2024/05/29 - AWS Glue - 11 updated api methods
Changes Add optional field JobMode to CreateJob and UpdateJob APIs.
{'Jobs': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
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',
],
'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'
}
},
'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'
},
],
'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>`_
{'Workflows': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT '
'| '
'VISUAL '
'| '
'NOTEBOOK'}}}},
'LastRun': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT '
'| '
'VISUAL '
'| '
'NOTEBOOK'}}}}}}}
Returns a list of resource metadata for a given list of workflow names. After calling the ListWorkflows operation, you can call this operation to access the data to which you have been granted permissions. This operation supports all IAM permissions, including permission conditions that uses tags.
See also: AWS API Documentation
Request Syntax
client.batch_get_workflows(
Names=[
'string',
],
IncludeGraph=True|False
)
list
[REQUIRED]
A list of workflow names, which may be the names returned from the ListWorkflows operation.
(string) --
boolean
Specifies whether to include a graph when returning the workflow resource metadata.
dict
Response Syntax
{
'Workflows': [
{
'Name': 'string',
'Description': 'string',
'DefaultRunProperties': {
'string': 'string'
},
'CreatedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'LastRun': {
'Name': 'string',
'WorkflowRunId': 'string',
'PreviousRunId': 'string',
'WorkflowRunProperties': {
'string': 'string'
},
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'Status': 'RUNNING'|'COMPLETED'|'STOPPING'|'STOPPED'|'ERROR',
'ErrorMessage': 'string',
'Statistics': {
'TotalActions': 123,
'TimeoutActions': 123,
'FailedActions': 123,
'StoppedActions': 123,
'SucceededActions': 123,
'RunningActions': 123,
'ErroredActions': 123,
'WaitingActions': 123
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'StartingEventBatchCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'MaxConcurrentRuns': 123,
'BlueprintDetails': {
'BlueprintName': 'string',
'RunId': 'string'
}
},
],
'MissingWorkflows': [
'string',
]
}
Response Structure
(dict) --
Workflows (list) --
A list of workflow resource metadata.
(dict) --
A workflow is a collection of multiple dependent Glue jobs and crawlers that are run to complete a complex ETL task. A workflow manages the execution and monitoring of all its jobs and crawlers.
Name (string) --
The name of the workflow.
Description (string) --
A description of the workflow.
DefaultRunProperties (dict) --
A collection of properties to be used as part of each execution of the workflow. The run properties are made available to each job in the workflow. A job can modify the properties for the next jobs in the flow.
(string) --
(string) --
CreatedOn (datetime) --
The date and time when the workflow was created.
LastModifiedOn (datetime) --
The date and time when the workflow was last modified.
LastRun (dict) --
The information about the last execution of the workflow.
Name (string) --
Name of the workflow that was run.
WorkflowRunId (string) --
The ID of this workflow run.
PreviousRunId (string) --
The ID of the previous workflow run.
WorkflowRunProperties (dict) --
The workflow run properties which were set during the run.
(string) --
(string) --
StartedOn (datetime) --
The date and time when the workflow run was started.
CompletedOn (datetime) --
The date and time when the workflow run completed.
Status (string) --
The status of the workflow run.
ErrorMessage (string) --
This error message describes any error that may have occurred in starting the workflow run. Currently the only error message is "Concurrent runs exceeded for workflow: foo."
Statistics (dict) --
The statistics of the run.
TotalActions (integer) --
Total number of Actions in the workflow run.
TimeoutActions (integer) --
Total number of Actions that timed out.
FailedActions (integer) --
Total number of Actions that have failed.
StoppedActions (integer) --
Total number of Actions that have stopped.
SucceededActions (integer) --
Total number of Actions that have succeeded.
RunningActions (integer) --
Total number Actions in running state.
ErroredActions (integer) --
Indicates the count of job runs in the ERROR state in the workflow run.
WaitingActions (integer) --
Indicates the count of job runs in WAITING state in the workflow run.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
StartingEventBatchCondition (dict) --
The batch condition that started the workflow run.
BatchSize (integer) --
Number of events in the batch.
BatchWindow (integer) --
Duration of the batch window in seconds.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
MaxConcurrentRuns (integer) --
You can use this parameter to prevent unwanted multiple updates to data, to control costs, or in some cases, to prevent exceeding the maximum number of concurrent runs of any of the component jobs. If you leave this parameter blank, there is no limit to the number of concurrent workflow runs.
BlueprintDetails (dict) --
This structure indicates the details of the blueprint that this particular workflow is created from.
BlueprintName (string) --
The name of the blueprint.
RunId (string) --
The run ID for this blueprint.
MissingWorkflows (list) --
A list of names of workflows not found.
(string) --
{'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}
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',
],
'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'
}
},
'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.
{'Job': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
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',
],
'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'
}
},
'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'
}
}
**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>`_
{'JobRun': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
Retrieves the metadata for a given job run.
See also: AWS API Documentation
Request Syntax
client.get_job_run(
JobName='string',
RunId='string',
PredecessorsIncluded=True|False
)
string
[REQUIRED]
Name of the job definition being run.
string
[REQUIRED]
The ID of the job run.
boolean
True if a list of predecessor runs should be returned.
dict
Response Syntax
{
'JobRun': {
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
}
}
Response Structure
(dict) --
JobRun (dict) --
The requested job-run metadata.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
{'JobRuns': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
Retrieves metadata for all runs of a given job definition.
See also: AWS API Documentation
Request Syntax
client.get_job_runs(
JobName='string',
NextToken='string',
MaxResults=123
)
string
[REQUIRED]
The name of the job definition for which to retrieve all job runs.
string
A continuation token, if this is a continuation call.
integer
The maximum size of the response.
dict
Response Syntax
{
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
JobRuns (list) --
A list of job-run metadata objects.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
NextToken (string) --
A continuation token, if not all requested job runs have been returned.
{'Jobs': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
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',
],
'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'
}
},
'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'
},
],
'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>`_
{'Workflow': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT '
'| '
'VISUAL '
'| '
'NOTEBOOK'}}}},
'LastRun': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT '
'| '
'VISUAL '
'| '
'NOTEBOOK'}}}}}}}
Retrieves resource metadata for a workflow.
See also: AWS API Documentation
Request Syntax
client.get_workflow(
Name='string',
IncludeGraph=True|False
)
string
[REQUIRED]
The name of the workflow to retrieve.
boolean
Specifies whether to include a graph when returning the workflow resource metadata.
dict
Response Syntax
{
'Workflow': {
'Name': 'string',
'Description': 'string',
'DefaultRunProperties': {
'string': 'string'
},
'CreatedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'LastRun': {
'Name': 'string',
'WorkflowRunId': 'string',
'PreviousRunId': 'string',
'WorkflowRunProperties': {
'string': 'string'
},
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'Status': 'RUNNING'|'COMPLETED'|'STOPPING'|'STOPPED'|'ERROR',
'ErrorMessage': 'string',
'Statistics': {
'TotalActions': 123,
'TimeoutActions': 123,
'FailedActions': 123,
'StoppedActions': 123,
'SucceededActions': 123,
'RunningActions': 123,
'ErroredActions': 123,
'WaitingActions': 123
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'StartingEventBatchCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'MaxConcurrentRuns': 123,
'BlueprintDetails': {
'BlueprintName': 'string',
'RunId': 'string'
}
}
}
Response Structure
(dict) --
Workflow (dict) --
The resource metadata for the workflow.
Name (string) --
The name of the workflow.
Description (string) --
A description of the workflow.
DefaultRunProperties (dict) --
A collection of properties to be used as part of each execution of the workflow. The run properties are made available to each job in the workflow. A job can modify the properties for the next jobs in the flow.
(string) --
(string) --
CreatedOn (datetime) --
The date and time when the workflow was created.
LastModifiedOn (datetime) --
The date and time when the workflow was last modified.
LastRun (dict) --
The information about the last execution of the workflow.
Name (string) --
Name of the workflow that was run.
WorkflowRunId (string) --
The ID of this workflow run.
PreviousRunId (string) --
The ID of the previous workflow run.
WorkflowRunProperties (dict) --
The workflow run properties which were set during the run.
(string) --
(string) --
StartedOn (datetime) --
The date and time when the workflow run was started.
CompletedOn (datetime) --
The date and time when the workflow run completed.
Status (string) --
The status of the workflow run.
ErrorMessage (string) --
This error message describes any error that may have occurred in starting the workflow run. Currently the only error message is "Concurrent runs exceeded for workflow: foo."
Statistics (dict) --
The statistics of the run.
TotalActions (integer) --
Total number of Actions in the workflow run.
TimeoutActions (integer) --
Total number of Actions that timed out.
FailedActions (integer) --
Total number of Actions that have failed.
StoppedActions (integer) --
Total number of Actions that have stopped.
SucceededActions (integer) --
Total number of Actions that have succeeded.
RunningActions (integer) --
Total number Actions in running state.
ErroredActions (integer) --
Indicates the count of job runs in the ERROR state in the workflow run.
WaitingActions (integer) --
Indicates the count of job runs in WAITING state in the workflow run.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
StartingEventBatchCondition (dict) --
The batch condition that started the workflow run.
BatchSize (integer) --
Number of events in the batch.
BatchWindow (integer) --
Duration of the batch window in seconds.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
MaxConcurrentRuns (integer) --
You can use this parameter to prevent unwanted multiple updates to data, to control costs, or in some cases, to prevent exceeding the maximum number of concurrent runs of any of the component jobs. If you leave this parameter blank, there is no limit to the number of concurrent workflow runs.
BlueprintDetails (dict) --
This structure indicates the details of the blueprint that this particular workflow is created from.
BlueprintName (string) --
The name of the blueprint.
RunId (string) --
The run ID for this blueprint.
{'Run': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT | '
'VISUAL | '
'NOTEBOOK'}}}}}}
Retrieves the metadata for a given workflow run.
See also: AWS API Documentation
Request Syntax
client.get_workflow_run(
Name='string',
RunId='string',
IncludeGraph=True|False
)
string
[REQUIRED]
Name of the workflow being run.
string
[REQUIRED]
The ID of the workflow run.
boolean
Specifies whether to include the workflow graph in response or not.
dict
Response Syntax
{
'Run': {
'Name': 'string',
'WorkflowRunId': 'string',
'PreviousRunId': 'string',
'WorkflowRunProperties': {
'string': 'string'
},
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'Status': 'RUNNING'|'COMPLETED'|'STOPPING'|'STOPPED'|'ERROR',
'ErrorMessage': 'string',
'Statistics': {
'TotalActions': 123,
'TimeoutActions': 123,
'FailedActions': 123,
'StoppedActions': 123,
'SucceededActions': 123,
'RunningActions': 123,
'ErroredActions': 123,
'WaitingActions': 123
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'StartingEventBatchCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
}
Response Structure
(dict) --
Run (dict) --
The requested workflow run metadata.
Name (string) --
Name of the workflow that was run.
WorkflowRunId (string) --
The ID of this workflow run.
PreviousRunId (string) --
The ID of the previous workflow run.
WorkflowRunProperties (dict) --
The workflow run properties which were set during the run.
(string) --
(string) --
StartedOn (datetime) --
The date and time when the workflow run was started.
CompletedOn (datetime) --
The date and time when the workflow run completed.
Status (string) --
The status of the workflow run.
ErrorMessage (string) --
This error message describes any error that may have occurred in starting the workflow run. Currently the only error message is "Concurrent runs exceeded for workflow: foo."
Statistics (dict) --
The statistics of the run.
TotalActions (integer) --
Total number of Actions in the workflow run.
TimeoutActions (integer) --
Total number of Actions that timed out.
FailedActions (integer) --
Total number of Actions that have failed.
StoppedActions (integer) --
Total number of Actions that have stopped.
SucceededActions (integer) --
Total number of Actions that have succeeded.
RunningActions (integer) --
Total number Actions in running state.
ErroredActions (integer) --
Indicates the count of job runs in the ERROR state in the workflow run.
WaitingActions (integer) --
Indicates the count of job runs in WAITING state in the workflow run.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
StartingEventBatchCondition (dict) --
The batch condition that started the workflow run.
BatchSize (integer) --
Number of events in the batch.
BatchWindow (integer) --
Duration of the batch window in seconds.
{'Runs': {'Graph': {'Nodes': {'JobDetails': {'JobRuns': {'JobMode': 'SCRIPT | '
'VISUAL | '
'NOTEBOOK'}}}}}}
Retrieves metadata for all runs of a given workflow.
See also: AWS API Documentation
Request Syntax
client.get_workflow_runs(
Name='string',
IncludeGraph=True|False,
NextToken='string',
MaxResults=123
)
string
[REQUIRED]
Name of the workflow whose metadata of runs should be returned.
boolean
Specifies whether to include the workflow graph in response or not.
string
The maximum size of the response.
integer
The maximum number of workflow runs to be included in the response.
dict
Response Syntax
{
'Runs': [
{
'Name': 'string',
'WorkflowRunId': 'string',
'PreviousRunId': 'string',
'WorkflowRunProperties': {
'string': 'string'
},
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'Status': 'RUNNING'|'COMPLETED'|'STOPPING'|'STOPPED'|'ERROR',
'ErrorMessage': 'string',
'Statistics': {
'TotalActions': 123,
'TimeoutActions': 123,
'FailedActions': 123,
'StoppedActions': 123,
'SucceededActions': 123,
'RunningActions': 123,
'ErroredActions': 123,
'WaitingActions': 123
},
'Graph': {
'Nodes': [
{
'Type': 'CRAWLER'|'JOB'|'TRIGGER',
'Name': 'string',
'UniqueId': 'string',
'TriggerDetails': {
'Trigger': {
'Name': 'string',
'WorkflowName': 'string',
'Id': 'string',
'Type': 'SCHEDULED'|'CONDITIONAL'|'ON_DEMAND'|'EVENT',
'State': 'CREATING'|'CREATED'|'ACTIVATING'|'ACTIVATED'|'DEACTIVATING'|'DEACTIVATED'|'DELETING'|'UPDATING',
'Description': 'string',
'Schedule': 'string',
'Actions': [
{
'JobName': 'string',
'Arguments': {
'string': 'string'
},
'Timeout': 123,
'SecurityConfiguration': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'CrawlerName': 'string'
},
],
'Predicate': {
'Logical': 'AND'|'ANY',
'Conditions': [
{
'LogicalOperator': 'EQUALS',
'JobName': 'string',
'State': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'CrawlerName': 'string',
'CrawlState': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR'
},
]
},
'EventBatchingCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
}
},
'JobDetails': {
'JobRuns': [
{
'Id': 'string',
'Attempt': 123,
'PreviousRunId': 'string',
'TriggerName': 'string',
'JobName': 'string',
'JobMode': 'SCRIPT'|'VISUAL'|'NOTEBOOK',
'StartedOn': datetime(2015, 1, 1),
'LastModifiedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'JobRunState': 'STARTING'|'RUNNING'|'STOPPING'|'STOPPED'|'SUCCEEDED'|'FAILED'|'TIMEOUT'|'ERROR'|'WAITING'|'EXPIRED',
'Arguments': {
'string': 'string'
},
'ErrorMessage': 'string',
'PredecessorRuns': [
{
'JobName': 'string',
'RunId': 'string'
},
],
'AllocatedCapacity': 123,
'ExecutionTime': 123,
'Timeout': 123,
'MaxCapacity': 123.0,
'WorkerType': 'Standard'|'G.1X'|'G.2X'|'G.025X'|'G.4X'|'G.8X'|'Z.2X',
'NumberOfWorkers': 123,
'SecurityConfiguration': 'string',
'LogGroupName': 'string',
'NotificationProperty': {
'NotifyDelayAfter': 123
},
'GlueVersion': 'string',
'DPUSeconds': 123.0,
'ExecutionClass': 'FLEX'|'STANDARD',
'MaintenanceWindow': 'string'
},
]
},
'CrawlerDetails': {
'Crawls': [
{
'State': 'RUNNING'|'CANCELLING'|'CANCELLED'|'SUCCEEDED'|'FAILED'|'ERROR',
'StartedOn': datetime(2015, 1, 1),
'CompletedOn': datetime(2015, 1, 1),
'ErrorMessage': 'string',
'LogGroup': 'string',
'LogStream': 'string'
},
]
}
},
],
'Edges': [
{
'SourceId': 'string',
'DestinationId': 'string'
},
]
},
'StartingEventBatchCondition': {
'BatchSize': 123,
'BatchWindow': 123
}
},
],
'NextToken': 'string'
}
Response Structure
(dict) --
Runs (list) --
A list of workflow run metadata objects.
(dict) --
A workflow run is an execution of a workflow providing all the runtime information.
Name (string) --
Name of the workflow that was run.
WorkflowRunId (string) --
The ID of this workflow run.
PreviousRunId (string) --
The ID of the previous workflow run.
WorkflowRunProperties (dict) --
The workflow run properties which were set during the run.
(string) --
(string) --
StartedOn (datetime) --
The date and time when the workflow run was started.
CompletedOn (datetime) --
The date and time when the workflow run completed.
Status (string) --
The status of the workflow run.
ErrorMessage (string) --
This error message describes any error that may have occurred in starting the workflow run. Currently the only error message is "Concurrent runs exceeded for workflow: foo."
Statistics (dict) --
The statistics of the run.
TotalActions (integer) --
Total number of Actions in the workflow run.
TimeoutActions (integer) --
Total number of Actions that timed out.
FailedActions (integer) --
Total number of Actions that have failed.
StoppedActions (integer) --
Total number of Actions that have stopped.
SucceededActions (integer) --
Total number of Actions that have succeeded.
RunningActions (integer) --
Total number Actions in running state.
ErroredActions (integer) --
Indicates the count of job runs in the ERROR state in the workflow run.
WaitingActions (integer) --
Indicates the count of job runs in WAITING state in the workflow run.
Graph (dict) --
The graph representing all the Glue components that belong to the workflow as nodes and directed connections between them as edges.
Nodes (list) --
A list of the the Glue components belong to the workflow represented as nodes.
(dict) --
A node represents an Glue component (trigger, crawler, or job) on a workflow graph.
Type (string) --
The type of Glue component represented by the node.
Name (string) --
The name of the Glue component represented by the node.
UniqueId (string) --
The unique Id assigned to the node within the workflow.
TriggerDetails (dict) --
Details of the Trigger when the node represents a Trigger.
Trigger (dict) --
The information of the trigger represented by the trigger node.
Name (string) --
The name of the trigger.
WorkflowName (string) --
The name of the workflow associated with the trigger.
Id (string) --
Reserved for future use.
Type (string) --
The type of trigger that this is.
State (string) --
The current state of the trigger.
Description (string) --
A description of this trigger.
Schedule (string) --
A cron expression used to specify the schedule (see Time-Based Schedules for Jobs and Crawlers. For example, to run something every day at 12:15 UTC, you would specify: cron(15 12 * * ? *).
Actions (list) --
The actions initiated by this trigger.
(dict) --
Defines an action to be initiated by a trigger.
JobName (string) --
The name of a job to be run.
Arguments (dict) --
The job arguments used when this trigger fires. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.
(string) --
(string) --
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. The default is 2,880 minutes (48 hours). This overrides the timeout value set in the parent job.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this action.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
CrawlerName (string) --
The name of the crawler to be used with this action.
Predicate (dict) --
The predicate of this trigger, which defines when it will fire.
Logical (string) --
An optional field if only one condition is listed. If multiple conditions are listed, then this field is required.
Conditions (list) --
A list of the conditions that determine when the trigger will fire.
(dict) --
Defines a condition under which a trigger fires.
LogicalOperator (string) --
A logical operator.
JobName (string) --
The name of the job whose JobRuns this condition applies to, and on which this trigger waits.
State (string) --
The condition state. Currently, the only job states that a trigger can listen for are SUCCEEDED, STOPPED, FAILED, and TIMEOUT. The only crawler states that a trigger can listen for are SUCCEEDED, FAILED, and CANCELLED.
CrawlerName (string) --
The name of the crawler to which this condition applies.
CrawlState (string) --
The state of the crawler to which this condition applies.
EventBatchingCondition (dict) --
Batch condition that must be met (specified number of events received or batch time window expired) before EventBridge event trigger fires.
BatchSize (integer) --
Number of events that must be received from Amazon EventBridge before EventBridge event trigger fires.
BatchWindow (integer) --
Window of time in seconds after which EventBridge event trigger fires. Window starts when first event is received.
JobDetails (dict) --
Details of the Job when the node represents a Job.
JobRuns (list) --
The information for the job runs represented by the job node.
(dict) --
Contains information about a job run.
Id (string) --
The ID of this job run.
Attempt (integer) --
The number of the attempt to run this job.
PreviousRunId (string) --
The ID of the previous run of this job. For example, the JobRunId specified in the StartJobRun action.
TriggerName (string) --
The name of the trigger that started this job run.
JobName (string) --
The name of the job definition being used in this run.
JobMode (string) --
A mode that describes how a job was created. Valid values are:
SCRIPT - The job was created using the Glue Studio script editor.
VISUAL - The job was created using the Glue Studio visual editor.
NOTEBOOK - The job was created using an interactive sessions notebook.
When the JobMode field is missing or null, SCRIPT is assigned as the default value.
StartedOn (datetime) --
The date and time at which this job run was started.
LastModifiedOn (datetime) --
The last time that this job run was modified.
CompletedOn (datetime) --
The date and time that this job run completed.
JobRunState (string) --
The current state of the job run. For more information about the statuses of jobs that have terminated abnormally, see Glue Job Run Statuses.
Arguments (dict) --
The job arguments associated with this run. For this job run, they replace the default arguments set in the job definition itself.
You can specify arguments here that your own job-execution script consumes, as well as arguments that Glue itself consumes.
Job arguments may be logged. Do not pass plaintext secrets as arguments. Retrieve secrets from a Glue Connection, Secrets Manager or other secret management mechanism if you intend to keep them within the Job.
For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.
For information about the arguments you can provide to this field when configuring Spark jobs, see the Special Parameters Used by Glue topic in the developer guide.
For information about the arguments you can provide to this field when configuring Ray jobs, see Using job parameters in Ray jobs in the developer guide.
(string) --
(string) --
ErrorMessage (string) --
An error message associated with this job run.
PredecessorRuns (list) --
A list of predecessors to this job run.
(dict) --
A job run that was used in the predicate of a conditional trigger that triggered this job run.
JobName (string) --
The name of the job definition used by the predecessor job run.
RunId (string) --
The job-run ID of the predecessor job run.
AllocatedCapacity (integer) --
This field is deprecated. Use MaxCapacity instead.
The number of Glue data processing units (DPUs) allocated to this JobRun. From 2 to 100 DPUs can be allocated; the default is 10. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
ExecutionTime (integer) --
The amount of time (in seconds) that the job run consumed resources.
Timeout (integer) --
The JobRun timeout in minutes. This is the maximum time that a job run can consume resources before it is terminated and enters TIMEOUT status. This value overrides the timeout value set in the parent job.
The maximum value for timeout for batch jobs is 7 days or 10080 minutes. The default is 2880 minutes (48 hours) for batch jobs.
Any existing Glue jobs that have a greater timeout value are defaulted to 7 days. For instance you have specified a timeout of 20 days for a batch job, it will be stopped on the 7th day.
Streaming jobs must have timeout values less than 7 days or 10080 minutes. When the value is left blank, the job will be restarted after 7 days based if you have not setup a maintenance window. If you have setup maintenance window, it will be restarted during the maintenance window after 7 days.
MaxCapacity (float) --
For Glue version 1.0 or earlier jobs, using the standard worker type, the number of Glue data processing units (DPUs) that can be allocated when this job runs. A DPU is a relative measure of processing power that consists of 4 vCPUs of compute capacity and 16 GB of memory. For more information, see the Glue pricing page.
For Glue version 2.0+ jobs, you cannot specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.
Do not set MaxCapacity if using WorkerType and NumberOfWorkers.
The value that can be allocated for MaxCapacity depends on whether you are running a Python shell job, an Apache Spark ETL job, or an Apache Spark streaming ETL job:
When you specify a Python shell job ( ``JobCommand.Name``="pythonshell"), you can allocate either 0.0625 or 1 DPU. The default is 0.0625 DPU.
When you specify an Apache Spark ETL job ( ``JobCommand.Name``="glueetl") or Apache Spark streaming ETL job ( ``JobCommand.Name``="gluestreaming"), you can allocate from 2 to 100 DPUs. The default is 10 DPUs. This job type cannot have a fractional DPU allocation.
WorkerType (string) --
The type of predefined worker that is allocated when a job runs. Accepts a value of G.1X, G.2X, G.4X, G.8X or G.025X for Spark jobs. Accepts the value Z.2X for Ray jobs.
For the G.1X worker type, each worker maps to 1 DPU (4 vCPUs, 16 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.2X worker type, each worker maps to 2 DPU (8 vCPUs, 32 GB of memory) with 128GB disk (approximately 77GB free), and provides 1 executor per worker. We recommend this worker type for workloads such as data transforms, joins, and queries, to offers a scalable and cost effective way to run most jobs.
For the G.4X worker type, each worker maps to 4 DPU (16 vCPUs, 64 GB of memory) with 256GB disk (approximately 235GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs in the following Amazon Web Services Regions: US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), and Europe (Stockholm).
For the G.8X worker type, each worker maps to 8 DPU (32 vCPUs, 128 GB of memory) with 512GB disk (approximately 487GB free), and provides 1 executor per worker. We recommend this worker type for jobs whose workloads contain your most demanding transforms, aggregations, joins, and queries. This worker type is available only for Glue version 3.0 or later Spark ETL jobs, in the same Amazon Web Services Regions as supported for the G.4X worker type.
For the G.025X worker type, each worker maps to 0.25 DPU (2 vCPUs, 4 GB of memory) with 84GB disk (approximately 34GB free), and provides 1 executor per worker. We recommend this worker type for low volume streaming jobs. This worker type is only available for Glue version 3.0 streaming jobs.
For the Z.2X worker type, each worker maps to 2 M-DPU (8vCPUs, 64 GB of memory) with 128 GB disk (approximately 120GB free), and provides up to 8 Ray workers based on the autoscaler.
NumberOfWorkers (integer) --
The number of workers of a defined workerType that are allocated when a job runs.
SecurityConfiguration (string) --
The name of the SecurityConfiguration structure to be used with this job run.
LogGroupName (string) --
The name of the log group for secure logging that can be server-side encrypted in Amazon CloudWatch using KMS. This name can be /aws-glue/jobs/, in which case the default encryption is NONE. If you add a role name and SecurityConfiguration name (in other words, /aws-glue/jobs-yourRoleName-yourSecurityConfigurationName/), then that security configuration is used to encrypt the log group.
NotificationProperty (dict) --
Specifies configuration properties of a job run notification.
NotifyDelayAfter (integer) --
After a job run starts, the number of minutes to wait before sending a job run delay notification.
GlueVersion (string) --
In Spark jobs, GlueVersion determines the versions of Apache Spark and Python that Glue available in a job. The Python version indicates the version supported for jobs of type Spark.
Ray jobs should set GlueVersion to 4.0 or greater. However, the versions of Ray, Python and additional libraries available in your Ray job are determined by the Runtime parameter of the Job command.
For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.
Jobs that are created without specifying a Glue version default to Glue 0.9.
DPUSeconds (float) --
This field can be set for either job runs with execution class FLEX or when Auto Scaling is enabled, and represents the total time each executor ran during the lifecycle of a job run in seconds, multiplied by a DPU factor (1 for G.1X, 2 for G.2X, or 0.25 for G.025X workers). This value may be different than the executionEngineRuntime * MaxCapacity as in the case of Auto Scaling jobs, as the number of executors running at a given time may be less than the MaxCapacity. Therefore, it is possible that the value of DPUSeconds is less than executionEngineRuntime * MaxCapacity.
ExecutionClass (string) --
Indicates whether the job is run with a standard or flexible execution class. The standard execution-class is ideal for time-sensitive workloads that require fast job startup and dedicated resources.
The flexible execution class is appropriate for time-insensitive jobs whose start and completion times may vary.
Only jobs with Glue version 3.0 and above and command type glueetl will be allowed to set ExecutionClass to FLEX. The flexible execution class is available for Spark jobs.
MaintenanceWindow (string) --
This field specifies a day of the week and hour for a maintenance window for streaming jobs. Glue periodically performs maintenance activities. During these maintenance windows, Glue will need to restart your streaming jobs.
Glue will restart the job within 3 hours of the specified maintenance window. For instance, if you set up the maintenance window for Monday at 10:00AM GMT, your jobs will be restarted between 10:00AM GMT to 1:00PM GMT.
CrawlerDetails (dict) --
Details of the crawler when the node represents a crawler.
Crawls (list) --
A list of crawls represented by the crawl node.
(dict) --
The details of a crawl in the workflow.
State (string) --
The state of the crawler.
StartedOn (datetime) --
The date and time on which the crawl started.
CompletedOn (datetime) --
The date and time on which the crawl completed.
ErrorMessage (string) --
The error message associated with the crawl.
LogGroup (string) --
The log group associated with the crawl.
LogStream (string) --
The log stream associated with the crawl.
Edges (list) --
A list of all the directed connections between the nodes belonging to the workflow.
(dict) --
An edge represents a directed connection between two Glue components that are part of the workflow the edge belongs to.
SourceId (string) --
The unique of the node within the workflow where the edge starts.
DestinationId (string) --
The unique of the node within the workflow where the edge ends.
StartingEventBatchCondition (dict) --
The batch condition that started the workflow run.
BatchSize (integer) --
Number of events in the batch.
BatchWindow (integer) --
Duration of the batch window in seconds.
NextToken (string) --
A continuation token, if not all requested workflow runs have been returned.
{'JobUpdate': {'JobMode': 'SCRIPT | VISUAL | NOTEBOOK'}}
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',
],
'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'
}
},
'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.