string',
'Inputs': [
'string',
],
'NullCheckBoxList': {
'IsEmpty': True|False,
'IsNullString': True|False,
'IsNegOne': True|False
},
'NullTextList': [
{
'Value': 'string',
'Datatype': {
'Id': 'string',
'Label': 'string'
}
},
]
},
'Merge': {
'Name': 'string',
'Inputs': [
'string',
],
'Source': 'string',
'PrimaryKeys': [
[
'string',
],
]
},
'Union': {
'Name': 'string',
'Inputs': [
'string',
],
'UnionType': 'ALL'|'DISTINCT'
},
'PIIDetection': {
'Name': 'string',
'Inputs': [
'string',
],
'PiiType': 'RowAudit'|'RowMasking'|'ColumnAudit'|'ColumnMasking',
'EntityTypesToDetect': [
'string',
],
'OutputColumnName': 'string',
'SampleFraction': 123.0,
'ThresholdFraction': 123.0,
'MaskValue': 'string'
},
'Aggregate': {
'Name': 'string',
'Inputs': [
'string',
],
'Groups': [
[
'string',
],
],
'Aggs': [
{
'Column': [
'string',
],
'AggFunc': 'avg'|'countDistinct'|'count'|'first'|'last'|'kurtosis'|'max'|'min'|'skewness'|'stddev_samp'|'stddev_pop'|'sum'|'sumDistinct'|'var_samp'|'var_pop'
},
]
},
'DropDuplicates': {
'Name': 'string',
'Inputs': [
'string',
],
'Columns': [
[
'string',
],
]
},
'GovernedCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'GovernedCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'MicrosoftSQLServerCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MicrosoftSQLServerCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'DynamicTransform': {
'Name': 'string',
'TransformName': 'string',
'Inputs': [
'string',
],
'Parameters': [
{
'Name': 'string',
'Type': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'ValidationRule': 'string',
'ValidationMessage': 'string',
'Value': [
'string',
],
'ListType': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'IsOptional': True|False
},
],
'FunctionName': 'string',
'Path': 'string',
'Version': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'EvaluateDataQuality': {
'Name': 'string',
'Inputs': [
'string',
],
'Ruleset': 'string',
'Output': 'PrimaryInput'|'EvaluationResults',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'S3CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalHudiOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3HudiDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Compression': 'gzip'|'lzo'|'uncompressed'|'snappy',
'PartitionKeys': [
[
'string',
],
],
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'DirectJDBCSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'ConnectionName': 'string',
'ConnectionType': 'sqlserver'|'mysql'|'oracle'|'postgresql'|'redshift',
'RedshiftTmpDir': 'string'
},
'S3CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalDeltaOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3DeltaDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'uncompressed'|'snappy',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'AmazonRedshiftSource': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
}
},
'AmazonRedshiftTarget': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'EvaluateDataQualityMultiFrame': {
'Name': 'string',
'Inputs': [
'string',
],
'AdditionalDataSources': {
'string': 'string'
},
'Ruleset': 'string',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'AdditionalOptions': {
'string': 'string'
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'Recipe': {
'Name': 'string',
'Inputs': [
'string',
],
'RecipeReference': {
'RecipeArn': 'string',
'RecipeVersion': 'string'
},
'RecipeSteps': [
{
'Action': {
'Operation': 'string',
'Parameters': {
'string': 'string'
}
},
'ConditionExpressions': [
{
'Condition': 'string',
'Value': 'string',
'TargetColumn': 'string'
},
]
},
]
},
'SnowflakeSource': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SnowflakeTarget': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'ConnectorDataSource': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'ConnectorDataTarget': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'Inputs': [
'string',
]
}
}
},
ExecutionClass='FLEX'|'STANDARD',
SourceControlDetails={
'Provider': 'GITHUB'|'GITLAB'|'BITBUCKET'|'AWS_CODE_COMMIT',
'Repository': 'string',
'Owner': 'string',
'Branch': 'string',
'Folder': 'string',
'LastCommitId': 'string',
'AuthStrategy': 'PERSONAL_ACCESS_TOKEN'|'AWS_SECRETS_MANAGER',
'AuthToken': 'string'
},
MaintenanceWindow='string'
)
**Parameters**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/CreateJob>`_
dict
Response Syntax
{
'Name': 'string'
}
Response Structure
(dict) --
Name (string) --
The unique name that was provided for this job definition.
{'Connection': {'ConnectionType': {'VIEW_VALIDATION_ATHENA',
'VIEW_VALIDATION_REDSHIFT'}}}
Retrieves a connection definition from the Data Catalog.
See also: AWS API Documentation
Request Syntax
client.get_connection(
CatalogId='string',
Name='string',
HidePassword=True|False
)
string
The ID of the Data Catalog in which the connection resides. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The name of the connection definition to retrieve.
boolean
Allows you to retrieve the connection metadata without returning the password. For instance, the Glue console uses this flag to retrieve the connection, and does not display the password. Set this parameter when the caller might not have permission to use the KMS key to decrypt the password, but it does have permission to access the rest of the connection properties.
dict
Response Syntax
{
'Connection': {
'Name': 'string',
'Description': 'string',
'ConnectionType': 'JDBC'|'SFTP'|'MONGODB'|'KAFKA'|'NETWORK'|'MARKETPLACE'|'CUSTOM'|'SALESFORCE'|'VIEW_VALIDATION_REDSHIFT'|'VIEW_VALIDATION_ATHENA',
'MatchCriteria': [
'string',
],
'ConnectionProperties': {
'string': 'string'
},
'PhysicalConnectionRequirements': {
'SubnetId': 'string',
'SecurityGroupIdList': [
'string',
],
'AvailabilityZone': 'string'
},
'CreationTime': datetime(2015, 1, 1),
'LastUpdatedTime': datetime(2015, 1, 1),
'LastUpdatedBy': 'string',
'Status': 'READY'|'IN_PROGRESS'|'FAILED',
'StatusReason': 'string',
'LastConnectionValidationTime': datetime(2015, 1, 1),
'AuthenticationConfiguration': {
'AuthenticationType': 'BASIC'|'OAUTH2'|'CUSTOM',
'SecretArn': 'string',
'OAuth2Properties': {
'OAuth2GrantType': 'AUTHORIZATION_CODE'|'CLIENT_CREDENTIALS'|'JWT_BEARER',
'OAuth2ClientApplication': {
'UserManagedClientApplicationClientId': 'string',
'AWSManagedClientApplicationReference': 'string'
},
'TokenUrl': 'string',
'TokenUrlParametersMap': {
'string': 'string'
}
}
}
}
}
Response Structure
(dict) --
Connection (dict) --
The requested connection definition.
Name (string) --
The name of the connection definition.
Description (string) --
The description of the connection.
ConnectionType (string) --
The type of the connection. Currently, SFTP is not supported.
MatchCriteria (list) --
A list of criteria that can be used in selecting this connection.
(string) --
ConnectionProperties (dict) --
These key-value pairs define parameters for the connection:
HOST - The host URI: either the fully qualified domain name (FQDN) or the IPv4 address of the database host.
PORT - The port number, between 1024 and 65535, of the port on which the database host is listening for database connections.
USER_NAME - The name under which to log in to the database. The value string for USER_NAME is " USERNAME".
PASSWORD - A password, if one is used, for the user name.
ENCRYPTED_PASSWORD - When you enable connection password protection by setting ConnectionPasswordEncryption in the Data Catalog encryption settings, this field stores the encrypted password.
JDBC_DRIVER_JAR_URI - The Amazon Simple Storage Service (Amazon S3) path of the JAR file that contains the JDBC driver to use.
JDBC_DRIVER_CLASS_NAME - The class name of the JDBC driver to use.
JDBC_ENGINE - The name of the JDBC engine to use.
JDBC_ENGINE_VERSION - The version of the JDBC engine to use.
CONFIG_FILES - (Reserved for future use.)
INSTANCE_ID - The instance ID to use.
JDBC_CONNECTION_URL - The URL for connecting to a JDBC data source.
JDBC_ENFORCE_SSL - A Boolean string (true, false) specifying whether Secure Sockets Layer (SSL) with hostname matching is enforced for the JDBC connection on the client. The default is false.
CUSTOM_JDBC_CERT - An Amazon S3 location specifying the customer's root certificate. Glue uses this root certificate to validate the customer’s certificate when connecting to the customer database. Glue only handles X.509 certificates. The certificate provided must be DER-encoded and supplied in Base64 encoding PEM format.
SKIP_CUSTOM_JDBC_CERT_VALIDATION - By default, this is false. Glue validates the Signature algorithm and Subject Public Key Algorithm for the customer certificate. The only permitted algorithms for the Signature algorithm are SHA256withRSA, SHA384withRSA or SHA512withRSA. For the Subject Public Key Algorithm, the key length must be at least 2048. You can set the value of this property to true to skip Glue’s validation of the customer certificate.
CUSTOM_JDBC_CERT_STRING - A custom JDBC certificate string which is used for domain match or distinguished name match to prevent a man-in-the-middle attack. In Oracle database, this is used as the SSL_SERVER_CERT_DN; in Microsoft SQL Server, this is used as the hostNameInCertificate.
CONNECTION_URL - The URL for connecting to a general (non-JDBC) data source.
SECRET_ID - The secret ID used for the secret manager of credentials.
CONNECTOR_URL - The connector URL for a MARKETPLACE or CUSTOM connection.
CONNECTOR_TYPE - The connector type for a MARKETPLACE or CUSTOM connection.
CONNECTOR_CLASS_NAME - The connector class name for a MARKETPLACE or CUSTOM connection.
KAFKA_BOOTSTRAP_SERVERS - A comma-separated list of host and port pairs that are the addresses of the Apache Kafka brokers in a Kafka cluster to which a Kafka client will connect to and bootstrap itself.
KAFKA_SSL_ENABLED - Whether to enable or disable SSL on an Apache Kafka connection. Default value is "true".
KAFKA_CUSTOM_CERT - The Amazon S3 URL for the private CA cert file (.pem format). The default is an empty string.
KAFKA_SKIP_CUSTOM_CERT_VALIDATION - Whether to skip the validation of the CA cert file or not. Glue validates for three algorithms: SHA256withRSA, SHA384withRSA and SHA512withRSA. Default value is "false".
KAFKA_CLIENT_KEYSTORE - The Amazon S3 location of the client keystore file for Kafka client side authentication (Optional).
KAFKA_CLIENT_KEYSTORE_PASSWORD - The password to access the provided keystore (Optional).
KAFKA_CLIENT_KEY_PASSWORD - A keystore can consist of multiple keys, so this is the password to access the client key to be used with the Kafka server side key (Optional).
ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD - The encrypted version of the Kafka client keystore password (if the user has the Glue encrypt passwords setting selected).
ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD - The encrypted version of the Kafka client key password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_MECHANISM - "SCRAM-SHA-512", "GSSAPI", "AWS_MSK_IAM", or "PLAIN". These are the supported SASL Mechanisms.
KAFKA_SASL_PLAIN_USERNAME - A plaintext username used to authenticate with the "PLAIN" mechanism.
KAFKA_SASL_PLAIN_PASSWORD - A plaintext password used to authenticate with the "PLAIN" mechanism.
ENCRYPTED_KAFKA_SASL_PLAIN_PASSWORD - The encrypted version of the Kafka SASL PLAIN password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_SCRAM_USERNAME - A plaintext username used to authenticate with the "SCRAM-SHA-512" mechanism.
KAFKA_SASL_SCRAM_PASSWORD - A plaintext password used to authenticate with the "SCRAM-SHA-512" mechanism.
ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD - The encrypted version of the Kafka SASL SCRAM password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_SCRAM_SECRETS_ARN - The Amazon Resource Name of a secret in Amazon Web Services Secrets Manager.
KAFKA_SASL_GSSAPI_KEYTAB - The S3 location of a Kerberos keytab file. A keytab stores long-term keys for one or more principals. For more information, see MIT Kerberos Documentation: Keytab.
KAFKA_SASL_GSSAPI_KRB5_CONF - The S3 location of a Kerberos krb5.conf file. A krb5.conf stores Kerberos configuration information, such as the location of the KDC server. For more information, see MIT Kerberos Documentation: krb5.conf.
KAFKA_SASL_GSSAPI_SERVICE - The Kerberos service name, as set with sasl.kerberos.service.name in your Kafka Configuration.
KAFKA_SASL_GSSAPI_PRINCIPAL - The name of the Kerberos princial used by Glue. For more information, see Kafka Documentation: Configuring Kafka Brokers.
ROLE_ARN - The role to be used for running queries.
REGION - The Amazon Web Services Region where queries will be run.
WORKGROUP_NAME - The name of an Amazon Redshift serverless workgroup or Amazon Athena workgroup in which queries will run.
CLUSTER_IDENTIFIER - The cluster identifier of an Amazon Redshift cluster in which queries will run.
DATABASE - The Amazon Redshift database that you are connecting to.
(string) --
(string) --
PhysicalConnectionRequirements (dict) --
The physical connection requirements, such as virtual private cloud (VPC) and SecurityGroup, that are needed to make this connection successfully.
SubnetId (string) --
The subnet ID used by the connection.
SecurityGroupIdList (list) --
The security group ID list used by the connection.
(string) --
AvailabilityZone (string) --
The connection's Availability Zone.
CreationTime (datetime) --
The timestamp of the time that this connection definition was created.
LastUpdatedTime (datetime) --
The timestamp of the last time the connection definition was updated.
LastUpdatedBy (string) --
The user, group, or role that last updated this connection definition.
Status (string) --
The status of the connection. Can be one of: READY, IN_PROGRESS, or FAILED.
StatusReason (string) --
The reason for the connection status.
LastConnectionValidationTime (datetime) --
A timestamp of the time this connection was last validated.
AuthenticationConfiguration (dict) --
The authentication properties of the connection.
AuthenticationType (string) --
A structure containing the authentication configuration.
SecretArn (string) --
The secret manager ARN to store credentials.
OAuth2Properties (dict) --
The properties for OAuth2 authentication.
OAuth2GrantType (string) --
The OAuth2 grant type. For example, AUTHORIZATION_CODE, JWT_BEARER, or CLIENT_CREDENTIALS.
OAuth2ClientApplication (dict) --
The client application type. For example, AWS_MANAGED or USER_MANAGED.
UserManagedClientApplicationClientId (string) --
The client application clientID if the ClientAppType is USER_MANAGED.
AWSManagedClientApplicationReference (string) --
The reference to the SaaS-side client app that is Amazon Web Services managed.
TokenUrl (string) --
The URL of the provider's authentication server, to exchange an authorization code for an access token.
TokenUrlParametersMap (dict) --
A map of parameters that are added to the token GET request.
(string) --
(string) --
{'Filter': {'ConnectionType': {'VIEW_VALIDATION_ATHENA',
'VIEW_VALIDATION_REDSHIFT'}}}
Response {'ConnectionList': {'ConnectionType': {'VIEW_VALIDATION_ATHENA',
'VIEW_VALIDATION_REDSHIFT'}}}
Retrieves a list of connection definitions from the Data Catalog.
See also: AWS API Documentation
Request Syntax
client.get_connections(
CatalogId='string',
Filter={
'MatchCriteria': [
'string',
],
'ConnectionType': 'JDBC'|'SFTP'|'MONGODB'|'KAFKA'|'NETWORK'|'MARKETPLACE'|'CUSTOM'|'SALESFORCE'|'VIEW_VALIDATION_REDSHIFT'|'VIEW_VALIDATION_ATHENA'
},
HidePassword=True|False,
NextToken='string',
MaxResults=123
)
string
The ID of the Data Catalog in which the connections reside. If none is provided, the Amazon Web Services account ID is used by default.
dict
A filter that controls which connections are returned.
MatchCriteria (list) --
A criteria string that must match the criteria recorded in the connection definition for that connection definition to be returned.
(string) --
ConnectionType (string) --
The type of connections to return. Currently, SFTP is not supported.
boolean
Allows you to retrieve the connection metadata without returning the password. For instance, the Glue console uses this flag to retrieve the connection, and does not display the password. Set this parameter when the caller might not have permission to use the KMS key to decrypt the password, but it does have permission to access the rest of the connection properties.
string
A continuation token, if this is a continuation call.
integer
The maximum number of connections to return in one response.
dict
Response Syntax
{
'ConnectionList': [
{
'Name': 'string',
'Description': 'string',
'ConnectionType': 'JDBC'|'SFTP'|'MONGODB'|'KAFKA'|'NETWORK'|'MARKETPLACE'|'CUSTOM'|'SALESFORCE'|'VIEW_VALIDATION_REDSHIFT'|'VIEW_VALIDATION_ATHENA',
'MatchCriteria': [
'string',
],
'ConnectionProperties': {
'string': 'string'
},
'PhysicalConnectionRequirements': {
'SubnetId': 'string',
'SecurityGroupIdList': [
'string',
],
'AvailabilityZone': 'string'
},
'CreationTime': datetime(2015, 1, 1),
'LastUpdatedTime': datetime(2015, 1, 1),
'LastUpdatedBy': 'string',
'Status': 'READY'|'IN_PROGRESS'|'FAILED',
'StatusReason': 'string',
'LastConnectionValidationTime': datetime(2015, 1, 1),
'AuthenticationConfiguration': {
'AuthenticationType': 'BASIC'|'OAUTH2'|'CUSTOM',
'SecretArn': 'string',
'OAuth2Properties': {
'OAuth2GrantType': 'AUTHORIZATION_CODE'|'CLIENT_CREDENTIALS'|'JWT_BEARER',
'OAuth2ClientApplication': {
'UserManagedClientApplicationClientId': 'string',
'AWSManagedClientApplicationReference': 'string'
},
'TokenUrl': 'string',
'TokenUrlParametersMap': {
'string': 'string'
}
}
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
ConnectionList (list) --
A list of requested connection definitions.
(dict) --
Defines a connection to a data source.
Name (string) --
The name of the connection definition.
Description (string) --
The description of the connection.
ConnectionType (string) --
The type of the connection. Currently, SFTP is not supported.
MatchCriteria (list) --
A list of criteria that can be used in selecting this connection.
(string) --
ConnectionProperties (dict) --
These key-value pairs define parameters for the connection:
HOST - The host URI: either the fully qualified domain name (FQDN) or the IPv4 address of the database host.
PORT - The port number, between 1024 and 65535, of the port on which the database host is listening for database connections.
USER_NAME - The name under which to log in to the database. The value string for USER_NAME is " USERNAME".
PASSWORD - A password, if one is used, for the user name.
ENCRYPTED_PASSWORD - When you enable connection password protection by setting ConnectionPasswordEncryption in the Data Catalog encryption settings, this field stores the encrypted password.
JDBC_DRIVER_JAR_URI - The Amazon Simple Storage Service (Amazon S3) path of the JAR file that contains the JDBC driver to use.
JDBC_DRIVER_CLASS_NAME - The class name of the JDBC driver to use.
JDBC_ENGINE - The name of the JDBC engine to use.
JDBC_ENGINE_VERSION - The version of the JDBC engine to use.
CONFIG_FILES - (Reserved for future use.)
INSTANCE_ID - The instance ID to use.
JDBC_CONNECTION_URL - The URL for connecting to a JDBC data source.
JDBC_ENFORCE_SSL - A Boolean string (true, false) specifying whether Secure Sockets Layer (SSL) with hostname matching is enforced for the JDBC connection on the client. The default is false.
CUSTOM_JDBC_CERT - An Amazon S3 location specifying the customer's root certificate. Glue uses this root certificate to validate the customer’s certificate when connecting to the customer database. Glue only handles X.509 certificates. The certificate provided must be DER-encoded and supplied in Base64 encoding PEM format.
SKIP_CUSTOM_JDBC_CERT_VALIDATION - By default, this is false. Glue validates the Signature algorithm and Subject Public Key Algorithm for the customer certificate. The only permitted algorithms for the Signature algorithm are SHA256withRSA, SHA384withRSA or SHA512withRSA. For the Subject Public Key Algorithm, the key length must be at least 2048. You can set the value of this property to true to skip Glue’s validation of the customer certificate.
CUSTOM_JDBC_CERT_STRING - A custom JDBC certificate string which is used for domain match or distinguished name match to prevent a man-in-the-middle attack. In Oracle database, this is used as the SSL_SERVER_CERT_DN; in Microsoft SQL Server, this is used as the hostNameInCertificate.
CONNECTION_URL - The URL for connecting to a general (non-JDBC) data source.
SECRET_ID - The secret ID used for the secret manager of credentials.
CONNECTOR_URL - The connector URL for a MARKETPLACE or CUSTOM connection.
CONNECTOR_TYPE - The connector type for a MARKETPLACE or CUSTOM connection.
CONNECTOR_CLASS_NAME - The connector class name for a MARKETPLACE or CUSTOM connection.
KAFKA_BOOTSTRAP_SERVERS - A comma-separated list of host and port pairs that are the addresses of the Apache Kafka brokers in a Kafka cluster to which a Kafka client will connect to and bootstrap itself.
KAFKA_SSL_ENABLED - Whether to enable or disable SSL on an Apache Kafka connection. Default value is "true".
KAFKA_CUSTOM_CERT - The Amazon S3 URL for the private CA cert file (.pem format). The default is an empty string.
KAFKA_SKIP_CUSTOM_CERT_VALIDATION - Whether to skip the validation of the CA cert file or not. Glue validates for three algorithms: SHA256withRSA, SHA384withRSA and SHA512withRSA. Default value is "false".
KAFKA_CLIENT_KEYSTORE - The Amazon S3 location of the client keystore file for Kafka client side authentication (Optional).
KAFKA_CLIENT_KEYSTORE_PASSWORD - The password to access the provided keystore (Optional).
KAFKA_CLIENT_KEY_PASSWORD - A keystore can consist of multiple keys, so this is the password to access the client key to be used with the Kafka server side key (Optional).
ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD - The encrypted version of the Kafka client keystore password (if the user has the Glue encrypt passwords setting selected).
ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD - The encrypted version of the Kafka client key password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_MECHANISM - "SCRAM-SHA-512", "GSSAPI", "AWS_MSK_IAM", or "PLAIN". These are the supported SASL Mechanisms.
KAFKA_SASL_PLAIN_USERNAME - A plaintext username used to authenticate with the "PLAIN" mechanism.
KAFKA_SASL_PLAIN_PASSWORD - A plaintext password used to authenticate with the "PLAIN" mechanism.
ENCRYPTED_KAFKA_SASL_PLAIN_PASSWORD - The encrypted version of the Kafka SASL PLAIN password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_SCRAM_USERNAME - A plaintext username used to authenticate with the "SCRAM-SHA-512" mechanism.
KAFKA_SASL_SCRAM_PASSWORD - A plaintext password used to authenticate with the "SCRAM-SHA-512" mechanism.
ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD - The encrypted version of the Kafka SASL SCRAM password (if the user has the Glue encrypt passwords setting selected).
KAFKA_SASL_SCRAM_SECRETS_ARN - The Amazon Resource Name of a secret in Amazon Web Services Secrets Manager.
KAFKA_SASL_GSSAPI_KEYTAB - The S3 location of a Kerberos keytab file. A keytab stores long-term keys for one or more principals. For more information, see MIT Kerberos Documentation: Keytab.
KAFKA_SASL_GSSAPI_KRB5_CONF - The S3 location of a Kerberos krb5.conf file. A krb5.conf stores Kerberos configuration information, such as the location of the KDC server. For more information, see MIT Kerberos Documentation: krb5.conf.
KAFKA_SASL_GSSAPI_SERVICE - The Kerberos service name, as set with sasl.kerberos.service.name in your Kafka Configuration.
KAFKA_SASL_GSSAPI_PRINCIPAL - The name of the Kerberos princial used by Glue. For more information, see Kafka Documentation: Configuring Kafka Brokers.
ROLE_ARN - The role to be used for running queries.
REGION - The Amazon Web Services Region where queries will be run.
WORKGROUP_NAME - The name of an Amazon Redshift serverless workgroup or Amazon Athena workgroup in which queries will run.
CLUSTER_IDENTIFIER - The cluster identifier of an Amazon Redshift cluster in which queries will run.
DATABASE - The Amazon Redshift database that you are connecting to.
(string) --
(string) --
PhysicalConnectionRequirements (dict) --
The physical connection requirements, such as virtual private cloud (VPC) and SecurityGroup, that are needed to make this connection successfully.
SubnetId (string) --
The subnet ID used by the connection.
SecurityGroupIdList (list) --
The security group ID list used by the connection.
(string) --
AvailabilityZone (string) --
The connection's Availability Zone.
CreationTime (datetime) --
The timestamp of the time that this connection definition was created.
LastUpdatedTime (datetime) --
The timestamp of the last time the connection definition was updated.
LastUpdatedBy (string) --
The user, group, or role that last updated this connection definition.
Status (string) --
The status of the connection. Can be one of: READY, IN_PROGRESS, or FAILED.
StatusReason (string) --
The reason for the connection status.
LastConnectionValidationTime (datetime) --
A timestamp of the time this connection was last validated.
AuthenticationConfiguration (dict) --
The authentication properties of the connection.
AuthenticationType (string) --
A structure containing the authentication configuration.
SecretArn (string) --
The secret manager ARN to store credentials.
OAuth2Properties (dict) --
The properties for OAuth2 authentication.
OAuth2GrantType (string) --
The OAuth2 grant type. For example, AUTHORIZATION_CODE, JWT_BEARER, or CLIENT_CREDENTIALS.
OAuth2ClientApplication (dict) --
The client application type. For example, AWS_MANAGED or USER_MANAGED.
UserManagedClientApplicationClientId (string) --
The client application clientID if the ClientAppType is USER_MANAGED.
AWSManagedClientApplicationReference (string) --
The reference to the SaaS-side client app that is Amazon Web Services managed.
TokenUrl (string) --
The URL of the provider's authentication server, to exchange an authorization code for an access token.
TokenUrlParametersMap (dict) --
A map of parameters that are added to the token GET request.
(string) --
(string) --
NextToken (string) --
A continuation token, if the list of connections returned does not include the last of the filtered connections.
{'Job': {'CodeGenConfigurationNodes': {'CatalogTarget': {'PartitionKeys': [['string']]}}}}
Retrieves an existing job definition.
See also: AWS API Documentation
Request Syntax
client.get_job(
JobName='string'
)
string
[REQUIRED]
The name of the job definition to retrieve.
dict
Response Syntax
{
'Job': {
'Name': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'Description': 'string',
'LogUri': 'string',
'Role': 'string',
'CreatedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'ExecutionProperty': {
'MaxConcurrentRuns': 123
},
'Command': {
'Name': 'string',
'ScriptLocation': 'string',
'PythonVersion': 'string',
'Runtime': 'string'
},
'DefaultArguments': {
'string': 'string'
},
'NonOverridableArguments': {
'string': 'string'
},
'Connections': {
'Connections': [
'string',
]
},
'MaxRetries': 123,
'AllocatedCapacity': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'CodeGenConfigurationNodes': {
'string': {
'AthenaConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'ConnectionTable': 'string',
'SchemaName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'JDBCConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'FilterPredicate': 'string',
'PartitionColumn': 'string',
'LowerBound': 123,
'UpperBound': 123,
'NumPartitions': 123,
'JobBookmarkKeys': [
'string',
],
'JobBookmarkKeysSortOrder': 'string',
'DataTypeMapping': {
'string': 'DATE'|'STRING'|'TIMESTAMP'|'INT'|'FLOAT'|'LONG'|'BIGDECIMAL'|'BYTE'|'SHORT'|'DOUBLE'
}
},
'ConnectionTable': 'string',
'Query': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'RedshiftSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string'
},
'S3CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'S3CsvSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'Separator': 'comma'|'ctrla'|'pipe'|'semicolon'|'tab',
'Escaper': 'string',
'QuoteChar': 'quote'|'quillemet'|'single_quote'|'disabled',
'Multiline': True|False,
'WithHeader': True|False,
'WriteHeader': True|False,
'SkipFirst': True|False,
'OptimizePerformance': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3JsonSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'JsonPath': 'string',
'Multiline': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3ParquetSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'RelationalCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'DynamoDBCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'JDBCConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectionTable': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Database': 'string',
'Table': 'string'
},
'RedshiftTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string',
'UpsertRedshiftOptions': {
'TableLocation': 'string',
'ConnectionName': 'string',
'UpsertKeys': [
'string',
]
}
},
'S3CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3GlueParquetTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'S3DirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'string',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'ApplyMapping': {
'Name': 'string',
'Inputs': [
'string',
],
'Mapping': [
{
'ToKey': 'string',
'FromPath': [
'string',
],
'FromType': 'string',
'ToType': 'string',
'Dropped': True|False,
'Children': {'... recursive ...'}
},
]
},
'SelectFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'DropFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'RenameField': {
'Name': 'string',
'Inputs': [
'string',
],
'SourcePath': [
'string',
],
'TargetPath': [
'string',
]
},
'Spigot': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Topk': 123,
'Prob': 123.0
},
'Join': {
'Name': 'string',
'Inputs': [
'string',
],
'JoinType': 'equijoin'|'left'|'right'|'outer'|'leftsemi'|'leftanti',
'Columns': [
{
'From': 'string',
'Keys': [
[
'string',
],
]
},
]
},
'SplitFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'SelectFromCollection': {
'Name': 'string',
'Inputs': [
'string',
],
'Index': 123
},
'FillMissingValues': {
'Name': 'string',
'Inputs': [
'string',
],
'ImputedPath': 'string',
'FilledPath': 'string'
},
'Filter': {
'Name': 'string',
'Inputs': [
'string',
],
'LogicalOperator': 'AND'|'OR',
'Filters': [
{
'Operation': 'EQ'|'LT'|'GT'|'LTE'|'GTE'|'REGEX'|'ISNULL',
'Negated': True|False,
'Values': [
{
'Type': 'COLUMNEXTRACTED'|'CONSTANT',
'Value': [
'string',
]
},
]
},
]
},
'CustomCode': {
'Name': 'string',
'Inputs': [
'string',
],
'Code': 'string',
'ClassName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkSQL': {
'Name': 'string',
'Inputs': [
'string',
],
'SqlQuery': 'string',
'SqlAliases': [
{
'From': 'string',
'Alias': 'string'
},
],
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'DirectKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DirectKafkaSource': {
'Name': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'WindowSize': 123,
'DetectSchema': True|False,
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKafkaSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DropNullFields': {
'Name': 'string',
'Inputs': [
'string',
],
'NullCheckBoxList': {
'IsEmpty': True|False,
'IsNullString': True|False,
'IsNegOne': True|False
},
'NullTextList': [
{
'Value': 'string',
'Datatype': {
'Id': 'string',
'Label': 'string'
}
},
]
},
'Merge': {
'Name': 'string',
'Inputs': [
'string',
],
'Source': 'string',
'PrimaryKeys': [
[
'string',
],
]
},
'Union': {
'Name': 'string',
'Inputs': [
'string',
],
'UnionType': 'ALL'|'DISTINCT'
},
'PIIDetection': {
'Name': 'string',
'Inputs': [
'string',
],
'PiiType': 'RowAudit'|'RowMasking'|'ColumnAudit'|'ColumnMasking',
'EntityTypesToDetect': [
'string',
],
'OutputColumnName': 'string',
'SampleFraction': 123.0,
'ThresholdFraction': 123.0,
'MaskValue': 'string'
},
'Aggregate': {
'Name': 'string',
'Inputs': [
'string',
],
'Groups': [
[
'string',
],
],
'Aggs': [
{
'Column': [
'string',
],
'AggFunc': 'avg'|'countDistinct'|'count'|'first'|'last'|'kurtosis'|'max'|'min'|'skewness'|'stddev_samp'|'stddev_pop'|'sum'|'sumDistinct'|'var_samp'|'var_pop'
},
]
},
'DropDuplicates': {
'Name': 'string',
'Inputs': [
'string',
],
'Columns': [
[
'string',
],
]
},
'GovernedCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'GovernedCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'MicrosoftSQLServerCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MicrosoftSQLServerCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'DynamicTransform': {
'Name': 'string',
'TransformName': 'string',
'Inputs': [
'string',
],
'Parameters': [
{
'Name': 'string',
'Type': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'ValidationRule': 'string',
'ValidationMessage': 'string',
'Value': [
'string',
],
'ListType': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'IsOptional': True|False
},
],
'FunctionName': 'string',
'Path': 'string',
'Version': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'EvaluateDataQuality': {
'Name': 'string',
'Inputs': [
'string',
],
'Ruleset': 'string',
'Output': 'PrimaryInput'|'EvaluationResults',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'S3CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalHudiOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3HudiDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Compression': 'gzip'|'lzo'|'uncompressed'|'snappy',
'PartitionKeys': [
[
'string',
],
],
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'DirectJDBCSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'ConnectionName': 'string',
'ConnectionType': 'sqlserver'|'mysql'|'oracle'|'postgresql'|'redshift',
'RedshiftTmpDir': 'string'
},
'S3CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalDeltaOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3DeltaDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'uncompressed'|'snappy',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'AmazonRedshiftSource': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
}
},
'AmazonRedshiftTarget': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'EvaluateDataQualityMultiFrame': {
'Name': 'string',
'Inputs': [
'string',
],
'AdditionalDataSources': {
'string': 'string'
},
'Ruleset': 'string',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'AdditionalOptions': {
'string': 'string'
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'Recipe': {
'Name': 'string',
'Inputs': [
'string',
],
'RecipeReference': {
'RecipeArn': 'string',
'RecipeVersion': 'string'
},
'RecipeSteps': [
{
'Action': {
'Operation': 'string',
'Parameters': {
'string': 'string'
}
},
'ConditionExpressions': [
{
'Condition': 'string',
'Value': 'string',
'TargetColumn': 'string'
},
]
},
]
},
'SnowflakeSource': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SnowflakeTarget': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'ConnectorDataSource': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'ConnectorDataTarget': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'Inputs': [
'string',
]
}
}
},
'ExecutionClass': 'FLEX'|'STANDARD',
'SourceControlDetails': {
'Provider': 'GITHUB'|'GITLAB'|'BITBUCKET'|'AWS_CODE_COMMIT',
'Repository': 'string',
'Owner': 'string',
'Branch': 'string',
'Folder': 'string',
'LastCommitId': 'string',
'AuthStrategy': 'PERSONAL_ACCESS_TOKEN'|'AWS_SECRETS_MANAGER',
'AuthToken': 'string'
},
'MaintenanceWindow': 'string',
'ProfileName': 'string'
}
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetJob>`_
{'Jobs': {'CodeGenConfigurationNodes': {'CatalogTarget': {'PartitionKeys': [['string']]}}}}
Retrieves all current job definitions.
See also: AWS API Documentation
Request Syntax
client.get_jobs(
NextToken='string',
MaxResults=123
)
string
A continuation token, if this is a continuation call.
integer
The maximum size of the response.
dict
Response Syntax
{
'Jobs': [
{
'Name': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'Description': 'string',
'LogUri': 'string',
'Role': 'string',
'CreatedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'ExecutionProperty': {
'MaxConcurrentRuns': 123
},
'Command': {
'Name': 'string',
'ScriptLocation': 'string',
'PythonVersion': 'string',
'Runtime': 'string'
},
'DefaultArguments': {
'string': 'string'
},
'NonOverridableArguments': {
'string': 'string'
},
'Connections': {
'Connections': [
'string',
]
},
'MaxRetries': 123,
'AllocatedCapacity': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'CodeGenConfigurationNodes': {
'string': {
'AthenaConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'ConnectionTable': 'string',
'SchemaName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'JDBCConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'FilterPredicate': 'string',
'PartitionColumn': 'string',
'LowerBound': 123,
'UpperBound': 123,
'NumPartitions': 123,
'JobBookmarkKeys': [
'string',
],
'JobBookmarkKeysSortOrder': 'string',
'DataTypeMapping': {
'string': 'DATE'|'STRING'|'TIMESTAMP'|'INT'|'FLOAT'|'LONG'|'BIGDECIMAL'|'BYTE'|'SHORT'|'DOUBLE'
}
},
'ConnectionTable': 'string',
'Query': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'RedshiftSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string'
},
'S3CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'S3CsvSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'Separator': 'comma'|'ctrla'|'pipe'|'semicolon'|'tab',
'Escaper': 'string',
'QuoteChar': 'quote'|'quillemet'|'single_quote'|'disabled',
'Multiline': True|False,
'WithHeader': True|False,
'WriteHeader': True|False,
'SkipFirst': True|False,
'OptimizePerformance': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3JsonSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'JsonPath': 'string',
'Multiline': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3ParquetSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'RelationalCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'DynamoDBCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'JDBCConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectionTable': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Database': 'string',
'Table': 'string'
},
'RedshiftTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string',
'UpsertRedshiftOptions': {
'TableLocation': 'string',
'ConnectionName': 'string',
'UpsertKeys': [
'string',
]
}
},
'S3CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3GlueParquetTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'S3DirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'string',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'ApplyMapping': {
'Name': 'string',
'Inputs': [
'string',
],
'Mapping': [
{
'ToKey': 'string',
'FromPath': [
'string',
],
'FromType': 'string',
'ToType': 'string',
'Dropped': True|False,
'Children': {'... recursive ...'}
},
]
},
'SelectFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'DropFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'RenameField': {
'Name': 'string',
'Inputs': [
'string',
],
'SourcePath': [
'string',
],
'TargetPath': [
'string',
]
},
'Spigot': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Topk': 123,
'Prob': 123.0
},
'Join': {
'Name': 'string',
'Inputs': [
'string',
],
'JoinType': 'equijoin'|'left'|'right'|'outer'|'leftsemi'|'leftanti',
'Columns': [
{
'From': 'string',
'Keys': [
[
'string',
],
]
},
]
},
'SplitFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'SelectFromCollection': {
'Name': 'string',
'Inputs': [
'string',
],
'Index': 123
},
'FillMissingValues': {
'Name': 'string',
'Inputs': [
'string',
],
'ImputedPath': 'string',
'FilledPath': 'string'
},
'Filter': {
'Name': 'string',
'Inputs': [
'string',
],
'LogicalOperator': 'AND'|'OR',
'Filters': [
{
'Operation': 'EQ'|'LT'|'GT'|'LTE'|'GTE'|'REGEX'|'ISNULL',
'Negated': True|False,
'Values': [
{
'Type': 'COLUMNEXTRACTED'|'CONSTANT',
'Value': [
'string',
]
},
]
},
]
},
'CustomCode': {
'Name': 'string',
'Inputs': [
'string',
],
'Code': 'string',
'ClassName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkSQL': {
'Name': 'string',
'Inputs': [
'string',
],
'SqlQuery': 'string',
'SqlAliases': [
{
'From': 'string',
'Alias': 'string'
},
],
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'DirectKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DirectKafkaSource': {
'Name': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'WindowSize': 123,
'DetectSchema': True|False,
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKafkaSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DropNullFields': {
'Name': 'string',
'Inputs': [
'string',
],
'NullCheckBoxList': {
'IsEmpty': True|False,
'IsNullString': True|False,
'IsNegOne': True|False
},
'NullTextList': [
{
'Value': 'string',
'Datatype': {
'Id': 'string',
'Label': 'string'
}
},
]
},
'Merge': {
'Name': 'string',
'Inputs': [
'string',
],
'Source': 'string',
'PrimaryKeys': [
[
'string',
],
]
},
'Union': {
'Name': 'string',
'Inputs': [
'string',
],
'UnionType': 'ALL'|'DISTINCT'
},
'PIIDetection': {
'Name': 'string',
'Inputs': [
'string',
],
'PiiType': 'RowAudit'|'RowMasking'|'ColumnAudit'|'ColumnMasking',
'EntityTypesToDetect': [
'string',
],
'OutputColumnName': 'string',
'SampleFraction': 123.0,
'ThresholdFraction': 123.0,
'MaskValue': 'string'
},
'Aggregate': {
'Name': 'string',
'Inputs': [
'string',
],
'Groups': [
[
'string',
],
],
'Aggs': [
{
'Column': [
'string',
],
'AggFunc': 'avg'|'countDistinct'|'count'|'first'|'last'|'kurtosis'|'max'|'min'|'skewness'|'stddev_samp'|'stddev_pop'|'sum'|'sumDistinct'|'var_samp'|'var_pop'
},
]
},
'DropDuplicates': {
'Name': 'string',
'Inputs': [
'string',
],
'Columns': [
[
'string',
],
]
},
'GovernedCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'GovernedCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'MicrosoftSQLServerCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MicrosoftSQLServerCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'DynamicTransform': {
'Name': 'string',
'TransformName': 'string',
'Inputs': [
'string',
],
'Parameters': [
{
'Name': 'string',
'Type': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'ValidationRule': 'string',
'ValidationMessage': 'string',
'Value': [
'string',
],
'ListType': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'IsOptional': True|False
},
],
'FunctionName': 'string',
'Path': 'string',
'Version': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'EvaluateDataQuality': {
'Name': 'string',
'Inputs': [
'string',
],
'Ruleset': 'string',
'Output': 'PrimaryInput'|'EvaluationResults',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'S3CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalHudiOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3HudiDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Compression': 'gzip'|'lzo'|'uncompressed'|'snappy',
'PartitionKeys': [
[
'string',
],
],
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'DirectJDBCSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'ConnectionName': 'string',
'ConnectionType': 'sqlserver'|'mysql'|'oracle'|'postgresql'|'redshift',
'RedshiftTmpDir': 'string'
},
'S3CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalDeltaOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3DeltaDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'uncompressed'|'snappy',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'AmazonRedshiftSource': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
}
},
'AmazonRedshiftTarget': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'EvaluateDataQualityMultiFrame': {
'Name': 'string',
'Inputs': [
'string',
],
'AdditionalDataSources': {
'string': 'string'
},
'Ruleset': 'string',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'AdditionalOptions': {
'string': 'string'
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'Recipe': {
'Name': 'string',
'Inputs': [
'string',
],
'RecipeReference': {
'RecipeArn': 'string',
'RecipeVersion': 'string'
},
'RecipeSteps': [
{
'Action': {
'Operation': 'string',
'Parameters': {
'string': 'string'
}
},
'ConditionExpressions': [
{
'Condition': 'string',
'Value': 'string',
'TargetColumn': 'string'
},
]
},
]
},
'SnowflakeSource': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SnowflakeTarget': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'ConnectorDataSource': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'ConnectorDataTarget': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'Inputs': [
'string',
]
}
}
},
'ExecutionClass': 'FLEX'|'STANDARD',
'SourceControlDetails': {
'Provider': 'GITHUB'|'GITLAB'|'BITBUCKET'|'AWS_CODE_COMMIT',
'Repository': 'string',
'Owner': 'string',
'Branch': 'string',
'Folder': 'string',
'LastCommitId': 'string',
'AuthStrategy': 'PERSONAL_ACCESS_TOKEN'|'AWS_SECRETS_MANAGER',
'AuthToken': 'string'
},
'MaintenanceWindow': 'string',
'ProfileName': 'string'
},
],
'NextToken': 'string'
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/GetJobs>`_
{'IncludeStatusDetails': 'boolean'}
Response {'Table': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT | '
'ATHENA | '
'SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED | '
'IN_PROGRESS | '
'SUCCESS | '
'STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | SUCCESS | STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}
Retrieves the Table definition in a Data Catalog for a specified table.
See also: AWS API Documentation
Request Syntax
client.get_table(
CatalogId='string',
DatabaseName='string',
Name='string',
TransactionId='string',
QueryAsOfTime=datetime(2015, 1, 1),
IncludeStatusDetails=True|False
)
string
The ID of the Data Catalog where the table resides. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The name of the database in the catalog in which the table resides. For Hive compatibility, this name is entirely lowercase.
string
[REQUIRED]
The name of the table for which to retrieve the definition. For Hive compatibility, this name is entirely lowercase.
string
The transaction ID at which to read the table contents.
datetime
The time as of when to read the table contents. If not set, the most recent transaction commit time will be used. Cannot be specified along with TransactionId.
boolean
Specifies whether to include status details related to a request to create or update an Glue Data Catalog view.
dict
Response Syntax
{
'Table': {
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
}
}
Response Structure
(dict) --
Table (dict) --
The Table object that defines the specified table.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
{'TableVersion': {'Table': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED '
'| '
'IN_PROGRESS '
'| '
'SUCCESS '
'| '
'STOPPED '
'| '
'FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | '
'SUCCESS | STOPPED | FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}}
Retrieves a specified version of a table.
See also: AWS API Documentation
Request Syntax
client.get_table_version(
CatalogId='string',
DatabaseName='string',
TableName='string',
VersionId='string'
)
string
The ID of the Data Catalog where the tables reside. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The database in the catalog in which the table resides. For Hive compatibility, this name is entirely lowercase.
string
[REQUIRED]
The name of the table. For Hive compatibility, this name is entirely lowercase.
string
The ID value of the table version to be retrieved. A VersionID is a string representation of an integer. Each version is incremented by 1.
dict
Response Syntax
{
'TableVersion': {
'Table': {
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
},
'VersionId': 'string'
}
}
Response Structure
(dict) --
TableVersion (dict) --
The requested table version.
Table (dict) --
The table in question.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
VersionId (string) --
The ID value that identifies this table version. A VersionId is a string representation of an integer. Each version is incremented by 1.
{'TableVersions': {'Table': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED '
'| '
'IN_PROGRESS '
'| '
'SUCCESS '
'| '
'STOPPED '
'| '
'FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | '
'SUCCESS | STOPPED | FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}}
Retrieves a list of strings that identify available versions of a specified table.
See also: AWS API Documentation
Request Syntax
client.get_table_versions(
CatalogId='string',
DatabaseName='string',
TableName='string',
NextToken='string',
MaxResults=123
)
string
The ID of the Data Catalog where the tables reside. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The database in the catalog in which the table resides. For Hive compatibility, this name is entirely lowercase.
string
[REQUIRED]
The name of the table. For Hive compatibility, this name is entirely lowercase.
string
A continuation token, if this is not the first call.
integer
The maximum number of table versions to return in one response.
dict
Response Syntax
{
'TableVersions': [
{
'Table': {
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
},
'VersionId': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
TableVersions (list) --
A list of strings identifying available versions of the specified table.
(dict) --
Specifies a version of a table.
Table (dict) --
The table in question.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
VersionId (string) --
The ID value that identifies this table version. A VersionId is a string representation of an integer. Each version is incremented by 1.
NextToken (string) --
A continuation token, if the list of available versions does not include the last one.
{'IncludeStatusDetails': 'boolean'}
Response {'TableList': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED | '
'IN_PROGRESS '
'| SUCCESS '
'| STOPPED '
'| FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | SUCCESS | STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}
Retrieves the definitions of some or all of the tables in a given Database.
See also: AWS API Documentation
Request Syntax
client.get_tables(
CatalogId='string',
DatabaseName='string',
Expression='string',
NextToken='string',
MaxResults=123,
TransactionId='string',
QueryAsOfTime=datetime(2015, 1, 1),
IncludeStatusDetails=True|False
)
string
The ID of the Data Catalog where the tables reside. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The database in the catalog whose tables to list. For Hive compatibility, this name is entirely lowercase.
string
A regular expression pattern. If present, only those tables whose names match the pattern are returned.
string
A continuation token, included if this is a continuation call.
integer
The maximum number of tables to return in a single response.
string
The transaction ID at which to read the table contents.
datetime
The time as of when to read the table contents. If not set, the most recent transaction commit time will be used. Cannot be specified along with TransactionId.
boolean
Specifies whether to include status details related to a request to create or update an Glue Data Catalog view.
dict
Response Syntax
{
'TableList': [
{
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
TableList (list) --
A list of the requested Table objects.
(dict) --
Represents a collection of related data organized in columns and rows.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
NextToken (string) --
A continuation token, present if the current list segment is not the last.
{'Table': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT | '
'ATHENA | '
'SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED | '
'IN_PROGRESS | '
'SUCCESS | '
'STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | SUCCESS | STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}
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.
See also: AWS API Documentation
Request Syntax
client.get_unfiltered_table_metadata(
Region='string',
CatalogId='string',
DatabaseName='string',
Name='string',
AuditContext={
'AdditionalAuditContext': 'string',
'RequestedColumns': [
'string',
],
'AllColumnsRequested': True|False
},
SupportedPermissionTypes=[
'COLUMN_PERMISSION'|'CELL_FILTER_PERMISSION'|'NESTED_PERMISSION'|'NESTED_CELL_PERMISSION',
],
ParentResourceArn='string',
RootResourceArn='string',
SupportedDialect={
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string'
},
Permissions=[
'ALL'|'SELECT'|'ALTER'|'DROP'|'DELETE'|'INSERT'|'CREATE_DATABASE'|'CREATE_TABLE'|'DATA_LOCATION_ACCESS',
],
QuerySessionContext={
'QueryId': 'string',
'QueryStartTime': datetime(2015, 1, 1),
'ClusterId': 'string',
'QueryAuthorizationId': 'string',
'AdditionalContext': {
'string': 'string'
}
}
)
string
Specified only if the base tables belong to a different Amazon Web Services Region.
string
[REQUIRED]
The catalog ID where the table resides.
string
[REQUIRED]
(Required) Specifies the name of a database that contains the table.
string
[REQUIRED]
(Required) Specifies the name of a table for which you are requesting metadata.
dict
A structure containing Lake Formation audit context information.
AdditionalAuditContext (string) --
A string containing the additional audit context information.
RequestedColumns (list) --
The requested columns for audit.
(string) --
AllColumnsRequested (boolean) --
All columns request for audit.
list
[REQUIRED]
Indicates the level of filtering a third-party analytical engine is capable of enforcing when calling the GetUnfilteredTableMetadata API operation. Accepted values are:
COLUMN_PERMISSION - Column permissions ensure that users can access only specific columns in the table. If there are particular columns contain sensitive data, data lake administrators can define column filters that exclude access to specific columns.
CELL_FILTER_PERMISSION - Cell-level filtering combines column filtering (include or exclude columns) and row filter expressions to restrict access to individual elements in the table.
NESTED_PERMISSION - Nested permissions combines cell-level filtering and nested column filtering to restrict access to columns and/or nested columns in specific rows based on row filter expressions.
NESTED_CELL_PERMISSION - Nested cell permissions combines nested permission with nested cell-level filtering. This allows different subsets of nested columns to be restricted based on an array of row filter expressions.
Note: Each of these permission types follows a hierarchical order where each subsequent permission type includes all permission of the previous type.
Important: If you provide a supported permission type that doesn't match the user's level of permissions on the table, then Lake Formation raises an exception. For example, if the third-party engine calling the GetUnfilteredTableMetadata operation can enforce only column-level filtering, and the user has nested cell filtering applied on the table, Lake Formation throws an exception, and will not return unfiltered table metadata and data access credentials.
(string) --
string
The resource ARN of the view.
string
The resource ARN of the root view in a chain of nested views.
dict
A structure specifying the dialect and dialect version used by the query engine.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
list
The Lake Formation data permissions of the caller on the table. Used to authorize the call when no view context is found.
(string) --
dict
A structure used as a protocol between query engines and Lake Formation or Glue. Contains both a Lake Formation generated authorization identifier and information from the request's authorization context.
QueryId (string) --
A unique identifier generated by the query engine for the query.
QueryStartTime (datetime) --
A timestamp provided by the query engine for when the query started.
ClusterId (string) --
An identifier string for the consumer cluster.
QueryAuthorizationId (string) --
A cryptographically generated query identifier generated by Glue or Lake Formation.
AdditionalContext (dict) --
An opaque string-string map passed by the query engine.
(string) --
(string) --
dict
Response Syntax
{
'Table': {
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
},
'AuthorizedColumns': [
'string',
],
'IsRegisteredWithLakeFormation': True|False,
'CellFilters': [
{
'ColumnName': 'string',
'RowFilterExpression': 'string'
},
],
'QueryAuthorizationId': 'string',
'IsMultiDialectView': True|False,
'ResourceArn': 'string',
'IsProtected': True|False,
'Permissions': [
'ALL'|'SELECT'|'ALTER'|'DROP'|'DELETE'|'INSERT'|'CREATE_DATABASE'|'CREATE_TABLE'|'DATA_LOCATION_ACCESS',
],
'RowFilter': 'string'
}
Response Structure
(dict) --
Table (dict) --
A Table object containing the table metadata.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
AuthorizedColumns (list) --
A list of column names that the user has been granted access to.
(string) --
IsRegisteredWithLakeFormation (boolean) --
A Boolean value that indicates whether the partition location is registered with Lake Formation.
CellFilters (list) --
A list of column row filters.
(dict) --
A filter that uses both column-level and row-level filtering.
ColumnName (string) --
A string containing the name of the column.
RowFilterExpression (string) --
A string containing the row-level filter expression.
QueryAuthorizationId (string) --
A cryptographically generated query identifier generated by Glue or Lake Formation.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
ResourceArn (string) --
The resource ARN of the parent resource extracted from the request.
IsProtected (boolean) --
A flag that instructs the engine not to push user-provided operations into the logical plan of the view during query planning. However, if set this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Permissions (list) --
The Lake Formation data permissions of the caller on the table. Used to authorize the call when no view context is found.
(string) --
RowFilter (string) --
The filter that applies to the table. For example when applying the filter in SQL, it would go in the WHERE clause and can be evaluated by using an AND operator with any other predicates applied by the user querying the table.
{'IncludeStatusDetails': 'boolean'}
Response {'TableList': {'Status': {'Action': 'UPDATE | CREATE',
'Details': {'RequestedChange': {'CatalogId': 'string',
'CreateTime': 'timestamp',
'CreatedBy': 'string',
'DatabaseName': 'string',
'Description': 'string',
'FederatedTable': {'ConnectionName': 'string',
'DatabaseIdentifier': 'string',
'Identifier': 'string'},
'IsMultiDialectView': 'boolean',
'IsRegisteredWithLakeFormation': 'boolean',
'LastAccessTime': 'timestamp',
'LastAnalyzedTime': 'timestamp',
'Name': 'string',
'Owner': 'string',
'Parameters': {'string': 'string'},
'PartitionKeys': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Retention': 'integer',
'Status': (),
'StorageDescriptor': {'AdditionalLocations': ['string'],
'BucketColumns': ['string'],
'Columns': [{'Comment': 'string',
'Name': 'string',
'Parameters': {'string': 'string'},
'Type': 'string'}],
'Compressed': 'boolean',
'InputFormat': 'string',
'Location': 'string',
'NumberOfBuckets': 'integer',
'OutputFormat': 'string',
'Parameters': {'string': 'string'},
'SchemaReference': {'SchemaId': {'RegistryName': 'string',
'SchemaArn': 'string',
'SchemaName': 'string'},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 'long'},
'SerdeInfo': {'Name': 'string',
'Parameters': {'string': 'string'},
'SerializationLibrary': 'string'},
'SkewedInfo': {'SkewedColumnNames': ['string'],
'SkewedColumnValueLocationMaps': {'string': 'string'},
'SkewedColumnValues': ['string']},
'SortColumns': [{'Column': 'string',
'SortOrder': 'integer'}],
'StoredAsSubDirectories': 'boolean'},
'TableType': 'string',
'TargetTable': {'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'},
'UpdateTime': 'timestamp',
'VersionId': 'string',
'ViewDefinition': {'Definer': 'string',
'IsProtected': 'boolean',
'Representations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| '
'SPARK',
'DialectVersion': 'string',
'IsStale': 'boolean',
'ValidationConnection': 'string',
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'}],
'SubObjects': ['string']},
'ViewExpandedText': 'string',
'ViewOriginalText': 'string'},
'ViewValidations': [{'Dialect': 'REDSHIFT '
'| '
'ATHENA '
'| SPARK',
'DialectVersion': 'string',
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'State': 'QUEUED | '
'IN_PROGRESS '
'| SUCCESS '
'| STOPPED '
'| FAILED',
'UpdateTime': 'timestamp',
'ViewValidationText': 'string'}]},
'Error': {'ErrorCode': 'string',
'ErrorMessage': 'string'},
'RequestTime': 'timestamp',
'RequestedBy': 'string',
'State': 'QUEUED | IN_PROGRESS | SUCCESS | STOPPED | '
'FAILED',
'UpdateTime': 'timestamp',
'UpdatedBy': 'string'}}}
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.
See also: AWS API Documentation
Request Syntax
client.search_tables(
CatalogId='string',
NextToken='string',
Filters=[
{
'Key': 'string',
'Value': 'string',
'Comparator': 'EQUALS'|'GREATER_THAN'|'LESS_THAN'|'GREATER_THAN_EQUALS'|'LESS_THAN_EQUALS'
},
],
SearchText='string',
SortCriteria=[
{
'FieldName': 'string',
'Sort': 'ASC'|'DESC'
},
],
MaxResults=123,
ResourceShareType='FOREIGN'|'ALL'|'FEDERATED',
IncludeStatusDetails=True|False
)
string
A unique identifier, consisting of ``account_id ``.
string
A continuation token, included if this is a continuation call.
list
A list of key-value pairs, and a comparator used to filter the search results. Returns all entities matching the predicate.
The Comparator member of the PropertyPredicate struct is used only for time fields, and can be omitted for other field types. Also, when comparing string values, such as when Key=Name, a fuzzy match algorithm is used. The Key field (for example, the value of the Name field) is split on certain punctuation characters, for example, -, :, #, etc. into tokens. Then each token is exact-match compared with the Value member of PropertyPredicate. For example, if Key=Name and Value=link, tables named customer-link and xx-link-yy are returned, but xxlinkyy is not returned.
(dict) --
Defines a property predicate.
Key (string) --
The key of the property.
Value (string) --
The value of the property.
Comparator (string) --
The comparator used to compare this property to others.
string
A string used for a text search.
Specifying a value in quotes filters based on an exact match to the value.
list
A list of criteria for sorting the results by a field name, in an ascending or descending order.
(dict) --
Specifies a field to sort by and a sort order.
FieldName (string) --
The name of the field on which to sort.
Sort (string) --
An ascending or descending sort.
integer
The maximum number of tables to return in a single response.
string
Allows you to specify that you want to search the tables shared with your account. The allowable values are FOREIGN or ALL.
If set to FOREIGN, will search the tables shared with your account.
If set to ALL, will search the tables shared with your account, as well as the tables in yor local account.
boolean
Specifies whether to include status details related to a request to create or update an Glue Data Catalog view.
dict
Response Syntax
{
'NextToken': 'string',
'TableList': [
{
'Name': 'string',
'DatabaseName': 'string',
'Description': 'string',
'Owner': 'string',
'CreateTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'LastAccessTime': datetime(2015, 1, 1),
'LastAnalyzedTime': datetime(2015, 1, 1),
'Retention': 123,
'StorageDescriptor': {
'Columns': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'Location': 'string',
'AdditionalLocations': [
'string',
],
'InputFormat': 'string',
'OutputFormat': 'string',
'Compressed': True|False,
'NumberOfBuckets': 123,
'SerdeInfo': {
'Name': 'string',
'SerializationLibrary': 'string',
'Parameters': {
'string': 'string'
}
},
'BucketColumns': [
'string',
],
'SortColumns': [
{
'Column': 'string',
'SortOrder': 123
},
],
'Parameters': {
'string': 'string'
},
'SkewedInfo': {
'SkewedColumnNames': [
'string',
],
'SkewedColumnValues': [
'string',
],
'SkewedColumnValueLocationMaps': {
'string': 'string'
}
},
'StoredAsSubDirectories': True|False,
'SchemaReference': {
'SchemaId': {
'SchemaArn': 'string',
'SchemaName': 'string',
'RegistryName': 'string'
},
'SchemaVersionId': 'string',
'SchemaVersionNumber': 123
}
},
'PartitionKeys': [
{
'Name': 'string',
'Type': 'string',
'Comment': 'string',
'Parameters': {
'string': 'string'
}
},
],
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'TableType': 'string',
'Parameters': {
'string': 'string'
},
'CreatedBy': 'string',
'IsRegisteredWithLakeFormation': True|False,
'TargetTable': {
'CatalogId': 'string',
'DatabaseName': 'string',
'Name': 'string',
'Region': 'string'
},
'CatalogId': 'string',
'VersionId': 'string',
'FederatedTable': {
'Identifier': 'string',
'DatabaseIdentifier': 'string',
'ConnectionName': 'string'
},
'ViewDefinition': {
'IsProtected': True|False,
'Definer': 'string',
'SubObjects': [
'string',
],
'Representations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewOriginalText': 'string',
'ViewExpandedText': 'string',
'ValidationConnection': 'string',
'IsStale': True|False
},
]
},
'IsMultiDialectView': True|False,
'Status': {
'RequestedBy': 'string',
'UpdatedBy': 'string',
'RequestTime': datetime(2015, 1, 1),
'UpdateTime': datetime(2015, 1, 1),
'Action': 'UPDATE'|'CREATE',
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
},
'Details': {
'RequestedChange': {'... recursive ...'},
'ViewValidations': [
{
'Dialect': 'REDSHIFT'|'ATHENA'|'SPARK',
'DialectVersion': 'string',
'ViewValidationText': 'string',
'UpdateTime': datetime(2015, 1, 1),
'State': 'QUEUED'|'IN_PROGRESS'|'SUCCESS'|'STOPPED'|'FAILED',
'Error': {
'ErrorCode': 'string',
'ErrorMessage': 'string'
}
},
]
}
}
},
]
}
Response Structure
(dict) --
NextToken (string) --
A continuation token, present if the current list segment is not the last.
TableList (list) --
A list of the requested Table objects. The SearchTables response returns only the tables that you have access to.
(dict) --
Represents a collection of related data organized in columns and rows.
Name (string) --
The table name. For Hive compatibility, this must be entirely lowercase.
DatabaseName (string) --
The name of the database where the table metadata resides. For Hive compatibility, this must be all lowercase.
Description (string) --
A description of the table.
Owner (string) --
The owner of the table.
CreateTime (datetime) --
The time when the table definition was created in the Data Catalog.
UpdateTime (datetime) --
The last time that the table was updated.
LastAccessTime (datetime) --
The last time that the table was accessed. This is usually taken from HDFS, and might not be reliable.
LastAnalyzedTime (datetime) --
The last time that column statistics were computed for this table.
Retention (integer) --
The retention time for this table.
StorageDescriptor (dict) --
A storage descriptor containing information about the physical storage of this table.
Columns (list) --
A list of the Columns in the table.
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
Location (string) --
The physical location of the table. By default, this takes the form of the warehouse location, followed by the database location in the warehouse, followed by the table name.
AdditionalLocations (list) --
A list of locations that point to the path where a Delta table is located.
(string) --
InputFormat (string) --
The input format: SequenceFileInputFormat (binary), or TextInputFormat, or a custom format.
OutputFormat (string) --
The output format: SequenceFileOutputFormat (binary), or IgnoreKeyTextOutputFormat, or a custom format.
Compressed (boolean) --
True if the data in the table is compressed, or False if not.
NumberOfBuckets (integer) --
Must be specified if the table contains any dimension columns.
SerdeInfo (dict) --
The serialization/deserialization (SerDe) information.
Name (string) --
Name of the SerDe.
SerializationLibrary (string) --
Usually the class that implements the SerDe. An example is org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe.
Parameters (dict) --
These key-value pairs define initialization parameters for the SerDe.
(string) --
(string) --
BucketColumns (list) --
A list of reducer grouping columns, clustering columns, and bucketing columns in the table.
(string) --
SortColumns (list) --
A list specifying the sort order of each bucket in the table.
(dict) --
Specifies the sort order of a sorted column.
Column (string) --
The name of the column.
SortOrder (integer) --
Indicates that the column is sorted in ascending order ( == 1), or in descending order ( ==0).
Parameters (dict) --
The user-supplied properties in key-value form.
(string) --
(string) --
SkewedInfo (dict) --
The information about values that appear frequently in a column (skewed values).
SkewedColumnNames (list) --
A list of names of columns that contain skewed values.
(string) --
SkewedColumnValues (list) --
A list of values that appear so frequently as to be considered skewed.
(string) --
SkewedColumnValueLocationMaps (dict) --
A mapping of skewed values to the columns that contain them.
(string) --
(string) --
StoredAsSubDirectories (boolean) --
True if the table data is stored in subdirectories, or False if not.
SchemaReference (dict) --
An object that references a schema stored in the Glue Schema Registry.
When creating a table, you can pass an empty list of columns for the schema, and instead use a schema reference.
SchemaId (dict) --
A structure that contains schema identity fields. Either this or the SchemaVersionId has to be provided.
SchemaArn (string) --
The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName has to be provided.
SchemaName (string) --
The name of the schema. One of SchemaArn or SchemaName has to be provided.
RegistryName (string) --
The name of the schema registry that contains the schema.
SchemaVersionId (string) --
The unique ID assigned to a version of the schema. Either this or the SchemaId has to be provided.
SchemaVersionNumber (integer) --
The version number of the schema.
PartitionKeys (list) --
A list of columns by which the table is partitioned. Only primitive types are supported as partition keys.
When you create a table used by Amazon Athena, and you do not specify any partitionKeys, you must at least set the value of partitionKeys to an empty list. For example:
"PartitionKeys": []
(dict) --
A column in a Table.
Name (string) --
The name of the Column.
Type (string) --
The data type of the Column.
Comment (string) --
A free-form text comment.
Parameters (dict) --
These key-value pairs define properties associated with the column.
(string) --
(string) --
ViewOriginalText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations. If the table is a VIRTUAL_VIEW, certain Athena configuration encoded in base64.
ViewExpandedText (string) --
Included for Apache Hive compatibility. Not used in the normal course of Glue operations.
TableType (string) --
The type of this table. Glue will create tables with the EXTERNAL_TABLE type. Other services, such as Athena, may create tables with additional table types.
Glue related table types:
EXTERNAL_TABLE
Hive compatible attribute - indicates a non-Hive managed table.
GOVERNED
Used by Lake Formation. The Glue Data Catalog understands GOVERNED.
Parameters (dict) --
These key-value pairs define properties associated with the table.
(string) --
(string) --
CreatedBy (string) --
The person or entity who created the table.
IsRegisteredWithLakeFormation (boolean) --
Indicates whether the table has been registered with Lake Formation.
TargetTable (dict) --
A TableIdentifier structure that describes a target table for resource linking.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
DatabaseName (string) --
The name of the catalog database that contains the target table.
Name (string) --
The name of the target table.
Region (string) --
Region of the target table.
CatalogId (string) --
The ID of the Data Catalog in which the table resides.
VersionId (string) --
The ID of the table version.
FederatedTable (dict) --
A FederatedTable structure that references an entity outside the Glue Data Catalog.
Identifier (string) --
A unique identifier for the federated table.
DatabaseIdentifier (string) --
A unique identifier for the federated database.
ConnectionName (string) --
The name of the connection to the external metastore.
ViewDefinition (dict) --
A structure that contains all the information that defines the view, including the dialect or dialects for the view, and the query.
IsProtected (boolean) --
You can set this flag as true to instruct the engine not to push user-provided operations into the logical plan of the view during query planning. However, setting this flag does not guarantee that the engine will comply. Refer to the engine's documentation to understand the guarantees provided, if any.
Definer (string) --
The definer of a view in SQL.
SubObjects (list) --
A list of table Amazon Resource Names (ARNs).
(string) --
Representations (list) --
A list of representations.
(dict) --
A structure that contains the dialect of the view, and the query that defines the view.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewOriginalText (string) --
The SELECT query provided by the customer during CREATE VIEW DDL. This SQL is not used during a query on a view ( ViewExpandedText is used instead). ViewOriginalText is used for cases like SHOW CREATE VIEW where users want to see the original DDL command that created the view.
ViewExpandedText (string) --
The expanded SQL for the view. This SQL is used by engines while processing a query on a view. Engines may perform operations during view creation to transform ViewOriginalText to ViewExpandedText. For example:
Fully qualified identifiers: SELECT * from table1 -> SELECT * from db1.table1
ValidationConnection (string) --
The name of the connection to be used to validate the specific representation of the view.
IsStale (boolean) --
Dialects marked as stale are no longer valid and must be updated before they can be queried in their respective query engines.
IsMultiDialectView (boolean) --
Specifies whether the view supports the SQL dialects of one or more different query engines and can therefore be read by those engines.
Status (dict) --
A structure containing information about the state of an asynchronous change to a table.
RequestedBy (string) --
The ARN of the user who requested the asynchronous change.
UpdatedBy (string) --
The ARN of the user to last manually alter the asynchronous change (requesting cancellation, etc).
RequestTime (datetime) --
An ISO 8601 formatted date string indicating the time that the change was initiated.
UpdateTime (datetime) --
An ISO 8601 formatted date string indicating the time that the state was last updated.
Action (string) --
Indicates which action was called on the table, currently only CREATE or UPDATE.
State (string) --
A generic status for the change in progress, such as QUEUED, IN_PROGRESS, SUCCESS, or FAILED.
Error (dict) --
An error that will only appear when the state is "FAILED". This is a parent level exception message, there may be different ``Error``s for each dialect.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
Details (dict) --
A StatusDetails object with information about the requested change.
RequestedChange (dict) --
A Table object representing the requested changes.
ViewValidations (list) --
A list of ViewValidation objects that contain information for an analytical engine to validate a view.
(dict) --
A structure that contains information for an analytical engine to validate a view, prior to persisting the view metadata. Used in the case of direct UpdateTable or CreateTable API calls.
Dialect (string) --
The dialect of the query engine.
DialectVersion (string) --
The version of the dialect of the query engine. For example, 3.0.0.
ViewValidationText (string) --
The SELECT query that defines the view, as provided by the customer.
UpdateTime (datetime) --
The time of the last update.
State (string) --
The state of the validation.
Error (dict) --
An error associated with the validation.
ErrorCode (string) --
The code associated with this error.
ErrorMessage (string) --
A message describing the error.
{'ConnectionInput': {'ConnectionType': {'VIEW_VALIDATION_ATHENA',
'VIEW_VALIDATION_REDSHIFT'}}}
Updates a connection definition in the Data Catalog.
See also: AWS API Documentation
Request Syntax
client.update_connection(
CatalogId='string',
Name='string',
ConnectionInput={
'Name': 'string',
'Description': 'string',
'ConnectionType': 'JDBC'|'SFTP'|'MONGODB'|'KAFKA'|'NETWORK'|'MARKETPLACE'|'CUSTOM'|'SALESFORCE'|'VIEW_VALIDATION_REDSHIFT'|'VIEW_VALIDATION_ATHENA',
'MatchCriteria': [
'string',
],
'ConnectionProperties': {
'string': 'string'
},
'PhysicalConnectionRequirements': {
'SubnetId': 'string',
'SecurityGroupIdList': [
'string',
],
'AvailabilityZone': 'string'
},
'AuthenticationConfiguration': {
'AuthenticationType': 'BASIC'|'OAUTH2'|'CUSTOM',
'SecretArn': 'string',
'OAuth2Properties': {
'OAuth2GrantType': 'AUTHORIZATION_CODE'|'CLIENT_CREDENTIALS'|'JWT_BEARER',
'OAuth2ClientApplication': {
'UserManagedClientApplicationClientId': 'string',
'AWSManagedClientApplicationReference': 'string'
},
'TokenUrl': 'string',
'TokenUrlParametersMap': {
'string': 'string'
},
'AuthorizationCodeProperties': {
'AuthorizationCode': 'string',
'RedirectUri': 'string'
}
}
},
'ValidateCredentials': True|False
}
)
string
The ID of the Data Catalog in which the connection resides. If none is provided, the Amazon Web Services account ID is used by default.
string
[REQUIRED]
The name of the connection definition to update.
dict
[REQUIRED]
A ConnectionInput object that redefines the connection in question.
Name (string) -- [REQUIRED]
The name of the connection.
Description (string) --
The description of the connection.
ConnectionType (string) -- [REQUIRED]
The type of the connection. Currently, these types are supported:
JDBC - Designates a connection to a database through Java Database Connectivity (JDBC). JDBC Connections use the following ConnectionParameters.
Required: All of ( HOST, PORT, JDBC_ENGINE) or JDBC_CONNECTION_URL.
Required: All of ( USERNAME, PASSWORD) or SECRET_ID.
Optional: JDBC_ENFORCE_SSL, CUSTOM_JDBC_CERT, CUSTOM_JDBC_CERT_STRING, SKIP_CUSTOM_JDBC_CERT_VALIDATION. These parameters are used to configure SSL with JDBC.
KAFKA - Designates a connection to an Apache Kafka streaming platform. KAFKA Connections use the following ConnectionParameters.
Required: KAFKA_BOOTSTRAP_SERVERS.
Optional: KAFKA_SSL_ENABLED, KAFKA_CUSTOM_CERT, KAFKA_SKIP_CUSTOM_CERT_VALIDATION. These parameters are used to configure SSL with KAFKA.
Optional: KAFKA_CLIENT_KEYSTORE, KAFKA_CLIENT_KEYSTORE_PASSWORD, KAFKA_CLIENT_KEY_PASSWORD, ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD, ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD. These parameters are used to configure TLS client configuration with SSL in KAFKA.
Optional: KAFKA_SASL_MECHANISM. Can be specified as SCRAM-SHA-512, GSSAPI, or AWS_MSK_IAM.
Optional: KAFKA_SASL_SCRAM_USERNAME, KAFKA_SASL_SCRAM_PASSWORD, ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD. These parameters are used to configure SASL/SCRAM-SHA-512 authentication with KAFKA.
Optional: KAFKA_SASL_GSSAPI_KEYTAB, KAFKA_SASL_GSSAPI_KRB5_CONF, KAFKA_SASL_GSSAPI_SERVICE, KAFKA_SASL_GSSAPI_PRINCIPAL. These parameters are used to configure SASL/GSSAPI authentication with KAFKA.
MONGODB - Designates a connection to a MongoDB document database. MONGODB Connections use the following ConnectionParameters.
Required: CONNECTION_URL.
Required: All of ( USERNAME, PASSWORD) or SECRET_ID.
SALESFORCE - Designates a connection to Salesforce using OAuth authencation.
Requires the AuthenticationConfiguration member to be configured.
VIEW_VALIDATION_REDSHIFT - Designates a connection used for view validation by Amazon Redshift.
VIEW_VALIDATION_ATHENA - Designates a connection used for view validation by Amazon Athena.
NETWORK - Designates a network connection to a data source within an Amazon Virtual Private Cloud environment (Amazon VPC). NETWORK Connections do not require ConnectionParameters. Instead, provide a PhysicalConnectionRequirements.
MARKETPLACE - Uses configuration settings contained in a connector purchased from Amazon Web Services Marketplace to read from and write to data stores that are not natively supported by Glue. MARKETPLACE Connections use the following ConnectionParameters.
Required: CONNECTOR_TYPE, CONNECTOR_URL, CONNECTOR_CLASS_NAME, CONNECTION_URL.
Required for JDBC CONNECTOR_TYPE connections: All of ( USERNAME, PASSWORD) or SECRET_ID.
CUSTOM - Uses configuration settings contained in a custom connector to read from and write to data stores that are not natively supported by Glue.
SFTP is not supported.
For more information about how optional ConnectionProperties are used to configure features in Glue, consult Glue connection properties.
For more information about how optional ConnectionProperties are used to configure features in Glue Studio, consult Using connectors and connections.
MatchCriteria (list) --
A list of criteria that can be used in selecting this connection.
(string) --
ConnectionProperties (dict) -- [REQUIRED]
These key-value pairs define parameters for the connection.
(string) --
(string) --
PhysicalConnectionRequirements (dict) --
The physical connection requirements, such as virtual private cloud (VPC) and SecurityGroup, that are needed to successfully make this connection.
SubnetId (string) --
The subnet ID used by the connection.
SecurityGroupIdList (list) --
The security group ID list used by the connection.
(string) --
AvailabilityZone (string) --
The connection's Availability Zone.
AuthenticationConfiguration (dict) --
The authentication properties of the connection. Used for a Salesforce connection.
AuthenticationType (string) --
A structure containing the authentication configuration in the CreateConnection request.
SecretArn (string) --
The secret manager ARN to store credentials in the CreateConnection request.
OAuth2Properties (dict) --
The properties for OAuth2 authentication in the CreateConnection request.
OAuth2GrantType (string) --
The OAuth2 grant type in the CreateConnection request. For example, AUTHORIZATION_CODE, JWT_BEARER, or CLIENT_CREDENTIALS.
OAuth2ClientApplication (dict) --
The client application type in the CreateConnection request. For example, AWS_MANAGED or USER_MANAGED.
UserManagedClientApplicationClientId (string) --
The client application clientID if the ClientAppType is USER_MANAGED.
AWSManagedClientApplicationReference (string) --
The reference to the SaaS-side client app that is Amazon Web Services managed.
TokenUrl (string) --
The URL of the provider's authentication server, to exchange an authorization code for an access token.
TokenUrlParametersMap (dict) --
A map of parameters that are added to the token GET request.
(string) --
(string) --
AuthorizationCodeProperties (dict) --
The set of properties required for the the OAuth2 AUTHORIZATION_CODE grant type.
AuthorizationCode (string) --
An authorization code to be used in the third leg of the AUTHORIZATION_CODE grant workflow. This is a single-use code which becomes invalid once exchanged for an access token, thus it is acceptable to have this value as a request parameter.
RedirectUri (string) --
The redirect URI where the user gets redirected to by authorization server when issuing an authorization code. The URI is subsequently used when the authorization code is exchanged for an access token.
ValidateCredentials (boolean) --
A flag to validate the credentials during create connection. Used for a Salesforce connection. Default is true.
dict
Response Syntax
{}
Response Structure
(dict) --
{'JobUpdate': {'CodeGenConfigurationNodes': {'CatalogTarget': {'PartitionKeys': [['string']]}}}}
Updates an existing job definition. The previous job definition is completely overwritten by this information.
See also: AWS API Documentation
Request Syntax
client.update_job(
JobName='string',
JobUpdate={
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'Description': 'string',
'LogUri': 'string',
'Role': 'string',
'ExecutionProperty': {
'MaxConcurrentRuns': 123
},
'Command': {
'Name': 'string',
'ScriptLocation': 'string',
'PythonVersion': 'string',
'Runtime': 'string'
},
'DefaultArguments': {
'string': 'string'
},
'NonOverridableArguments': {
'string': 'string'
},
'Connections': {
'Connections': [
'string',
]
},
'MaxRetries': 123,
'AllocatedCapacity': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'CodeGenConfigurationNodes': {
'string': {
'AthenaConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'ConnectionTable': 'string',
'SchemaName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'JDBCConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'FilterPredicate': 'string',
'PartitionColumn': 'string',
'LowerBound': 123,
'UpperBound': 123,
'NumPartitions': 123,
'JobBookmarkKeys': [
'string',
],
'JobBookmarkKeysSortOrder': 'string',
'DataTypeMapping': {
'string': 'DATE'|'STRING'|'TIMESTAMP'|'INT'|'FLOAT'|'LONG'|'BIGDECIMAL'|'BYTE'|'SHORT'|'DOUBLE'
}
},
'ConnectionTable': 'string',
'Query': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorSource': {
'Name': 'string',
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'RedshiftSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string'
},
'S3CatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'S3CsvSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'Separator': 'comma'|'ctrla'|'pipe'|'semicolon'|'tab',
'Escaper': 'string',
'QuoteChar': 'quote'|'quillemet'|'single_quote'|'disabled',
'Multiline': True|False,
'WithHeader': True|False,
'WriteHeader': True|False,
'SkipFirst': True|False,
'OptimizePerformance': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3JsonSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'gzip'|'bzip2',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'JsonPath': 'string',
'Multiline': True|False,
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3ParquetSource': {
'Name': 'string',
'Paths': [
'string',
],
'CompressionType': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'Exclusions': [
'string',
],
'GroupSize': 'string',
'GroupFiles': 'string',
'Recurse': True|False,
'MaxBand': 123,
'MaxFilesInBand': 123,
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'RelationalCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'DynamoDBCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'JDBCConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectionTable': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkConnectorTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'ConnectionName': 'string',
'ConnectorName': 'string',
'ConnectionType': 'string',
'AdditionalOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Database': 'string',
'Table': 'string'
},
'RedshiftTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string',
'RedshiftTmpDir': 'string',
'TmpDirIAMRole': 'string',
'UpsertRedshiftOptions': {
'TableLocation': 'string',
'ConnectionName': 'string',
'UpsertKeys': [
'string',
]
}
},
'S3CatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3GlueParquetTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'snappy'|'lzo'|'gzip'|'uncompressed'|'none',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'S3DirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'string',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'ApplyMapping': {
'Name': 'string',
'Inputs': [
'string',
],
'Mapping': [
{
'ToKey': 'string',
'FromPath': [
'string',
],
'FromType': 'string',
'ToType': 'string',
'Dropped': True|False,
'Children': {'... recursive ...'}
},
]
},
'SelectFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'DropFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'RenameField': {
'Name': 'string',
'Inputs': [
'string',
],
'SourcePath': [
'string',
],
'TargetPath': [
'string',
]
},
'Spigot': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Topk': 123,
'Prob': 123.0
},
'Join': {
'Name': 'string',
'Inputs': [
'string',
],
'JoinType': 'equijoin'|'left'|'right'|'outer'|'leftsemi'|'leftanti',
'Columns': [
{
'From': 'string',
'Keys': [
[
'string',
],
]
},
]
},
'SplitFields': {
'Name': 'string',
'Inputs': [
'string',
],
'Paths': [
[
'string',
],
]
},
'SelectFromCollection': {
'Name': 'string',
'Inputs': [
'string',
],
'Index': 123
},
'FillMissingValues': {
'Name': 'string',
'Inputs': [
'string',
],
'ImputedPath': 'string',
'FilledPath': 'string'
},
'Filter': {
'Name': 'string',
'Inputs': [
'string',
],
'LogicalOperator': 'AND'|'OR',
'Filters': [
{
'Operation': 'EQ'|'LT'|'GT'|'LTE'|'GTE'|'REGEX'|'ISNULL',
'Negated': True|False,
'Values': [
{
'Type': 'COLUMNEXTRACTED'|'CONSTANT',
'Value': [
'string',
]
},
]
},
]
},
'CustomCode': {
'Name': 'string',
'Inputs': [
'string',
],
'Code': 'string',
'ClassName': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SparkSQL': {
'Name': 'string',
'Inputs': [
'string',
],
'SqlQuery': 'string',
'SqlAliases': [
{
'From': 'string',
'Alias': 'string'
},
],
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'DirectKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DirectKafkaSource': {
'Name': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'WindowSize': 123,
'DetectSchema': True|False,
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKinesisSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'EndpointUrl': 'string',
'StreamName': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingPosition': 'latest'|'trim_horizon'|'earliest'|'timestamp',
'MaxFetchTimeInMs': 123,
'MaxFetchRecordsPerShard': 123,
'MaxRecordPerRead': 123,
'AddIdleTimeBetweenReads': True|False,
'IdleTimeBetweenReadsInMs': 123,
'DescribeShardInterval': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxRetryIntervalMs': 123,
'AvoidEmptyBatches': True|False,
'StreamArn': 'string',
'RoleArn': 'string',
'RoleSessionName': 'string',
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'CatalogKafkaSource': {
'Name': 'string',
'WindowSize': 123,
'DetectSchema': True|False,
'Table': 'string',
'Database': 'string',
'StreamingOptions': {
'BootstrapServers': 'string',
'SecurityProtocol': 'string',
'ConnectionName': 'string',
'TopicName': 'string',
'Assign': 'string',
'SubscribePattern': 'string',
'Classification': 'string',
'Delimiter': 'string',
'StartingOffsets': 'string',
'EndingOffsets': 'string',
'PollTimeoutMs': 123,
'NumRetries': 123,
'RetryIntervalMs': 123,
'MaxOffsetsPerTrigger': 123,
'MinPartitions': 123,
'IncludeHeaders': True|False,
'AddRecordTimestamp': 'string',
'EmitConsumerLagMetrics': 'string',
'StartingTimestamp': datetime(2015, 1, 1)
},
'DataPreviewOptions': {
'PollingTime': 123,
'RecordPollingLimit': 123
}
},
'DropNullFields': {
'Name': 'string',
'Inputs': [
'string',
],
'NullCheckBoxList': {
'IsEmpty': True|False,
'IsNullString': True|False,
'IsNegOne': True|False
},
'NullTextList': [
{
'Value': 'string',
'Datatype': {
'Id': 'string',
'Label': 'string'
}
},
]
},
'Merge': {
'Name': 'string',
'Inputs': [
'string',
],
'Source': 'string',
'PrimaryKeys': [
[
'string',
],
]
},
'Union': {
'Name': 'string',
'Inputs': [
'string',
],
'UnionType': 'ALL'|'DISTINCT'
},
'PIIDetection': {
'Name': 'string',
'Inputs': [
'string',
],
'PiiType': 'RowAudit'|'RowMasking'|'ColumnAudit'|'ColumnMasking',
'EntityTypesToDetect': [
'string',
],
'OutputColumnName': 'string',
'SampleFraction': 123.0,
'ThresholdFraction': 123.0,
'MaskValue': 'string'
},
'Aggregate': {
'Name': 'string',
'Inputs': [
'string',
],
'Groups': [
[
'string',
],
],
'Aggs': [
{
'Column': [
'string',
],
'AggFunc': 'avg'|'countDistinct'|'count'|'first'|'last'|'kurtosis'|'max'|'min'|'skewness'|'stddev_samp'|'stddev_pop'|'sum'|'sumDistinct'|'var_samp'|'var_pop'
},
]
},
'DropDuplicates': {
'Name': 'string',
'Inputs': [
'string',
],
'Columns': [
[
'string',
],
]
},
'GovernedCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'GovernedCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'PartitionPredicate': 'string',
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123
}
},
'MicrosoftSQLServerCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string'
},
'MicrosoftSQLServerCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'MySQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'OracleSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'PostgreSQLCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Database': 'string',
'Table': 'string'
},
'DynamicTransform': {
'Name': 'string',
'TransformName': 'string',
'Inputs': [
'string',
],
'Parameters': [
{
'Name': 'string',
'Type': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'ValidationRule': 'string',
'ValidationMessage': 'string',
'Value': [
'string',
],
'ListType': 'str'|'int'|'float'|'complex'|'bool'|'list'|'null',
'IsOptional': True|False
},
],
'FunctionName': 'string',
'Path': 'string',
'Version': 'string',
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'EvaluateDataQuality': {
'Name': 'string',
'Inputs': [
'string',
],
'Ruleset': 'string',
'Output': 'PrimaryInput'|'EvaluationResults',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'S3CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogHudiSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalHudiOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalHudiOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3HudiCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3HudiDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'Path': 'string',
'Compression': 'gzip'|'lzo'|'uncompressed'|'snappy',
'PartitionKeys': [
[
'string',
],
],
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'DirectJDBCSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'ConnectionName': 'string',
'ConnectionType': 'sqlserver'|'mysql'|'oracle'|'postgresql'|'redshift',
'RedshiftTmpDir': 'string'
},
'S3CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'CatalogDeltaSource': {
'Name': 'string',
'Database': 'string',
'Table': 'string',
'AdditionalDeltaOptions': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaSource': {
'Name': 'string',
'Paths': [
'string',
],
'AdditionalDeltaOptions': {
'string': 'string'
},
'AdditionalOptions': {
'BoundedSize': 123,
'BoundedFiles': 123,
'EnableSamplePath': True|False,
'SamplePath': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'S3DeltaCatalogTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Table': 'string',
'Database': 'string',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG'
}
},
'S3DeltaDirectTarget': {
'Name': 'string',
'Inputs': [
'string',
],
'PartitionKeys': [
[
'string',
],
],
'Path': 'string',
'Compression': 'uncompressed'|'snappy',
'Format': 'json'|'csv'|'avro'|'orc'|'parquet'|'hudi'|'delta',
'AdditionalOptions': {
'string': 'string'
},
'SchemaChangePolicy': {
'EnableUpdateCatalog': True|False,
'UpdateBehavior': 'UPDATE_IN_DATABASE'|'LOG',
'Table': 'string',
'Database': 'string'
}
},
'AmazonRedshiftSource': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
}
},
'AmazonRedshiftTarget': {
'Name': 'string',
'Data': {
'AccessType': 'string',
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Table': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogDatabase': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogTable': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'CatalogRedshiftSchema': 'string',
'CatalogRedshiftTable': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdvancedOptions': [
{
'Key': 'string',
'Value': 'string'
},
],
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'TablePrefix': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'CrawlerConnection': 'string',
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'EvaluateDataQualityMultiFrame': {
'Name': 'string',
'Inputs': [
'string',
],
'AdditionalDataSources': {
'string': 'string'
},
'Ruleset': 'string',
'PublishingOptions': {
'EvaluationContext': 'string',
'ResultsS3Prefix': 'string',
'CloudWatchMetricsEnabled': True|False,
'ResultsPublishingEnabled': True|False
},
'AdditionalOptions': {
'string': 'string'
},
'StopJobOnFailureOptions': {
'StopJobOnFailureTiming': 'Immediate'|'AfterDataLoad'
}
},
'Recipe': {
'Name': 'string',
'Inputs': [
'string',
],
'RecipeReference': {
'RecipeArn': 'string',
'RecipeVersion': 'string'
},
'RecipeSteps': [
{
'Action': {
'Operation': 'string',
'Parameters': {
'string': 'string'
}
},
'ConditionExpressions': [
{
'Condition': 'string',
'Value': 'string',
'TargetColumn': 'string'
},
]
},
]
},
'SnowflakeSource': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'SnowflakeTarget': {
'Name': 'string',
'Data': {
'SourceType': 'string',
'Connection': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'Schema': 'string',
'Table': 'string',
'Database': 'string',
'TempDir': 'string',
'IamRole': {
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
'AdditionalOptions': {
'string': 'string'
},
'SampleQuery': 'string',
'PreAction': 'string',
'PostAction': 'string',
'Action': 'string',
'Upsert': True|False,
'MergeAction': 'string',
'MergeWhenMatched': 'string',
'MergeWhenNotMatched': 'string',
'MergeClause': 'string',
'StagingTable': 'string',
'SelectedColumns': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
],
'AutoPushdown': True|False,
'TableSchema': [
{
'Value': 'string',
'Label': 'string',
'Description': 'string'
},
]
},
'Inputs': [
'string',
]
},
'ConnectorDataSource': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'OutputSchemas': [
{
'Columns': [
{
'Name': 'string',
'Type': 'string'
},
]
},
]
},
'ConnectorDataTarget': {
'Name': 'string',
'ConnectionType': 'string',
'Data': {
'string': 'string'
},
'Inputs': [
'string',
]
}
}
},
'ExecutionClass': 'FLEX'|'STANDARD',
'SourceControlDetails': {
'Provider': 'GITHUB'|'GITLAB'|'BITBUCKET'|'AWS_CODE_COMMIT',
'Repository': 'string',
'Owner': 'string',
'Branch': 'string',
'Folder': 'string',
'LastCommitId': 'string',
'AuthStrategy': 'PERSONAL_ACCESS_TOKEN'|'AWS_SECRETS_MANAGER',
'AuthToken': 'string'
},
'MaintenanceWindow': 'string'
}
)
**Parameters**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/glue-2017-03-31/UpdateJob>`_
dict
Response Syntax
{
'JobName': 'string'
}
Response Structure
(dict) --
JobName (string) --
Returns the name of the updated job definition.