File: types.go

package info (click to toggle)
golang-github-aws-aws-sdk-go-v2 1.24.1-2~bpo12%2B1
links: PTS, VCS
area: main
in suites: bookworm-backports
size: 554,032 kB
sloc: java: 15,941; makefile: 419; sh: 175
file content (8542 lines) | stat: -rw-r--r-- 261,729 bytes
// Code generated by smithy-go-codegen DO NOT EDIT.

package types

import (
	smithydocument "github.com/aws/smithy-go/document"
	"time"
)

// Defines an action to be initiated by a trigger.
type Action struct {

	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html)
	// topic in the developer guide.
	Arguments map[string]string

	// The name of the crawler to be used with this action.
	CrawlerName *string

	// The name of a job to be run.
	JobName *string

	// Specifies configuration properties of a job run notification.
	NotificationProperty *NotificationProperty

	// The name of the SecurityConfiguration structure to be used with this action.
	SecurityConfiguration *string

	// 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.
	Timeout *int32

	noSmithyDocumentSerde
}

// Specifies a transform that groups rows by chosen fields and computes the
// aggregated value by specified function.
type Aggregate struct {

	// Specifies the aggregate functions to be performed on specified fields.
	//
	// This member is required.
	Aggs []AggregateOperation

	// Specifies the fields to group by.
	//
	// This member is required.
	Groups [][]string

	// Specifies the fields and rows to use as inputs for the aggregate transform.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Specifies the set of parameters needed to perform aggregation in the aggregate
// transform.
type AggregateOperation struct {

	// Specifies the aggregation function to apply. Possible aggregation functions
	// include: avg countDistinct, count, first, last, kurtosis, max, min, skewness,
	// stddev_samp, stddev_pop, sum, sumDistinct, var_samp, var_pop
	//
	// This member is required.
	AggFunc AggFunction

	// Specifies the column on the data set on which the aggregation function will be
	// applied.
	//
	// This member is required.
	Column []string

	noSmithyDocumentSerde
}

// Specifies an optional value when connecting to the Redshift cluster.
type AmazonRedshiftAdvancedOption struct {

	// The key for the additional connection option.
	Key *string

	// The value for the additional connection option.
	Value *string

	noSmithyDocumentSerde
}

// Specifies an Amazon Redshift node.
type AmazonRedshiftNodeData struct {

	// The access type for the Redshift connection. Can be a direct connection or
	// catalog connections.
	AccessType *string

	// Specifies how writing to a Redshift cluser will occur.
	Action *string

	// Optional values when connecting to the Redshift cluster.
	AdvancedOptions []AmazonRedshiftAdvancedOption

	// The name of the Glue Data Catalog database when working with a data catalog.
	CatalogDatabase *Option

	// The Redshift schema name when working with a data catalog.
	CatalogRedshiftSchema *string

	// The database table to read from.
	CatalogRedshiftTable *string

	// The Glue Data Catalog table name when working with a data catalog.
	CatalogTable *Option

	// The Glue connection to the Redshift cluster.
	Connection *Option

	// Specifies the name of the connection that is associated with the catalog table
	// used.
	CrawlerConnection *string

	// Optional. The role name use when connection to S3. The IAM role ill default to
	// the role on the job when left blank.
	IamRole *Option

	// The action used when to detemine how a MERGE in a Redshift sink will be handled.
	MergeAction *string

	// The SQL used in a custom merge to deal with matching records.
	MergeClause *string

	// The action used when to detemine how a MERGE in a Redshift sink will be handled
	// when an existing record matches a new record.
	MergeWhenMatched *string

	// The action used when to detemine how a MERGE in a Redshift sink will be handled
	// when an existing record doesn't match a new record.
	MergeWhenNotMatched *string

	// The SQL used before a MERGE or APPEND with upsert is run.
	PostAction *string

	// The SQL used before a MERGE or APPEND with upsert is run.
	PreAction *string

	// The SQL used to fetch the data from a Redshift sources when the SourceType is
	// 'query'.
	SampleQuery *string

	// The Redshift schema name when working with a direct connection.
	Schema *Option

	// The list of column names used to determine a matching record when doing a MERGE
	// or APPEND with upsert.
	SelectedColumns []Option

	// The source type to specify whether a specific table is the source or a custom
	// query.
	SourceType *string

	// The name of the temporary staging table that is used when doing a MERGE or
	// APPEND with upsert.
	StagingTable *string

	// The Redshift table name when working with a direct connection.
	Table *Option

	// Specifies the prefix to a table.
	TablePrefix *string

	// The array of schema output for a given node.
	TableSchema []Option

	// The Amazon S3 path where temporary data can be staged when copying out of the
	// database.
	TempDir *string

	// The action used on Redshift sinks when doing an APPEND.
	Upsert bool

	noSmithyDocumentSerde
}

// Specifies an Amazon Redshift source.
type AmazonRedshiftSource struct {

	// Specifies the data of the Amazon Reshift source node.
	Data *AmazonRedshiftNodeData

	// The name of the Amazon Redshift source.
	Name *string

	noSmithyDocumentSerde
}

// Specifies an Amazon Redshift target.
type AmazonRedshiftTarget struct {

	// Specifies the data of the Amazon Redshift target node.
	Data *AmazonRedshiftNodeData

	// The nodes that are inputs to the data target.
	Inputs []string

	// The name of the Amazon Redshift target.
	Name *string

	noSmithyDocumentSerde
}

// Specifies a transform that maps data property keys in the data source to data
// property keys in the data target. You can rename keys, modify the data types for
// keys, and choose which keys to drop from the dataset.
type ApplyMapping struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// Specifies the mapping of data property keys in the data source to data property
	// keys in the data target.
	//
	// This member is required.
	Mapping []Mapping

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Specifies a connector to an Amazon Athena data source.
type AthenaConnectorSource struct {

	// The name of the connection that is associated with the connector.
	//
	// This member is required.
	ConnectionName *string

	// The type of connection, such as marketplace.athena or custom.athena,
	// designating a connection to an Amazon Athena data store.
	//
	// This member is required.
	ConnectionType *string

	// The name of a connector that assists with accessing the data store in Glue
	// Studio.
	//
	// This member is required.
	ConnectorName *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the Cloudwatch log group to read from. For example,
	// /aws-glue/jobs/output .
	//
	// This member is required.
	SchemaName *string

	// The name of the table in the data source.
	ConnectionTable *string

	// Specifies the data schema for the custom Athena source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// A structure containing the Lake Formation audit context.
type AuditContext struct {

	// A string containing the additional audit context information.
	AdditionalAuditContext *string

	// All columns request for audit.
	AllColumnsRequested *bool

	// The requested columns for audit.
	RequestedColumns []string

	noSmithyDocumentSerde
}

// A list of errors that can occur when registering partition indexes for an
// existing table. These errors give the details about why an index registration
// failed and provide a limited number of partitions in the response, so that you
// can fix the partitions at fault and try registering the index again. The most
// common set of errors that can occur are categorized as follows:
//   - EncryptedPartitionError: The partitions are encrypted.
//   - InvalidPartitionTypeDataError: The partition value doesn't match the data
//     type for that partition column.
//   - MissingPartitionValueError: The partitions are encrypted.
//   - UnsupportedPartitionCharacterError: Characters inside the partition value
//     are not supported. For example: U+0000 , U+0001, U+0002.
//   - InternalError: Any error which does not belong to other error codes.
type BackfillError struct {

	// The error code for an error that occurred when registering partition indexes
	// for an existing table.
	Code BackfillErrorCode

	// A list of a limited number of partitions in the response.
	Partitions []PartitionValueList

	noSmithyDocumentSerde
}

// Specifies a target that uses a Glue Data Catalog table.
type BasicCatalogTarget struct {

	// The database that contains the table you want to use as the target. This
	// database must already exist in the Data Catalog.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of your data target.
	//
	// This member is required.
	Name *string

	// The table that defines the schema of your output data. This table must already
	// exist in the Data Catalog.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Represents a table optimizer to retrieve in the BatchGetTableOptimizer
// operation.
type BatchGetTableOptimizerEntry struct {

	// The Catalog ID of the table.
	CatalogId *string

	// The name of the database in the catalog in which the table resides.
	DatabaseName *string

	// The name of the table.
	TableName *string

	// The type of table optimizer.
	Type TableOptimizerType

	noSmithyDocumentSerde
}

// Contains details on one of the errors in the error list returned by the
// BatchGetTableOptimizer operation.
type BatchGetTableOptimizerError struct {

	// The Catalog ID of the table.
	CatalogId *string

	// The name of the database in the catalog in which the table resides.
	DatabaseName *string

	// An ErrorDetail object containing code and message details about the error.
	Error *ErrorDetail

	// The name of the table.
	TableName *string

	// The type of table optimizer.
	Type TableOptimizerType

	noSmithyDocumentSerde
}

// Records an error that occurred when attempting to stop a specified job run.
type BatchStopJobRunError struct {

	// Specifies details about the error that was encountered.
	ErrorDetail *ErrorDetail

	// The name of the job definition that is used in the job run in question.
	JobName *string

	// The JobRunId of the job run in question.
	JobRunId *string

	noSmithyDocumentSerde
}

// Records a successful request to stop a specified JobRun .
type BatchStopJobRunSuccessfulSubmission struct {

	// The name of the job definition used in the job run that was stopped.
	JobName *string

	// The JobRunId of the job run that was stopped.
	JobRunId *string

	noSmithyDocumentSerde
}

// Contains details for one of the table optimizers returned by the
// BatchGetTableOptimizer operation.
type BatchTableOptimizer struct {

	// The Catalog ID of the table.
	CatalogId *string

	// The name of the database in the catalog in which the table resides.
	DatabaseName *string

	// The name of the table.
	TableName *string

	// A TableOptimizer object that contains details on the configuration and last run
	// of a table optimzer.
	TableOptimizer *TableOptimizer

	noSmithyDocumentSerde
}

// Contains information about a batch update partition error.
type BatchUpdatePartitionFailureEntry struct {

	// The details about the batch update partition error.
	ErrorDetail *ErrorDetail

	// A list of values defining the partitions.
	PartitionValueList []string

	noSmithyDocumentSerde
}

// A structure that contains the values and structure used to update a partition.
type BatchUpdatePartitionRequestEntry struct {

	// The structure used to update a partition.
	//
	// This member is required.
	PartitionInput *PartitionInput

	// A list of values defining the partitions.
	//
	// This member is required.
	PartitionValueList []string

	noSmithyDocumentSerde
}

// Defines column statistics supported for bit sequence data values.
type BinaryColumnStatisticsData struct {

	// The average bit sequence length in the column.
	//
	// This member is required.
	AverageLength float64

	// The size of the longest bit sequence in the column.
	//
	// This member is required.
	MaximumLength int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	noSmithyDocumentSerde
}

// The details of a blueprint.
type Blueprint struct {

	// Specifies the path in Amazon S3 where the blueprint is published.
	BlueprintLocation *string

	// Specifies a path in Amazon S3 where the blueprint is copied when you call
	// CreateBlueprint/UpdateBlueprint to register the blueprint in Glue.
	BlueprintServiceLocation *string

	// The date and time the blueprint was registered.
	CreatedOn *time.Time

	// The description of the blueprint.
	Description *string

	// An error message.
	ErrorMessage *string

	// When there are multiple versions of a blueprint and the latest version has some
	// errors, this attribute indicates the last successful blueprint definition that
	// is available with the service.
	LastActiveDefinition *LastActiveDefinition

	// The date and time the blueprint was last modified.
	LastModifiedOn *time.Time

	// The name of the blueprint.
	Name *string

	// A JSON string that indicates the list of parameter specifications for the
	// blueprint.
	ParameterSpec *string

	// The status of the blueprint registration.
	//   - Creating — The blueprint registration is in progress.
	//   - Active — The blueprint has been successfully registered.
	//   - Updating — An update to the blueprint registration is in progress.
	//   - Failed — The blueprint registration failed.
	Status BlueprintStatus

	noSmithyDocumentSerde
}

// The details of a blueprint.
type BlueprintDetails struct {

	// The name of the blueprint.
	BlueprintName *string

	// The run ID for this blueprint.
	RunId *string

	noSmithyDocumentSerde
}

// The details of a blueprint run.
type BlueprintRun struct {

	// The name of the blueprint.
	BlueprintName *string

	// The date and time that the blueprint run completed.
	CompletedOn *time.Time

	// Indicates any errors that are seen while running the blueprint.
	ErrorMessage *string

	// The blueprint parameters as a string. You will have to provide a value for each
	// key that is required from the parameter spec that is defined in the
	// Blueprint$ParameterSpec .
	Parameters *string

	// The role ARN. This role will be assumed by the Glue service and will be used to
	// create the workflow and other entities of a workflow.
	RoleArn *string

	// If there are any errors while creating the entities of a workflow, we try to
	// roll back the created entities until that point and delete them. This attribute
	// indicates the errors seen while trying to delete the entities that are created.
	RollbackErrorMessage *string

	// The run ID for this blueprint run.
	RunId *string

	// The date and time that the blueprint run started.
	StartedOn *time.Time

	// The state of the blueprint run. Possible values are:
	//   - Running — The blueprint run is in progress.
	//   - Succeeded — The blueprint run completed successfully.
	//   - Failed — The blueprint run failed and rollback is complete.
	//   - Rolling Back — The blueprint run failed and rollback is in progress.
	State BlueprintRunState

	// The name of a workflow that is created as a result of a successful blueprint
	// run. If a blueprint run has an error, there will not be a workflow created.
	WorkflowName *string

	noSmithyDocumentSerde
}

// Defines column statistics supported for Boolean data columns.
type BooleanColumnStatisticsData struct {

	// The number of false values in the column.
	//
	// This member is required.
	NumberOfFalses int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	// The number of true values in the column.
	//
	// This member is required.
	NumberOfTrues int64

	noSmithyDocumentSerde
}

// Specifies a Delta Lake data source that is registered in the Glue Data Catalog.
type CatalogDeltaSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the Delta Lake data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalDeltaOptions map[string]string

	// Specifies the data schema for the Delta Lake source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a table definition in the Glue Data Catalog.
type CatalogEntry struct {

	// The database in which the table metadata resides.
	//
	// This member is required.
	DatabaseName *string

	// The name of the table in question.
	//
	// This member is required.
	TableName *string

	noSmithyDocumentSerde
}

// Specifies a Hudi data source that is registered in the Glue Data Catalog.
type CatalogHudiSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the Hudi data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalHudiOptions map[string]string

	// Specifies the data schema for the Hudi source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// A structure containing migration status information.
type CatalogImportStatus struct {

	// True if the migration has completed, or False otherwise.
	ImportCompleted bool

	// The time that the migration was started.
	ImportTime *time.Time

	// The name of the person who initiated the migration.
	ImportedBy *string

	noSmithyDocumentSerde
}

// Specifies an Apache Kafka data store in the Data Catalog.
type CatalogKafkaSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Specifies options related to data preview for viewing a sample of your data.
	DataPreviewOptions *StreamingDataPreviewOptions

	// Whether to automatically determine the schema from the incoming data.
	DetectSchema *bool

	// Specifies the streaming options.
	StreamingOptions *KafkaStreamingSourceOptions

	// The amount of time to spend processing each micro batch.
	WindowSize *int32

	noSmithyDocumentSerde
}

// Specifies a Kinesis data source in the Glue Data Catalog.
type CatalogKinesisSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Additional options for data preview.
	DataPreviewOptions *StreamingDataPreviewOptions

	// Whether to automatically determine the schema from the incoming data.
	DetectSchema *bool

	// Additional options for the Kinesis streaming data source.
	StreamingOptions *KinesisStreamingSourceOptions

	// The amount of time to spend processing each micro batch.
	WindowSize *int32

	noSmithyDocumentSerde
}

// A policy that specifies update behavior for the crawler.
type CatalogSchemaChangePolicy struct {

	// Whether to use the specified update behavior when the crawler finds a changed
	// schema.
	EnableUpdateCatalog *bool

	// The update behavior when the crawler finds a changed schema.
	UpdateBehavior UpdateCatalogBehavior

	noSmithyDocumentSerde
}

// Specifies a data store in the Glue Data Catalog.
type CatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies an Glue Data Catalog target.
type CatalogTarget struct {

	// The name of the database to be synchronized.
	//
	// This member is required.
	DatabaseName *string

	// A list of the tables to be synchronized.
	//
	// This member is required.
	Tables []string

	// The name of the connection for an Amazon S3-backed Data Catalog table to be a
	// target of the crawl when using a Catalog connection type paired with a NETWORK
	// Connection type.
	ConnectionName *string

	// A valid Amazon dead-letter SQS ARN. For example,
	// arn:aws:sqs:region:account:deadLetterQueue .
	DlqEventQueueArn *string

	// A valid Amazon SQS ARN. For example, arn:aws:sqs:region:account:sqs .
	EventQueueArn *string

	noSmithyDocumentSerde
}

// Classifiers are triggered during a crawl task. A classifier checks whether a
// given file is in a format it can handle. If it is, the classifier creates a
// schema in the form of a StructType object that matches that data format. You
// can use the standard classifiers that Glue provides, or you can write your own
// classifiers to best categorize your data sources and specify the appropriate
// schemas to use for them. A classifier can be a grok classifier, an XML
// classifier, a JSON classifier, or a custom CSV classifier, as specified in one
// of the fields in the Classifier object.
type Classifier struct {

	// A classifier for comma-separated values (CSV).
	CsvClassifier *CsvClassifier

	// A classifier that uses grok .
	GrokClassifier *GrokClassifier

	// A classifier for JSON content.
	JsonClassifier *JsonClassifier

	// A classifier for XML content.
	XMLClassifier *XMLClassifier

	noSmithyDocumentSerde
}

// Specifies how Amazon CloudWatch data should be encrypted.
type CloudWatchEncryption struct {

	// The encryption mode to use for CloudWatch data.
	CloudWatchEncryptionMode CloudWatchEncryptionMode

	// The Amazon Resource Name (ARN) of the KMS key to be used to encrypt the data.
	KmsKeyArn *string

	noSmithyDocumentSerde
}

// CodeGenConfigurationNode enumerates all valid Node types. One and only one of
// its member variables can be populated.
type CodeGenConfigurationNode struct {

	// Specifies a transform that groups rows by chosen fields and computes the
	// aggregated value by specified function.
	Aggregate *Aggregate

	// Specifies a target that writes to a data source in Amazon Redshift.
	AmazonRedshiftSource *AmazonRedshiftSource

	// Specifies a target that writes to a data target in Amazon Redshift.
	AmazonRedshiftTarget *AmazonRedshiftTarget

	// Specifies a transform that maps data property keys in the data source to data
	// property keys in the data target. You can rename keys, modify the data types for
	// keys, and choose which keys to drop from the dataset.
	ApplyMapping *ApplyMapping

	// Specifies a connector to an Amazon Athena data source.
	AthenaConnectorSource *AthenaConnectorSource

	// Specifies a Delta Lake data source that is registered in the Glue Data Catalog.
	CatalogDeltaSource *CatalogDeltaSource

	// Specifies a Hudi data source that is registered in the Glue Data Catalog.
	CatalogHudiSource *CatalogHudiSource

	// Specifies an Apache Kafka data store in the Data Catalog.
	CatalogKafkaSource *CatalogKafkaSource

	// Specifies a Kinesis data source in the Glue Data Catalog.
	CatalogKinesisSource *CatalogKinesisSource

	// Specifies a data store in the Glue Data Catalog.
	CatalogSource *CatalogSource

	// Specifies a target that uses a Glue Data Catalog table.
	CatalogTarget *BasicCatalogTarget

	// Specifies a source generated with standard connection options.
	ConnectorDataSource *ConnectorDataSource

	// Specifies a target generated with standard connection options.
	ConnectorDataTarget *ConnectorDataTarget

	// Specifies a transform that uses custom code you provide to perform the data
	// transformation. The output is a collection of DynamicFrames.
	CustomCode *CustomCode

	// Specifies the direct JDBC source connection.
	DirectJDBCSource *DirectJDBCSource

	// Specifies an Apache Kafka data store.
	DirectKafkaSource *DirectKafkaSource

	// Specifies a direct Amazon Kinesis data source.
	DirectKinesisSource *DirectKinesisSource

	// Specifies a transform that removes rows of repeating data from a data set.
	DropDuplicates *DropDuplicates

	// Specifies a transform that chooses the data property keys that you want to drop.
	DropFields *DropFields

	// Specifies a transform that removes columns from the dataset if all values in
	// the column are 'null'. By default, Glue Studio will recognize null objects, but
	// some values such as empty strings, strings that are "null", -1 integers or other
	// placeholders such as zeros, are not automatically recognized as nulls.
	DropNullFields *DropNullFields

	// Specifies a custom visual transform created by a user.
	DynamicTransform *DynamicTransform

	// Specifies a DynamoDBC Catalog data store in the Glue Data Catalog.
	DynamoDBCatalogSource *DynamoDBCatalogSource

	// Specifies your data quality evaluation criteria.
	EvaluateDataQuality *EvaluateDataQuality

	// Specifies your data quality evaluation criteria. Allows multiple input data and
	// returns a collection of Dynamic Frames.
	EvaluateDataQualityMultiFrame *EvaluateDataQualityMultiFrame

	// Specifies a transform that locates records in the dataset that have missing
	// values and adds a new field with a value determined by imputation. The input
	// data set is used to train the machine learning model that determines what the
	// missing value should be.
	FillMissingValues *FillMissingValues

	// Specifies a transform that splits a dataset into two, based on a filter
	// condition.
	Filter *Filter

	// Specifies a data source in a goverened Data Catalog.
	GovernedCatalogSource *GovernedCatalogSource

	// Specifies a data target that writes to a goverened catalog.
	GovernedCatalogTarget *GovernedCatalogTarget

	// Specifies a connector to a JDBC data source.
	JDBCConnectorSource *JDBCConnectorSource

	// Specifies a data target that writes to Amazon S3 in Apache Parquet columnar
	// storage.
	JDBCConnectorTarget *JDBCConnectorTarget

	// Specifies a transform that joins two datasets into one dataset using a
	// comparison phrase on the specified data property keys. You can use inner, outer,
	// left, right, left semi, and left anti joins.
	Join *Join

	// Specifies a transform that merges a DynamicFrame with a staging DynamicFrame
	// based on the specified primary keys to identify records. Duplicate records
	// (records with the same primary keys) are not de-duplicated.
	Merge *Merge

	// Specifies a Microsoft SQL server data source in the Glue Data Catalog.
	MicrosoftSQLServerCatalogSource *MicrosoftSQLServerCatalogSource

	// Specifies a target that uses Microsoft SQL.
	MicrosoftSQLServerCatalogTarget *MicrosoftSQLServerCatalogTarget

	// Specifies a MySQL data source in the Glue Data Catalog.
	MySQLCatalogSource *MySQLCatalogSource

	// Specifies a target that uses MySQL.
	MySQLCatalogTarget *MySQLCatalogTarget

	// Specifies an Oracle data source in the Glue Data Catalog.
	OracleSQLCatalogSource *OracleSQLCatalogSource

	// Specifies a target that uses Oracle SQL.
	OracleSQLCatalogTarget *OracleSQLCatalogTarget

	// Specifies a transform that identifies, removes or masks PII data.
	PIIDetection *PIIDetection

	// Specifies a PostgresSQL data source in the Glue Data Catalog.
	PostgreSQLCatalogSource *PostgreSQLCatalogSource

	// Specifies a target that uses Postgres SQL.
	PostgreSQLCatalogTarget *PostgreSQLCatalogTarget

	// Specifies a Glue DataBrew recipe node.
	Recipe *Recipe

	// Specifies an Amazon Redshift data store.
	RedshiftSource *RedshiftSource

	// Specifies a target that uses Amazon Redshift.
	RedshiftTarget *RedshiftTarget

	// Specifies a relational catalog data store in the Glue Data Catalog.
	RelationalCatalogSource *RelationalCatalogSource

	// Specifies a transform that renames a single data property key.
	RenameField *RenameField

	// Specifies a Delta Lake data source that is registered in the Glue Data Catalog.
	// The data source must be stored in Amazon S3.
	S3CatalogDeltaSource *S3CatalogDeltaSource

	// Specifies a Hudi data source that is registered in the Glue Data Catalog. The
	// data source must be stored in Amazon S3.
	S3CatalogHudiSource *S3CatalogHudiSource

	// Specifies an Amazon S3 data store in the Glue Data Catalog.
	S3CatalogSource *S3CatalogSource

	// Specifies a data target that writes to Amazon S3 using the Glue Data Catalog.
	S3CatalogTarget *S3CatalogTarget

	// Specifies a command-separated value (CSV) data store stored in Amazon S3.
	S3CsvSource *S3CsvSource

	// Specifies a target that writes to a Delta Lake data source in the Glue Data
	// Catalog.
	S3DeltaCatalogTarget *S3DeltaCatalogTarget

	// Specifies a target that writes to a Delta Lake data source in Amazon S3.
	S3DeltaDirectTarget *S3DeltaDirectTarget

	// Specifies a Delta Lake data source stored in Amazon S3.
	S3DeltaSource *S3DeltaSource

	// Specifies a data target that writes to Amazon S3.
	S3DirectTarget *S3DirectTarget

	// Specifies a data target that writes to Amazon S3 in Apache Parquet columnar
	// storage.
	S3GlueParquetTarget *S3GlueParquetTarget

	// Specifies a target that writes to a Hudi data source in the Glue Data Catalog.
	S3HudiCatalogTarget *S3HudiCatalogTarget

	// Specifies a target that writes to a Hudi data source in Amazon S3.
	S3HudiDirectTarget *S3HudiDirectTarget

	// Specifies a Hudi data source stored in Amazon S3.
	S3HudiSource *S3HudiSource

	// Specifies a JSON data store stored in Amazon S3.
	S3JsonSource *S3JsonSource

	// Specifies an Apache Parquet data store stored in Amazon S3.
	S3ParquetSource *S3ParquetSource

	// Specifies a transform that chooses the data property keys that you want to keep.
	SelectFields *SelectFields

	// Specifies a transform that chooses one DynamicFrame from a collection of
	// DynamicFrames . The output is the selected DynamicFrame
	SelectFromCollection *SelectFromCollection

	// Specifies a Snowflake data source.
	SnowflakeSource *SnowflakeSource

	// Specifies a target that writes to a Snowflake data source.
	SnowflakeTarget *SnowflakeTarget

	// Specifies a connector to an Apache Spark data source.
	SparkConnectorSource *SparkConnectorSource

	// Specifies a target that uses an Apache Spark connector.
	SparkConnectorTarget *SparkConnectorTarget

	// Specifies a transform where you enter a SQL query using Spark SQL syntax to
	// transform the data. The output is a single DynamicFrame .
	SparkSQL *SparkSQL

	// Specifies a transform that writes samples of the data to an Amazon S3 bucket.
	Spigot *Spigot

	// Specifies a transform that splits data property keys into two DynamicFrames .
	// The output is a collection of DynamicFrames : one with selected data property
	// keys, and one with the remaining data property keys.
	SplitFields *SplitFields

	// Specifies a transform that combines the rows from two or more datasets into a
	// single result.
	Union *Union

	noSmithyDocumentSerde
}

// Represents a directional edge in a directed acyclic graph (DAG).
type CodeGenEdge struct {

	// The ID of the node at which the edge starts.
	//
	// This member is required.
	Source *string

	// The ID of the node at which the edge ends.
	//
	// This member is required.
	Target *string

	// The target of the edge.
	TargetParameter *string

	noSmithyDocumentSerde
}

// Represents a node in a directed acyclic graph (DAG)
type CodeGenNode struct {

	// Properties of the node, in the form of name-value pairs.
	//
	// This member is required.
	Args []CodeGenNodeArg

	// A node identifier that is unique within the node's graph.
	//
	// This member is required.
	Id *string

	// The type of node that this is.
	//
	// This member is required.
	NodeType *string

	// The line number of the node.
	LineNumber int32

	noSmithyDocumentSerde
}

// An argument or property of a node.
type CodeGenNodeArg struct {

	// The name of the argument or property.
	//
	// This member is required.
	Name *string

	// The value of the argument or property.
	//
	// This member is required.
	Value *string

	// True if the value is used as a parameter.
	Param bool

	noSmithyDocumentSerde
}

// A column in a Table .
type Column struct {

	// The name of the Column .
	//
	// This member is required.
	Name *string

	// A free-form text comment.
	Comment *string

	// These key-value pairs define properties associated with the column.
	Parameters map[string]string

	// The data type of the Column .
	Type *string

	noSmithyDocumentSerde
}

// Encapsulates a column name that failed and the reason for failure.
type ColumnError struct {

	// The name of the column that failed.
	ColumnName *string

	// An error message with the reason for the failure of an operation.
	Error *ErrorDetail

	noSmithyDocumentSerde
}

// A structure containing the column name and column importance score for a
// column. Column importance helps you understand how columns contribute to your
// model, by identifying which columns in your records are more important than
// others.
type ColumnImportance struct {

	// The name of a column.
	ColumnName *string

	// The column importance score for the column, as a decimal.
	Importance *float64

	noSmithyDocumentSerde
}

// A filter that uses both column-level and row-level filtering.
type ColumnRowFilter struct {

	// A string containing the name of the column.
	ColumnName *string

	// A string containing the row-level filter expression.
	RowFilterExpression *string

	noSmithyDocumentSerde
}

// Represents the generated column-level statistics for a table or partition.
type ColumnStatistics struct {

	// The timestamp of when column statistics were generated.
	//
	// This member is required.
	AnalyzedTime *time.Time

	// Name of column which statistics belong to.
	//
	// This member is required.
	ColumnName *string

	// The data type of the column.
	//
	// This member is required.
	ColumnType *string

	// A ColumnStatisticData object that contains the statistics data values.
	//
	// This member is required.
	StatisticsData *ColumnStatisticsData

	noSmithyDocumentSerde
}

// Contains the individual types of column statistics data. Only one data object
// should be set and indicated by the Type attribute.
type ColumnStatisticsData struct {

	// The type of column statistics data.
	//
	// This member is required.
	Type ColumnStatisticsType

	// Binary column statistics data.
	BinaryColumnStatisticsData *BinaryColumnStatisticsData

	// Boolean column statistics data.
	BooleanColumnStatisticsData *BooleanColumnStatisticsData

	// Date column statistics data.
	DateColumnStatisticsData *DateColumnStatisticsData

	// Decimal column statistics data. UnscaledValues within are Base64-encoded binary
	// objects storing big-endian, two's complement representations of the decimal's
	// unscaled value.
	DecimalColumnStatisticsData *DecimalColumnStatisticsData

	// Double column statistics data.
	DoubleColumnStatisticsData *DoubleColumnStatisticsData

	// Long column statistics data.
	LongColumnStatisticsData *LongColumnStatisticsData

	// String column statistics data.
	StringColumnStatisticsData *StringColumnStatisticsData

	noSmithyDocumentSerde
}

// Encapsulates a ColumnStatistics object that failed and the reason for failure.
type ColumnStatisticsError struct {

	// The ColumnStatistics of the column.
	ColumnStatistics *ColumnStatistics

	// An error message with the reason for the failure of an operation.
	Error *ErrorDetail

	noSmithyDocumentSerde
}

// The object that shows the details of the column stats run.
type ColumnStatisticsTaskRun struct {

	// The ID of the Data Catalog where the table resides. If none is supplied, the
	// Amazon Web Services account ID is used by default.
	CatalogID *string

	// A list of the column names. If none is supplied, all column names for the table
	// will be used by default.
	ColumnNameList []string

	// The identifier for the particular column statistics task run.
	ColumnStatisticsTaskRunId *string

	// The time that this task was created.
	CreationTime *time.Time

	// The Amazon Web Services account ID.
	CustomerId *string

	// The calculated DPU usage in seconds for all autoscaled workers.
	DPUSeconds float64

	// The database where the table resides.
	DatabaseName *string

	// The end time of the task.
	EndTime *time.Time

	// The error message for the job.
	ErrorMessage *string

	// The last point in time when this task was modified.
	LastUpdated *time.Time

	// The number of workers used to generate column statistics. The job is
	// preconfigured to autoscale up to 25 instances.
	NumberOfWorkers int32

	// The IAM role that the service assumes to generate statistics.
	Role *string

	// The percentage of rows used to generate statistics. If none is supplied, the
	// entire table will be used to generate stats.
	SampleSize float64

	// Name of the security configuration that is used to encrypt CloudWatch logs for
	// the column stats task run.
	SecurityConfiguration *string

	// The start time of the task.
	StartTime *time.Time

	// The status of the task run.
	Status ColumnStatisticsState

	// The name of the table for which column statistics is generated.
	TableName *string

	// The type of workers being used for generating stats. The default is g.1x .
	WorkerType *string

	noSmithyDocumentSerde
}

// Defines a condition under which a trigger fires.
type Condition struct {

	// The state of the crawler to which this condition applies.
	CrawlState CrawlState

	// The name of the crawler to which this condition applies.
	CrawlerName *string

	// The name of the job whose JobRuns this condition applies to, and on which this
	// trigger waits.
	JobName *string

	// A logical operator.
	LogicalOperator LogicalOperator

	// 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 .
	State JobRunState

	noSmithyDocumentSerde
}

// The confusion matrix shows you what your transform is predicting accurately and
// what types of errors it is making. For more information, see Confusion matrix (https://en.wikipedia.org/wiki/Confusion_matrix)
// in Wikipedia.
type ConfusionMatrix struct {

	// The number of matches in the data that the transform didn't find, in the
	// confusion matrix for your transform.
	NumFalseNegatives *int64

	// The number of nonmatches in the data that the transform incorrectly classified
	// as a match, in the confusion matrix for your transform.
	NumFalsePositives *int64

	// The number of nonmatches in the data that the transform correctly rejected, in
	// the confusion matrix for your transform.
	NumTrueNegatives *int64

	// The number of matches in the data that the transform correctly found, in the
	// confusion matrix for your transform.
	NumTruePositives *int64

	noSmithyDocumentSerde
}

// Defines a connection to a data source.
type Connection struct {

	// These key-value pairs define parameters for the connection:
	//   - HOST - The host URI: either the fully qualified domain name (FQDN) or the
	//   IPv4 address of the database host.
	//   - PORT - The port number, between 1024 and 65535, of the port on which the
	//   database host is listening for database connections.
	//   - USER_NAME - The name under which to log in to the database. The value string
	//   for USER_NAME is " USERNAME ".
	//   - PASSWORD - A password, if one is used, for the user name.
	//   - ENCRYPTED_PASSWORD - When you enable connection password protection by
	//   setting ConnectionPasswordEncryption in the Data Catalog encryption settings,
	//   this field stores the encrypted password.
	//   - JDBC_DRIVER_JAR_URI - The Amazon Simple Storage Service (Amazon S3) path of
	//   the JAR file that contains the JDBC driver to use.
	//   - JDBC_DRIVER_CLASS_NAME - The class name of the JDBC driver to use.
	//   - JDBC_ENGINE - The name of the JDBC engine to use.
	//   - JDBC_ENGINE_VERSION - The version of the JDBC engine to use.
	//   - CONFIG_FILES - (Reserved for future use.)
	//   - INSTANCE_ID - The instance ID to use.
	//   - JDBC_CONNECTION_URL - The URL for connecting to a JDBC data source.
	//   - JDBC_ENFORCE_SSL - A Boolean string (true, false) specifying whether Secure
	//   Sockets Layer (SSL) with hostname matching is enforced for the JDBC connection
	//   on the client. The default is false.
	//   - CUSTOM_JDBC_CERT - An Amazon S3 location specifying the customer's root
	//   certificate. Glue uses this root certificate to validate the customer’s
	//   certificate when connecting to the customer database. Glue only handles X.509
	//   certificates. The certificate provided must be DER-encoded and supplied in
	//   Base64 encoding PEM format.
	//   - SKIP_CUSTOM_JDBC_CERT_VALIDATION - By default, this is false . Glue
	//   validates the Signature algorithm and Subject Public Key Algorithm for the
	//   customer certificate. The only permitted algorithms for the Signature algorithm
	//   are SHA256withRSA, SHA384withRSA or SHA512withRSA. For the Subject Public Key
	//   Algorithm, the key length must be at least 2048. You can set the value of this
	//   property to true to skip Glue’s validation of the customer certificate.
	//   - CUSTOM_JDBC_CERT_STRING - A custom JDBC certificate string which is used for
	//   domain match or distinguished name match to prevent a man-in-the-middle attack.
	//   In Oracle database, this is used as the SSL_SERVER_CERT_DN ; in Microsoft SQL
	//   Server, this is used as the hostNameInCertificate .
	//   - CONNECTION_URL - The URL for connecting to a general (non-JDBC) data source.
	//   - SECRET_ID - The secret ID used for the secret manager of credentials.
	//   - CONNECTOR_URL - The connector URL for a MARKETPLACE or CUSTOM connection.
	//   - CONNECTOR_TYPE - The connector type for a MARKETPLACE or CUSTOM connection.
	//   - CONNECTOR_CLASS_NAME - The connector class name for a MARKETPLACE or CUSTOM
	//   connection.
	//   - KAFKA_BOOTSTRAP_SERVERS - A comma-separated list of host and port pairs that
	//   are the addresses of the Apache Kafka brokers in a Kafka cluster to which a
	//   Kafka client will connect to and bootstrap itself.
	//   - KAFKA_SSL_ENABLED - Whether to enable or disable SSL on an Apache Kafka
	//   connection. Default value is "true".
	//   - KAFKA_CUSTOM_CERT - The Amazon S3 URL for the private CA cert file (.pem
	//   format). The default is an empty string.
	//   - KAFKA_SKIP_CUSTOM_CERT_VALIDATION - Whether to skip the validation of the CA
	//   cert file or not. Glue validates for three algorithms: SHA256withRSA,
	//   SHA384withRSA and SHA512withRSA. Default value is "false".
	//   - KAFKA_CLIENT_KEYSTORE - The Amazon S3 location of the client keystore file
	//   for Kafka client side authentication (Optional).
	//   - KAFKA_CLIENT_KEYSTORE_PASSWORD - The password to access the provided
	//   keystore (Optional).
	//   - KAFKA_CLIENT_KEY_PASSWORD - A keystore can consist of multiple keys, so this
	//   is the password to access the client key to be used with the Kafka server side
	//   key (Optional).
	//   - ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD - The encrypted version of the
	//   Kafka client keystore password (if the user has the Glue encrypt passwords
	//   setting selected).
	//   - ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD - The encrypted version of the Kafka
	//   client key password (if the user has the Glue encrypt passwords setting
	//   selected).
	//   - KAFKA_SASL_MECHANISM - "SCRAM-SHA-512" , "GSSAPI" , or "AWS_MSK_IAM" . These
	//   are the supported SASL Mechanisms (https://www.iana.org/assignments/sasl-mechanisms/sasl-mechanisms.xhtml)
	//   .
	//   - KAFKA_SASL_SCRAM_USERNAME - A plaintext username used to authenticate with
	//   the "SCRAM-SHA-512" mechanism.
	//   - KAFKA_SASL_SCRAM_PASSWORD - A plaintext password used to authenticate with
	//   the "SCRAM-SHA-512" mechanism.
	//   - ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD - The encrypted version of the Kafka
	//   SASL SCRAM password (if the user has the Glue encrypt passwords setting
	//   selected).
	//   - KAFKA_SASL_SCRAM_SECRETS_ARN - The Amazon Resource Name of a secret in
	//   Amazon Web Services Secrets Manager.
	//   - KAFKA_SASL_GSSAPI_KEYTAB - The S3 location of a Kerberos keytab file. A
	//   keytab stores long-term keys for one or more principals. For more information,
	//   see MIT Kerberos Documentation: Keytab (https://web.mit.edu/kerberos/krb5-latest/doc/basic/keytab_def.html)
	//   .
	//   - KAFKA_SASL_GSSAPI_KRB5_CONF - The S3 location of a Kerberos krb5.conf file.
	//   A krb5.conf stores Kerberos configuration information, such as the location of
	//   the KDC server. For more information, see MIT Kerberos Documentation:
	//   krb5.conf (https://web.mit.edu/kerberos/krb5-1.12/doc/admin/conf_files/krb5_conf.html)
	//   .
	//   - KAFKA_SASL_GSSAPI_SERVICE - The Kerberos service name, as set with
	//   sasl.kerberos.service.name in your Kafka Configuration (https://kafka.apache.org/documentation/#brokerconfigs_sasl.kerberos.service.name)
	//   .
	//   - KAFKA_SASL_GSSAPI_PRINCIPAL - The name of the Kerberos princial used by
	//   Glue. For more information, see Kafka Documentation: Configuring Kafka Brokers (https://kafka.apache.org/documentation/#security_sasl_kerberos_clientconfig)
	//   .
	ConnectionProperties map[string]string

	// The type of the connection. Currently, SFTP is not supported.
	ConnectionType ConnectionType

	// The time that this connection definition was created.
	CreationTime *time.Time

	// The description of the connection.
	Description *string

	// The user, group, or role that last updated this connection definition.
	LastUpdatedBy *string

	// The last time that this connection definition was updated.
	LastUpdatedTime *time.Time

	// A list of criteria that can be used in selecting this connection.
	MatchCriteria []string

	// The name of the connection definition.
	Name *string

	// A map of physical connection requirements, such as virtual private cloud (VPC)
	// and SecurityGroup , that are needed to make this connection successfully.
	PhysicalConnectionRequirements *PhysicalConnectionRequirements

	noSmithyDocumentSerde
}

// A structure that is used to specify a connection to create or update.
type ConnectionInput struct {

	// These key-value pairs define parameters for the connection.
	//
	// This member is required.
	ConnectionProperties map[string]string

	// The type of the connection. Currently, these types are supported:
	//   - JDBC - Designates a connection to a database through Java Database
	//   Connectivity (JDBC). JDBC Connections use the following ConnectionParameters.
	//   - Required: All of ( HOST , PORT , JDBC_ENGINE ) or JDBC_CONNECTION_URL .
	//   - Required: All of ( USERNAME , PASSWORD ) or SECRET_ID .
	//   - Optional: JDBC_ENFORCE_SSL , CUSTOM_JDBC_CERT , CUSTOM_JDBC_CERT_STRING ,
	//   SKIP_CUSTOM_JDBC_CERT_VALIDATION . These parameters are used to configure SSL
	//   with JDBC.
	//   - KAFKA - Designates a connection to an Apache Kafka streaming platform. KAFKA
	//   Connections use the following ConnectionParameters.
	//   - Required: KAFKA_BOOTSTRAP_SERVERS .
	//   - Optional: KAFKA_SSL_ENABLED , KAFKA_CUSTOM_CERT ,
	//   KAFKA_SKIP_CUSTOM_CERT_VALIDATION . These parameters are used to configure SSL
	//   with KAFKA .
	//   - Optional: KAFKA_CLIENT_KEYSTORE , KAFKA_CLIENT_KEYSTORE_PASSWORD ,
	//   KAFKA_CLIENT_KEY_PASSWORD , ENCRYPTED_KAFKA_CLIENT_KEYSTORE_PASSWORD ,
	//   ENCRYPTED_KAFKA_CLIENT_KEY_PASSWORD . These parameters are used to configure
	//   TLS client configuration with SSL in KAFKA .
	//   - Optional: KAFKA_SASL_MECHANISM . Can be specified as SCRAM-SHA-512 , GSSAPI
	//   , or AWS_MSK_IAM .
	//   - Optional: KAFKA_SASL_SCRAM_USERNAME , KAFKA_SASL_SCRAM_PASSWORD ,
	//   ENCRYPTED_KAFKA_SASL_SCRAM_PASSWORD . These parameters are used to configure
	//   SASL/SCRAM-SHA-512 authentication with KAFKA .
	//   - Optional: KAFKA_SASL_GSSAPI_KEYTAB , KAFKA_SASL_GSSAPI_KRB5_CONF ,
	//   KAFKA_SASL_GSSAPI_SERVICE , KAFKA_SASL_GSSAPI_PRINCIPAL . These parameters are
	//   used to configure SASL/GSSAPI authentication with KAFKA .
	//   - MONGODB - Designates a connection to a MongoDB document database. MONGODB
	//   Connections use the following ConnectionParameters.
	//   - Required: CONNECTION_URL .
	//   - Required: All of ( USERNAME , PASSWORD ) or SECRET_ID .
	//   - NETWORK - Designates a network connection to a data source within an Amazon
	//   Virtual Private Cloud environment (Amazon VPC). NETWORK Connections do not
	//   require ConnectionParameters. Instead, provide a PhysicalConnectionRequirements.
	//
	//   - MARKETPLACE - Uses configuration settings contained in a connector purchased
	//   from Amazon Web Services Marketplace to read from and write to data stores that
	//   are not natively supported by Glue. MARKETPLACE Connections use the following
	//   ConnectionParameters.
	//   - Required: CONNECTOR_TYPE , CONNECTOR_URL , CONNECTOR_CLASS_NAME ,
	//   CONNECTION_URL .
	//   - Required for JDBC CONNECTOR_TYPE connections: All of ( USERNAME , PASSWORD )
	//   or SECRET_ID .
	//   - CUSTOM - Uses configuration settings contained in a custom connector to read
	//   from and write to data stores that are not natively supported by Glue.
	// SFTP is not supported. For more information about how optional
	// ConnectionProperties are used to configure features in Glue, consult Glue
	// connection properties (https://docs.aws.amazon.com/glue/latest/dg/connection-defining.html)
	// . For more information about how optional ConnectionProperties are used to
	// configure features in Glue Studio, consult Using connectors and connections (https://docs.aws.amazon.com/glue/latest/ug/connectors-chapter.html)
	// .
	//
	// This member is required.
	ConnectionType ConnectionType

	// The name of the connection. Connection will not function as expected without a
	// name.
	//
	// This member is required.
	Name *string

	// The description of the connection.
	Description *string

	// A list of criteria that can be used in selecting this connection.
	MatchCriteria []string

	// A map of physical connection requirements, such as virtual private cloud (VPC)
	// and SecurityGroup , that are needed to successfully make this connection.
	PhysicalConnectionRequirements *PhysicalConnectionRequirements

	noSmithyDocumentSerde
}

// The data structure used by the Data Catalog to encrypt the password as part of
// CreateConnection or UpdateConnection and store it in the ENCRYPTED_PASSWORD
// field in the connection properties. You can enable catalog encryption or only
// password encryption. When a CreationConnection request arrives containing a
// password, the Data Catalog first encrypts the password using your KMS key. It
// then encrypts the whole connection object again if catalog encryption is also
// enabled. This encryption requires that you set KMS key permissions to enable or
// restrict access on the password key according to your security requirements. For
// example, you might want only administrators to have decrypt permission on the
// password key.
type ConnectionPasswordEncryption struct {

	// When the ReturnConnectionPasswordEncrypted flag is set to "true", passwords
	// remain encrypted in the responses of GetConnection and GetConnections . This
	// encryption takes effect independently from catalog encryption.
	//
	// This member is required.
	ReturnConnectionPasswordEncrypted bool

	// An KMS key that is used to encrypt the connection password. If connection
	// password protection is enabled, the caller of CreateConnection and
	// UpdateConnection needs at least kms:Encrypt permission on the specified KMS
	// key, to encrypt passwords before storing them in the Data Catalog. You can set
	// the decrypt permission to enable or restrict access on the password key
	// according to your security requirements.
	AwsKmsKeyId *string

	noSmithyDocumentSerde
}

// Specifies the connections used by a job.
type ConnectionsList struct {

	// A list of connections used by the job.
	Connections []string

	noSmithyDocumentSerde
}

// Specifies a source generated with standard connection options.
type ConnectorDataSource struct {

	// The connectionType , as provided to the underlying Glue library. This node type
	// supports the following connection types:
	//   - opensearch
	//   - azuresql
	//   - azurecosmos
	//   - bigquery
	//   - saphana
	//   - teradata
	//   - vertica
	//
	// This member is required.
	ConnectionType *string

	// A map specifying connection options for the node. You can find standard
	// connection options for the corresponding connection type in the Connection
	// parameters (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-connect.html)
	// section of the Glue documentation.
	//
	// This member is required.
	Data map[string]string

	// The name of this source node.
	//
	// This member is required.
	Name *string

	// Specifies the data schema for this source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a target generated with standard connection options.
type ConnectorDataTarget struct {

	// The connectionType , as provided to the underlying Glue library. This node type
	// supports the following connection types:
	//   - opensearch
	//   - azuresql
	//   - azurecosmos
	//   - bigquery
	//   - saphana
	//   - teradata
	//   - vertica
	//
	// This member is required.
	ConnectionType *string

	// A map specifying connection options for the node. You can find standard
	// connection options for the corresponding connection type in the Connection
	// parameters (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-connect.html)
	// section of the Glue documentation.
	//
	// This member is required.
	Data map[string]string

	// The name of this target node.
	//
	// This member is required.
	Name *string

	// The nodes that are inputs to the data target.
	Inputs []string

	noSmithyDocumentSerde
}

// The details of a crawl in the workflow.
type Crawl struct {

	// The date and time on which the crawl completed.
	CompletedOn *time.Time

	// The error message associated with the crawl.
	ErrorMessage *string

	// The log group associated with the crawl.
	LogGroup *string

	// The log stream associated with the crawl.
	LogStream *string

	// The date and time on which the crawl started.
	StartedOn *time.Time

	// The state of the crawler.
	State CrawlState

	noSmithyDocumentSerde
}

// Specifies a crawler program that examines a data source and uses classifiers to
// try to determine its schema. If successful, the crawler records metadata
// concerning the data source in the Glue Data Catalog.
type Crawler struct {

	// A list of UTF-8 strings that specify the custom classifiers that are associated
	// with the crawler.
	Classifiers []string

	// Crawler configuration information. This versioned JSON string allows users to
	// specify aspects of a crawler's behavior. For more information, see Setting
	// crawler configuration options (https://docs.aws.amazon.com/glue/latest/dg/crawler-configuration.html)
	// .
	Configuration *string

	// If the crawler is running, contains the total time elapsed since the last crawl
	// began.
	CrawlElapsedTime int64

	// The name of the SecurityConfiguration structure to be used by this crawler.
	CrawlerSecurityConfiguration *string

	// The time that the crawler was created.
	CreationTime *time.Time

	// The name of the database in which the crawler's output is stored.
	DatabaseName *string

	// A description of the crawler.
	Description *string

	// Specifies whether the crawler should use Lake Formation credentials for the
	// crawler instead of the IAM role credentials.
	LakeFormationConfiguration *LakeFormationConfiguration

	// The status of the last crawl, and potentially error information if an error
	// occurred.
	LastCrawl *LastCrawlInfo

	// The time that the crawler was last updated.
	LastUpdated *time.Time

	// A configuration that specifies whether data lineage is enabled for the crawler.
	LineageConfiguration *LineageConfiguration

	// The name of the crawler.
	Name *string

	// A policy that specifies whether to crawl the entire dataset again, or to crawl
	// only folders that were added since the last crawler run.
	RecrawlPolicy *RecrawlPolicy

	// The Amazon Resource Name (ARN) of an IAM role that's used to access customer
	// resources, such as Amazon Simple Storage Service (Amazon S3) data.
	Role *string

	// For scheduled crawlers, the schedule when the crawler runs.
	Schedule *Schedule

	// The policy that specifies update and delete behaviors for the crawler.
	SchemaChangePolicy *SchemaChangePolicy

	// Indicates whether the crawler is running, or whether a run is pending.
	State CrawlerState

	// The prefix added to the names of tables that are created.
	TablePrefix *string

	// A collection of targets to crawl.
	Targets *CrawlerTargets

	// The version of the crawler.
	Version int64

	noSmithyDocumentSerde
}

// Contains the information for a run of a crawler.
type CrawlerHistory struct {

	// A UUID identifier for each crawl.
	CrawlId *string

	// The number of data processing units (DPU) used in hours for the crawl.
	DPUHour float64

	// The date and time on which the crawl ended.
	EndTime *time.Time

	// If an error occurred, the error message associated with the crawl.
	ErrorMessage *string

	// The log group associated with the crawl.
	LogGroup *string

	// The log stream associated with the crawl.
	LogStream *string

	// The prefix for a CloudWatch message about this crawl.
	MessagePrefix *string

	// The date and time on which the crawl started.
	StartTime *time.Time

	// The state of the crawl.
	State CrawlerHistoryState

	// A run summary for the specific crawl in JSON. Contains the catalog tables and
	// partitions that were added, updated, or deleted.
	Summary *string

	noSmithyDocumentSerde
}

// Metrics for a specified crawler.
type CrawlerMetrics struct {

	// The name of the crawler.
	CrawlerName *string

	// The duration of the crawler's most recent run, in seconds.
	LastRuntimeSeconds float64

	// The median duration of this crawler's runs, in seconds.
	MedianRuntimeSeconds float64

	// True if the crawler is still estimating how long it will take to complete this
	// run.
	StillEstimating bool

	// The number of tables created by this crawler.
	TablesCreated int32

	// The number of tables deleted by this crawler.
	TablesDeleted int32

	// The number of tables updated by this crawler.
	TablesUpdated int32

	// The estimated time left to complete a running crawl.
	TimeLeftSeconds float64

	noSmithyDocumentSerde
}

// The details of a Crawler node present in the workflow.
type CrawlerNodeDetails struct {

	// A list of crawls represented by the crawl node.
	Crawls []Crawl

	noSmithyDocumentSerde
}

// Specifies data stores to crawl.
type CrawlerTargets struct {

	// Specifies Glue Data Catalog targets.
	CatalogTargets []CatalogTarget

	// Specifies Delta data store targets.
	DeltaTargets []DeltaTarget

	// Specifies Amazon DynamoDB targets.
	DynamoDBTargets []DynamoDBTarget

	// Specifies Apache Hudi data store targets.
	HudiTargets []HudiTarget

	// Specifies Apache Iceberg data store targets.
	IcebergTargets []IcebergTarget

	// Specifies JDBC targets.
	JdbcTargets []JdbcTarget

	// Specifies Amazon DocumentDB or MongoDB targets.
	MongoDBTargets []MongoDBTarget

	// Specifies Amazon Simple Storage Service (Amazon S3) targets.
	S3Targets []S3Target

	noSmithyDocumentSerde
}

// A list of fields, comparators and value that you can use to filter the crawler
// runs for a specified crawler.
type CrawlsFilter struct {

	// A key used to filter the crawler runs for a specified crawler. Valid values for
	// each of the field names are:
	//   - CRAWL_ID : A string representing the UUID identifier for a crawl.
	//   - STATE : A string representing the state of the crawl.
	//   - START_TIME and END_TIME : The epoch timestamp in milliseconds.
	//   - DPU_HOUR : The number of data processing unit (DPU) hours used for the
	//   crawl.
	FieldName FieldName

	// The value provided for comparison on the crawl field.
	FieldValue *string

	// A defined comparator that operates on the value. The available operators are:
	//   - GT : Greater than.
	//   - GE : Greater than or equal to.
	//   - LT : Less than.
	//   - LE : Less than or equal to.
	//   - EQ : Equal to.
	//   - NE : Not equal to.
	FilterOperator FilterOperator

	noSmithyDocumentSerde
}

// Specifies a custom CSV classifier for CreateClassifier to create.
type CreateCsvClassifierRequest struct {

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// Enables the processing of files that contain only one column.
	AllowSingleColumn *bool

	// Indicates whether the CSV file contains a header.
	ContainsHeader CsvHeaderOption

	// Enables the configuration of custom datatypes.
	CustomDatatypeConfigured *bool

	// Creates a list of supported custom datatypes.
	CustomDatatypes []string

	// A custom symbol to denote what separates each column entry in the row.
	Delimiter *string

	// Specifies not to trim values before identifying the type of column values. The
	// default value is true.
	DisableValueTrimming *bool

	// A list of strings representing column names.
	Header []string

	// A custom symbol to denote what combines content into a single column value.
	// Must be different from the column delimiter.
	QuoteSymbol *string

	// Sets the SerDe for processing CSV in the classifier, which will be applied in
	// the Data Catalog. Valid values are OpenCSVSerDe , LazySimpleSerDe , and None .
	// You can specify the None value when you want the crawler to do the detection.
	Serde CsvSerdeOption

	noSmithyDocumentSerde
}

// Specifies a grok classifier for CreateClassifier to create.
type CreateGrokClassifierRequest struct {

	// An identifier of the data format that the classifier matches, such as Twitter,
	// JSON, Omniture logs, Amazon CloudWatch Logs, and so on.
	//
	// This member is required.
	Classification *string

	// The grok pattern used by this classifier.
	//
	// This member is required.
	GrokPattern *string

	// The name of the new classifier.
	//
	// This member is required.
	Name *string

	// Optional custom grok patterns used by this classifier.
	CustomPatterns *string

	noSmithyDocumentSerde
}

// Specifies a JSON classifier for CreateClassifier to create.
type CreateJsonClassifierRequest struct {

	// A JsonPath string defining the JSON data for the classifier to classify. Glue
	// supports a subset of JsonPath, as described in Writing JsonPath Custom
	// Classifiers (https://docs.aws.amazon.com/glue/latest/dg/custom-classifier.html#custom-classifier-json)
	// .
	//
	// This member is required.
	JsonPath *string

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Specifies an XML classifier for CreateClassifier to create.
type CreateXMLClassifierRequest struct {

	// An identifier of the data format that the classifier matches.
	//
	// This member is required.
	Classification *string

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// The XML tag designating the element that contains each record in an XML
	// document being parsed. This can't identify a self-closing element (closed by />
	// ). An empty row element that contains only attributes can be parsed as long as
	// it ends with a closing tag (for example, is okay, but  is not).
	RowTag *string

	noSmithyDocumentSerde
}

// A classifier for custom CSV content.
type CsvClassifier struct {

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// Enables the processing of files that contain only one column.
	AllowSingleColumn *bool

	// Indicates whether the CSV file contains a header.
	ContainsHeader CsvHeaderOption

	// The time that this classifier was registered.
	CreationTime *time.Time

	// Enables the custom datatype to be configured.
	CustomDatatypeConfigured *bool

	// A list of custom datatypes including "BINARY", "BOOLEAN", "DATE", "DECIMAL",
	// "DOUBLE", "FLOAT", "INT", "LONG", "SHORT", "STRING", "TIMESTAMP".
	CustomDatatypes []string

	// A custom symbol to denote what separates each column entry in the row.
	Delimiter *string

	// Specifies not to trim values before identifying the type of column values. The
	// default value is true .
	DisableValueTrimming *bool

	// A list of strings representing column names.
	Header []string

	// The time that this classifier was last updated.
	LastUpdated *time.Time

	// A custom symbol to denote what combines content into a single column value. It
	// must be different from the column delimiter.
	QuoteSymbol *string

	// Sets the SerDe for processing CSV in the classifier, which will be applied in
	// the Data Catalog. Valid values are OpenCSVSerDe , LazySimpleSerDe , and None .
	// You can specify the None value when you want the crawler to do the detection.
	Serde CsvSerdeOption

	// The version of this classifier.
	Version int64

	noSmithyDocumentSerde
}

// Specifies a transform that uses custom code you provide to perform the data
// transformation. The output is a collection of DynamicFrames.
type CustomCode struct {

	// The name defined for the custom code node class.
	//
	// This member is required.
	ClassName *string

	// The custom code that is used to perform the data transformation.
	//
	// This member is required.
	Code *string

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// Specifies the data schema for the custom code transform.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// An object representing a custom pattern for detecting sensitive data across the
// columns and rows of your structured data.
type CustomEntityType struct {

	// A name for the custom pattern that allows it to be retrieved or deleted later.
	// This name must be unique per Amazon Web Services account.
	//
	// This member is required.
	Name *string

	// A regular expression string that is used for detecting sensitive data in a
	// custom pattern.
	//
	// This member is required.
	RegexString *string

	// A list of context words. If none of these context words are found within the
	// vicinity of the regular expression the data will not be detected as sensitive
	// data. If no context words are passed only a regular expression is checked.
	ContextWords []string

	noSmithyDocumentSerde
}

// The Database object represents a logical grouping of tables that might reside
// in a Hive metastore or an RDBMS.
type Database struct {

	// The name of the database. For Hive compatibility, this is folded to lowercase
	// when it is stored.
	//
	// This member is required.
	Name *string

	// The ID of the Data Catalog in which the database resides.
	CatalogId *string

	// Creates a set of default permissions on the table for principals. Used by Lake
	// Formation. Not used in the normal course of Glue operations.
	CreateTableDefaultPermissions []PrincipalPermissions

	// The time at which the metadata database was created in the catalog.
	CreateTime *time.Time

	// A description of the database.
	Description *string

	// A FederatedDatabase structure that references an entity outside the Glue Data
	// Catalog.
	FederatedDatabase *FederatedDatabase

	// The location of the database (for example, an HDFS path).
	LocationUri *string

	// These key-value pairs define parameters and properties of the database.
	Parameters map[string]string

	// A DatabaseIdentifier structure that describes a target database for resource
	// linking.
	TargetDatabase *DatabaseIdentifier

	noSmithyDocumentSerde
}

// A structure that describes a target database for resource linking.
type DatabaseIdentifier struct {

	// The ID of the Data Catalog in which the database resides.
	CatalogId *string

	// The name of the catalog database.
	DatabaseName *string

	// Region of the target database.
	Region *string

	noSmithyDocumentSerde
}

// The structure used to create or update a database.
type DatabaseInput struct {

	// The name of the database. For Hive compatibility, this is folded to lowercase
	// when it is stored.
	//
	// This member is required.
	Name *string

	// Creates a set of default permissions on the table for principals. Used by Lake
	// Formation. Not used in the normal course of Glue operations.
	CreateTableDefaultPermissions []PrincipalPermissions

	// A description of the database.
	Description *string

	// A FederatedDatabase structure that references an entity outside the Glue Data
	// Catalog.
	FederatedDatabase *FederatedDatabase

	// The location of the database (for example, an HDFS path).
	LocationUri *string

	// These key-value pairs define parameters and properties of the database. These
	// key-value pairs define parameters and properties of the database.
	Parameters map[string]string

	// A DatabaseIdentifier structure that describes a target database for resource
	// linking.
	TargetDatabase *DatabaseIdentifier

	noSmithyDocumentSerde
}

// Contains configuration information for maintaining Data Catalog security.
type DataCatalogEncryptionSettings struct {

	// When connection password protection is enabled, the Data Catalog uses a
	// customer-provided key to encrypt the password as part of CreateConnection or
	// UpdateConnection and store it in the ENCRYPTED_PASSWORD field in the connection
	// properties. You can enable catalog encryption or only password encryption.
	ConnectionPasswordEncryption *ConnectionPasswordEncryption

	// Specifies the encryption-at-rest configuration for the Data Catalog.
	EncryptionAtRest *EncryptionAtRest

	noSmithyDocumentSerde
}

// The Lake Formation principal.
type DataLakePrincipal struct {

	// An identifier for the Lake Formation principal.
	DataLakePrincipalIdentifier *string

	noSmithyDocumentSerde
}

// Describes the result of the evaluation of a data quality analyzer.
type DataQualityAnalyzerResult struct {

	// A description of the data quality analyzer.
	Description *string

	// A map of metrics associated with the evaluation of the analyzer.
	EvaluatedMetrics map[string]float64

	// An evaluation message.
	EvaluationMessage *string

	// The name of the data quality analyzer.
	Name *string

	noSmithyDocumentSerde
}

// Additional run options you can specify for an evaluation run.
type DataQualityEvaluationRunAdditionalRunOptions struct {

	// Whether or not to enable CloudWatch metrics.
	CloudWatchMetricsEnabled *bool

	// Prefix for Amazon S3 to store results.
	ResultsS3Prefix *string

	noSmithyDocumentSerde
}

// Describes the data quality metric value according to the analysis of historical
// data.
type DataQualityMetricValues struct {

	// The actual value of the data quality metric.
	ActualValue *float64

	// The expected value of the data quality metric according to the analysis of
	// historical data.
	ExpectedValue *float64

	// The lower limit of the data quality metric value according to the analysis of
	// historical data.
	LowerLimit *float64

	// The upper limit of the data quality metric value according to the analysis of
	// historical data.
	UpperLimit *float64

	noSmithyDocumentSerde
}

// Describes the observation generated after evaluating the rules and analyzers.
type DataQualityObservation struct {

	// A description of the data quality observation.
	Description *string

	// An object of type MetricBasedObservation representing the observation that is
	// based on evaluated data quality metrics.
	MetricBasedObservation *MetricBasedObservation

	noSmithyDocumentSerde
}

// Describes a data quality result.
type DataQualityResult struct {

	// A list of DataQualityAnalyzerResult objects representing the results for each
	// analyzer.
	AnalyzerResults []DataQualityAnalyzerResult

	// The date and time when this data quality run completed.
	CompletedOn *time.Time

	// The table associated with the data quality result, if any.
	DataSource *DataSource

	// In the context of a job in Glue Studio, each node in the canvas is typically
	// assigned some sort of name and data quality nodes will have names. In the case
	// of multiple nodes, the evaluationContext can differentiate the nodes.
	EvaluationContext *string

	// The job name associated with the data quality result, if any.
	JobName *string

	// The job run ID associated with the data quality result, if any.
	JobRunId *string

	// A list of DataQualityObservation objects representing the observations
	// generated after evaluating the rules and analyzers.
	Observations []DataQualityObservation

	// A unique result ID for the data quality result.
	ResultId *string

	// A list of DataQualityRuleResult objects representing the results for each rule.
	RuleResults []DataQualityRuleResult

	// The unique run ID for the ruleset evaluation for this data quality result.
	RulesetEvaluationRunId *string

	// The name of the ruleset associated with the data quality result.
	RulesetName *string

	// An aggregate data quality score. Represents the ratio of rules that passed to
	// the total number of rules.
	Score *float64

	// The date and time when this data quality run started.
	StartedOn *time.Time

	noSmithyDocumentSerde
}

// Describes a data quality result.
type DataQualityResultDescription struct {

	// The table name associated with the data quality result.
	DataSource *DataSource

	// The job name associated with the data quality result.
	JobName *string

	// The job run ID associated with the data quality result.
	JobRunId *string

	// The unique result ID for this data quality result.
	ResultId *string

	// The time that the run started for this data quality result.
	StartedOn *time.Time

	noSmithyDocumentSerde
}

// Criteria used to return data quality results.
type DataQualityResultFilterCriteria struct {

	// Filter results by the specified data source. For example, retrieving all
	// results for an Glue table.
	DataSource *DataSource

	// Filter results by the specified job name.
	JobName *string

	// Filter results by the specified job run ID.
	JobRunId *string

	// Filter results by runs that started after this time.
	StartedAfter *time.Time

	// Filter results by runs that started before this time.
	StartedBefore *time.Time

	noSmithyDocumentSerde
}

// Describes the result of a data quality rule recommendation run.
type DataQualityRuleRecommendationRunDescription struct {

	// The data source (Glue table) associated with the recommendation run.
	DataSource *DataSource

	// The unique run identifier associated with this run.
	RunId *string

	// The date and time when this run started.
	StartedOn *time.Time

	// The status for this run.
	Status TaskStatusType

	noSmithyDocumentSerde
}

// A filter for listing data quality recommendation runs.
type DataQualityRuleRecommendationRunFilter struct {

	// Filter based on a specified data source (Glue table).
	//
	// This member is required.
	DataSource *DataSource

	// Filter based on time for results started after provided time.
	StartedAfter *time.Time

	// Filter based on time for results started before provided time.
	StartedBefore *time.Time

	noSmithyDocumentSerde
}

// Describes the result of the evaluation of a data quality rule.
type DataQualityRuleResult struct {

	// A description of the data quality rule.
	Description *string

	// A map of metrics associated with the evaluation of the rule.
	EvaluatedMetrics map[string]float64

	// An evaluation message.
	EvaluationMessage *string

	// The name of the data quality rule.
	Name *string

	// A pass or fail status for the rule.
	Result DataQualityRuleResultStatus

	noSmithyDocumentSerde
}

// Describes the result of a data quality ruleset evaluation run.
type DataQualityRulesetEvaluationRunDescription struct {

	// The data source (an Glue table) associated with the run.
	DataSource *DataSource

	// The unique run identifier associated with this run.
	RunId *string

	// The date and time when the run started.
	StartedOn *time.Time

	// The status for this run.
	Status TaskStatusType

	noSmithyDocumentSerde
}

// The filter criteria.
type DataQualityRulesetEvaluationRunFilter struct {

	// Filter based on a data source (an Glue table) associated with the run.
	//
	// This member is required.
	DataSource *DataSource

	// Filter results by runs that started after this time.
	StartedAfter *time.Time

	// Filter results by runs that started before this time.
	StartedBefore *time.Time

	noSmithyDocumentSerde
}

// The criteria used to filter data quality rulesets.
type DataQualityRulesetFilterCriteria struct {

	// Filter on rulesets created after this date.
	CreatedAfter *time.Time

	// Filter on rulesets created before this date.
	CreatedBefore *time.Time

	// The description of the ruleset filter criteria.
	Description *string

	// Filter on rulesets last modified after this date.
	LastModifiedAfter *time.Time

	// Filter on rulesets last modified before this date.
	LastModifiedBefore *time.Time

	// The name of the ruleset filter criteria.
	Name *string

	// The name and database name of the target table.
	TargetTable *DataQualityTargetTable

	noSmithyDocumentSerde
}

// Describes a data quality ruleset returned by GetDataQualityRuleset .
type DataQualityRulesetListDetails struct {

	// The date and time the data quality ruleset was created.
	CreatedOn *time.Time

	// A description of the data quality ruleset.
	Description *string

	// The date and time the data quality ruleset was last modified.
	LastModifiedOn *time.Time

	// The name of the data quality ruleset.
	Name *string

	// When a ruleset was created from a recommendation run, this run ID is generated
	// to link the two together.
	RecommendationRunId *string

	// The number of rules in the ruleset.
	RuleCount *int32

	// An object representing an Glue table.
	TargetTable *DataQualityTargetTable

	noSmithyDocumentSerde
}

// An object representing an Glue table.
type DataQualityTargetTable struct {

	// The name of the database where the Glue table exists.
	//
	// This member is required.
	DatabaseName *string

	// The name of the Glue table.
	//
	// This member is required.
	TableName *string

	// The catalog id where the Glue table exists.
	CatalogId *string

	noSmithyDocumentSerde
}

// A data source (an Glue table) for which you want data quality results.
type DataSource struct {

	// An Glue table.
	//
	// This member is required.
	GlueTable *GlueTable

	noSmithyDocumentSerde
}

// A structure representing the datatype of the value.
type Datatype struct {

	// The datatype of the value.
	//
	// This member is required.
	Id *string

	// A label assigned to the datatype.
	//
	// This member is required.
	Label *string

	noSmithyDocumentSerde
}

// Defines column statistics supported for timestamp data columns.
type DateColumnStatisticsData struct {

	// The number of distinct values in a column.
	//
	// This member is required.
	NumberOfDistinctValues int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	// The highest value in the column.
	MaximumValue *time.Time

	// The lowest value in the column.
	MinimumValue *time.Time

	noSmithyDocumentSerde
}

// Defines column statistics supported for fixed-point number data columns.
type DecimalColumnStatisticsData struct {

	// The number of distinct values in a column.
	//
	// This member is required.
	NumberOfDistinctValues int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	// The highest value in the column.
	MaximumValue *DecimalNumber

	// The lowest value in the column.
	MinimumValue *DecimalNumber

	noSmithyDocumentSerde
}

// Contains a numeric value in decimal format.
type DecimalNumber struct {

	// The scale that determines where the decimal point falls in the unscaled value.
	//
	// This member is required.
	Scale int32

	// The unscaled numeric value.
	//
	// This member is required.
	UnscaledValue []byte

	noSmithyDocumentSerde
}

// Specifies a Delta data store to crawl one or more Delta tables.
type DeltaTarget struct {

	// The name of the connection to use to connect to the Delta table target.
	ConnectionName *string

	// Specifies whether the crawler will create native tables, to allow integration
	// with query engines that support querying of the Delta transaction log directly.
	CreateNativeDeltaTable *bool

	// A list of the Amazon S3 paths to the Delta tables.
	DeltaTables []string

	// Specifies whether to write the manifest files to the Delta table path.
	WriteManifest *bool

	noSmithyDocumentSerde
}

// A development endpoint where a developer can remotely debug extract, transform,
// and load (ETL) scripts.
type DevEndpoint struct {

	// A map of arguments used to configure the DevEndpoint . Valid arguments are:
	//   - "--enable-glue-datacatalog": ""
	// You can specify a version of Python support for development endpoints by using
	// the Arguments parameter in the CreateDevEndpoint or UpdateDevEndpoint APIs. If
	// no arguments are provided, the version defaults to Python 2.
	Arguments map[string]string

	// The Amazon Web Services Availability Zone where this DevEndpoint is located.
	AvailabilityZone *string

	// The point in time at which this DevEndpoint was created.
	CreatedTimestamp *time.Time

	// The name of the DevEndpoint .
	EndpointName *string

	// The path to one or more Java .jar files in an S3 bucket that should be loaded
	// in your DevEndpoint . You can only use pure Java/Scala libraries with a
	// DevEndpoint .
	ExtraJarsS3Path *string

	// The paths to one or more Python libraries in an Amazon S3 bucket that should be
	// loaded in your DevEndpoint . Multiple values must be complete paths separated by
	// a comma. You can only use pure Python libraries with a DevEndpoint . Libraries
	// that rely on C extensions, such as the pandas (http://pandas.pydata.org/)
	// Python data analysis library, are not currently supported.
	ExtraPythonLibsS3Path *string

	// The reason for a current failure in this DevEndpoint .
	FailureReason *string

	// Glue version determines the versions of Apache Spark and Python that Glue
	// supports. The Python version indicates the version supported for running your
	// ETL scripts on development endpoints. For more information about the available
	// Glue versions and corresponding Spark and Python versions, see Glue version (https://docs.aws.amazon.com/glue/latest/dg/add-job.html)
	// in the developer guide. Development endpoints that are created without
	// specifying a Glue version default to Glue 0.9. You can specify a version of
	// Python support for development endpoints by using the Arguments parameter in
	// the CreateDevEndpoint or UpdateDevEndpoint APIs. If no arguments are provided,
	// the version defaults to Python 2.
	GlueVersion *string

	// The point in time at which this DevEndpoint was last modified.
	LastModifiedTimestamp *time.Time

	// The status of the last update.
	LastUpdateStatus *string

	// The number of Glue Data Processing Units (DPUs) allocated to this DevEndpoint .
	NumberOfNodes int32

	// The number of workers of a defined workerType that are allocated to the
	// development endpoint. The maximum number of workers you can define are 299 for
	// G.1X , and 149 for G.2X .
	NumberOfWorkers *int32

	// A private IP address to access the DevEndpoint within a VPC if the DevEndpoint
	// is created within one. The PrivateAddress field is present only when you create
	// the DevEndpoint within your VPC.
	PrivateAddress *string

	// The public IP address used by this DevEndpoint . The PublicAddress field is
	// present only when you create a non-virtual private cloud (VPC) DevEndpoint .
	PublicAddress *string

	// The public key to be used by this DevEndpoint for authentication. This
	// attribute is provided for backward compatibility because the recommended
	// attribute to use is public keys.
	PublicKey *string

	// A list of public keys to be used by the DevEndpoints for authentication. Using
	// this attribute is preferred over a single public key because the public keys
	// allow you to have a different private key per client. If you previously created
	// an endpoint with a public key, you must remove that key to be able to set a list
	// of public keys. Call the UpdateDevEndpoint API operation with the public key
	// content in the deletePublicKeys attribute, and the list of new keys in the
	// addPublicKeys attribute.
	PublicKeys []string

	// The Amazon Resource Name (ARN) of the IAM role used in this DevEndpoint .
	RoleArn *string

	// The name of the SecurityConfiguration structure to be used with this DevEndpoint
	// .
	SecurityConfiguration *string

	// A list of security group identifiers used in this DevEndpoint .
	SecurityGroupIds []string

	// The current status of this DevEndpoint .
	Status *string

	// The subnet ID for this DevEndpoint .
	SubnetId *string

	// The ID of the virtual private cloud (VPC) used by this DevEndpoint .
	VpcId *string

	// The type of predefined worker that is allocated to the development endpoint.
	// Accepts a value of Standard, G.1X, or G.2X.
	//   - For the Standard worker type, each worker provides 4 vCPU, 16 GB of memory
	//   and a 50GB disk, and 2 executors per worker.
	//   - For the G.1X worker type, each worker maps to 1 DPU (4 vCPU, 16 GB of
	//   memory, 64 GB disk), and provides 1 executor per worker. We recommend this
	//   worker type for memory-intensive jobs.
	//   - For the G.2X worker type, each worker maps to 2 DPU (8 vCPU, 32 GB of
	//   memory, 128 GB disk), and provides 1 executor per worker. We recommend this
	//   worker type for memory-intensive jobs.
	// Known issue: when a development endpoint is created with the G.2X WorkerType
	// configuration, the Spark drivers for the development endpoint will run on 4
	// vCPU, 16 GB of memory, and a 64 GB disk.
	WorkerType WorkerType

	// The YARN endpoint address used by this DevEndpoint .
	YarnEndpointAddress *string

	// The Apache Zeppelin port for the remote Apache Spark interpreter.
	ZeppelinRemoteSparkInterpreterPort int32

	noSmithyDocumentSerde
}

// Custom libraries to be loaded into a development endpoint.
type DevEndpointCustomLibraries struct {

	// The path to one or more Java .jar files in an S3 bucket that should be loaded
	// in your DevEndpoint . You can only use pure Java/Scala libraries with a
	// DevEndpoint .
	ExtraJarsS3Path *string

	// The paths to one or more Python libraries in an Amazon Simple Storage Service
	// (Amazon S3) bucket that should be loaded in your DevEndpoint . Multiple values
	// must be complete paths separated by a comma. You can only use pure Python
	// libraries with a DevEndpoint . Libraries that rely on C extensions, such as the
	// pandas (http://pandas.pydata.org/) Python data analysis library, are not
	// currently supported.
	ExtraPythonLibsS3Path *string

	noSmithyDocumentSerde
}

// Specifies the direct JDBC source connection.
type DirectJDBCSource struct {

	// The connection name of the JDBC source.
	//
	// This member is required.
	ConnectionName *string

	// The connection type of the JDBC source.
	//
	// This member is required.
	ConnectionType JDBCConnectionType

	// The database of the JDBC source connection.
	//
	// This member is required.
	Database *string

	// The name of the JDBC source connection.
	//
	// This member is required.
	Name *string

	// The table of the JDBC source connection.
	//
	// This member is required.
	Table *string

	// The temp directory of the JDBC Redshift source.
	RedshiftTmpDir *string

	noSmithyDocumentSerde
}

// Specifies an Apache Kafka data store.
type DirectKafkaSource struct {

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// Specifies options related to data preview for viewing a sample of your data.
	DataPreviewOptions *StreamingDataPreviewOptions

	// Whether to automatically determine the schema from the incoming data.
	DetectSchema *bool

	// Specifies the streaming options.
	StreamingOptions *KafkaStreamingSourceOptions

	// The amount of time to spend processing each micro batch.
	WindowSize *int32

	noSmithyDocumentSerde
}

// Specifies a direct Amazon Kinesis data source.
type DirectKinesisSource struct {

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// Additional options for data preview.
	DataPreviewOptions *StreamingDataPreviewOptions

	// Whether to automatically determine the schema from the incoming data.
	DetectSchema *bool

	// Additional options for the Kinesis streaming data source.
	StreamingOptions *KinesisStreamingSourceOptions

	// The amount of time to spend processing each micro batch.
	WindowSize *int32

	noSmithyDocumentSerde
}

// A policy that specifies update behavior for the crawler.
type DirectSchemaChangePolicy struct {

	// Specifies the database that the schema change policy applies to.
	Database *string

	// Whether to use the specified update behavior when the crawler finds a changed
	// schema.
	EnableUpdateCatalog *bool

	// Specifies the table in the database that the schema change policy applies to.
	Table *string

	// The update behavior when the crawler finds a changed schema.
	UpdateBehavior UpdateCatalogBehavior

	noSmithyDocumentSerde
}

// Defines column statistics supported for floating-point number data columns.
type DoubleColumnStatisticsData struct {

	// The number of distinct values in a column.
	//
	// This member is required.
	NumberOfDistinctValues int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	// The highest value in the column.
	MaximumValue float64

	// The lowest value in the column.
	MinimumValue float64

	noSmithyDocumentSerde
}

// Options to configure how your data quality evaluation results are published.
type DQResultsPublishingOptions struct {

	// Enable metrics for your data quality results.
	CloudWatchMetricsEnabled *bool

	// The context of the evaluation.
	EvaluationContext *string

	// Enable publishing for your data quality results.
	ResultsPublishingEnabled *bool

	// The Amazon S3 prefix prepended to the results.
	ResultsS3Prefix *string

	noSmithyDocumentSerde
}

// Options to configure how your job will stop if your data quality evaluation
// fails.
type DQStopJobOnFailureOptions struct {

	// When to stop job if your data quality evaluation fails. Options are Immediate
	// or AfterDataLoad.
	StopJobOnFailureTiming DQStopJobOnFailureTiming

	noSmithyDocumentSerde
}

// Specifies a transform that removes rows of repeating data from a data set.
type DropDuplicates struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// The name of the columns to be merged or removed if repeating.
	Columns [][]string

	noSmithyDocumentSerde
}

// Specifies a transform that chooses the data property keys that you want to drop.
type DropFields struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A JSON path to a variable in the data structure.
	//
	// This member is required.
	Paths [][]string

	noSmithyDocumentSerde
}

// Specifies a transform that removes columns from the dataset if all values in
// the column are 'null'. By default, Glue Studio will recognize null objects, but
// some values such as empty strings, strings that are "null", -1 integers or other
// placeholders such as zeros, are not automatically recognized as nulls.
type DropNullFields struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A structure that represents whether certain values are recognized as null
	// values for removal.
	NullCheckBoxList *NullCheckBoxList

	// A structure that specifies a list of NullValueField structures that represent a
	// custom null value such as zero or other value being used as a null placeholder
	// unique to the dataset. The DropNullFields transform removes custom null values
	// only if both the value of the null placeholder and the datatype match the data.
	NullTextList []NullValueField

	noSmithyDocumentSerde
}

// Specifies the set of parameters needed to perform the dynamic transform.
type DynamicTransform struct {

	// Specifies the name of the function of the dynamic transform.
	//
	// This member is required.
	FunctionName *string

	// Specifies the inputs for the dynamic transform that are required.
	//
	// This member is required.
	Inputs []string

	// Specifies the name of the dynamic transform.
	//
	// This member is required.
	Name *string

	// Specifies the path of the dynamic transform source and config files.
	//
	// This member is required.
	Path *string

	// Specifies the name of the dynamic transform as it appears in the Glue Studio
	// visual editor.
	//
	// This member is required.
	TransformName *string

	// Specifies the data schema for the dynamic transform.
	OutputSchemas []GlueSchema

	// Specifies the parameters of the dynamic transform.
	Parameters []TransformConfigParameter

	// This field is not used and will be deprecated in future release.
	Version *string

	noSmithyDocumentSerde
}

// Specifies a DynamoDB data source in the Glue Data Catalog.
type DynamoDBCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies an Amazon DynamoDB table to crawl.
type DynamoDBTarget struct {

	// The name of the DynamoDB table to crawl.
	Path *string

	// Indicates whether to scan all the records, or to sample rows from the table.
	// Scanning all the records can take a long time when the table is not a high
	// throughput table. A value of true means to scan all records, while a value of
	// false means to sample the records. If no value is specified, the value defaults
	// to true .
	ScanAll *bool

	// The percentage of the configured read capacity units to use by the Glue
	// crawler. Read capacity units is a term defined by DynamoDB, and is a numeric
	// value that acts as rate limiter for the number of reads that can be performed on
	// that table per second. The valid values are null or a value between 0.1 to 1.5.
	// A null value is used when user does not provide a value, and defaults to 0.5 of
	// the configured Read Capacity Unit (for provisioned tables), or 0.25 of the max
	// configured Read Capacity Unit (for tables using on-demand mode).
	ScanRate *float64

	noSmithyDocumentSerde
}

// An edge represents a directed connection between two Glue components that are
// part of the workflow the edge belongs to.
type Edge struct {

	// The unique of the node within the workflow where the edge ends.
	DestinationId *string

	// The unique of the node within the workflow where the edge starts.
	SourceId *string

	noSmithyDocumentSerde
}

// Specifies the encryption-at-rest configuration for the Data Catalog.
type EncryptionAtRest struct {

	// The encryption-at-rest mode for encrypting Data Catalog data.
	//
	// This member is required.
	CatalogEncryptionMode CatalogEncryptionMode

	// The ID of the KMS key to use for encryption at rest.
	SseAwsKmsKeyId *string

	noSmithyDocumentSerde
}

// Specifies an encryption configuration.
type EncryptionConfiguration struct {

	// The encryption configuration for Amazon CloudWatch.
	CloudWatchEncryption *CloudWatchEncryption

	// The encryption configuration for job bookmarks.
	JobBookmarksEncryption *JobBookmarksEncryption

	// The encryption configuration for Amazon Simple Storage Service (Amazon S3) data.
	S3Encryption []S3Encryption

	noSmithyDocumentSerde
}

// Contains details about an error.
type ErrorDetail struct {

	// The code associated with this error.
	ErrorCode *string

	// A message describing the error.
	ErrorMessage *string

	noSmithyDocumentSerde
}

// An object containing error details.
type ErrorDetails struct {

	// The error code for an error.
	ErrorCode *string

	// The error message for an error.
	ErrorMessage *string

	noSmithyDocumentSerde
}

// Specifies your data quality evaluation criteria.
type EvaluateDataQuality struct {

	// The inputs of your data quality evaluation.
	//
	// This member is required.
	Inputs []string

	// The name of the data quality evaluation.
	//
	// This member is required.
	Name *string

	// The ruleset for your data quality evaluation.
	//
	// This member is required.
	Ruleset *string

	// The output of your data quality evaluation.
	Output DQTransformOutput

	// Options to configure how your results are published.
	PublishingOptions *DQResultsPublishingOptions

	// Options to configure how your job will stop if your data quality evaluation
	// fails.
	StopJobOnFailureOptions *DQStopJobOnFailureOptions

	noSmithyDocumentSerde
}

// Specifies your data quality evaluation criteria.
type EvaluateDataQualityMultiFrame struct {

	// The inputs of your data quality evaluation. The first input in this list is the
	// primary data source.
	//
	// This member is required.
	Inputs []string

	// The name of the data quality evaluation.
	//
	// This member is required.
	Name *string

	// The ruleset for your data quality evaluation.
	//
	// This member is required.
	Ruleset *string

	// The aliases of all data sources except primary.
	AdditionalDataSources map[string]string

	// Options to configure runtime behavior of the transform.
	AdditionalOptions map[string]string

	// Options to configure how your results are published.
	PublishingOptions *DQResultsPublishingOptions

	// Options to configure how your job will stop if your data quality evaluation
	// fails.
	StopJobOnFailureOptions *DQStopJobOnFailureOptions

	noSmithyDocumentSerde
}

// Evaluation metrics provide an estimate of the quality of your machine learning
// transform.
type EvaluationMetrics struct {

	// The type of machine learning transform.
	//
	// This member is required.
	TransformType TransformType

	// The evaluation metrics for the find matches algorithm.
	FindMatchesMetrics *FindMatchesMetrics

	noSmithyDocumentSerde
}

// Batch condition that must be met (specified number of events received or batch
// time window expired) before EventBridge event trigger fires.
type EventBatchingCondition struct {

	// Number of events that must be received from Amazon EventBridge before
	// EventBridge event trigger fires.
	//
	// This member is required.
	BatchSize *int32

	// Window of time in seconds after which EventBridge event trigger fires. Window
	// starts when first event is received.
	BatchWindow *int32

	noSmithyDocumentSerde
}

// An execution property of a job.
type ExecutionProperty struct {

	// The maximum number of concurrent runs allowed for the job. The default is 1. An
	// error is returned when this threshold is reached. The maximum value you can
	// specify is controlled by a service limit.
	MaxConcurrentRuns int32

	noSmithyDocumentSerde
}

// Specifies configuration properties for an exporting labels task run.
type ExportLabelsTaskRunProperties struct {

	// The Amazon Simple Storage Service (Amazon S3) path where you will export the
	// labels.
	OutputS3Path *string

	noSmithyDocumentSerde
}

// A database that points to an entity outside the Glue Data Catalog.
type FederatedDatabase struct {

	// The name of the connection to the external metastore.
	ConnectionName *string

	// A unique identifier for the federated database.
	Identifier *string

	noSmithyDocumentSerde
}

// A table that points to an entity outside the Glue Data Catalog.
type FederatedTable struct {

	// The name of the connection to the external metastore.
	ConnectionName *string

	// A unique identifier for the federated database.
	DatabaseIdentifier *string

	// A unique identifier for the federated table.
	Identifier *string

	noSmithyDocumentSerde
}

// Specifies a transform that locates records in the dataset that have missing
// values and adds a new field with a value determined by imputation. The input
// data set is used to train the machine learning model that determines what the
// missing value should be.
type FillMissingValues struct {

	// A JSON path to a variable in the data structure for the dataset that is imputed.
	//
	// This member is required.
	ImputedPath *string

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A JSON path to a variable in the data structure for the dataset that is filled.
	FilledPath *string

	noSmithyDocumentSerde
}

// Specifies a transform that splits a dataset into two, based on a filter
// condition.
type Filter struct {

	// Specifies a filter expression.
	//
	// This member is required.
	Filters []FilterExpression

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The operator used to filter rows by comparing the key value to a specified
	// value.
	//
	// This member is required.
	LogicalOperator FilterLogicalOperator

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Specifies a filter expression.
type FilterExpression struct {

	// The type of operation to perform in the expression.
	//
	// This member is required.
	Operation FilterOperation

	// A list of filter values.
	//
	// This member is required.
	Values []FilterValue

	// Whether the expression is to be negated.
	Negated *bool

	noSmithyDocumentSerde
}

// Represents a single entry in the list of values for a FilterExpression .
type FilterValue struct {

	// The type of filter value.
	//
	// This member is required.
	Type FilterValueType

	// The value to be associated.
	//
	// This member is required.
	Value []string

	noSmithyDocumentSerde
}

// The evaluation metrics for the find matches algorithm. The quality of your
// machine learning transform is measured by getting your transform to predict some
// matches and comparing the results to known matches from the same dataset. The
// quality metrics are based on a subset of your data, so they are not precise.
type FindMatchesMetrics struct {

	// The area under the precision/recall curve (AUPRC) is a single number measuring
	// the overall quality of the transform, that is independent of the choice made for
	// precision vs. recall. Higher values indicate that you have a more attractive
	// precision vs. recall tradeoff. For more information, see Precision and recall (https://en.wikipedia.org/wiki/Precision_and_recall)
	// in Wikipedia.
	AreaUnderPRCurve *float64

	// A list of ColumnImportance structures containing column importance metrics,
	// sorted in order of descending importance.
	ColumnImportances []ColumnImportance

	// The confusion matrix shows you what your transform is predicting accurately and
	// what types of errors it is making. For more information, see Confusion matrix (https://en.wikipedia.org/wiki/Confusion_matrix)
	// in Wikipedia.
	ConfusionMatrix *ConfusionMatrix

	// The maximum F1 metric indicates the transform's accuracy between 0 and 1, where
	// 1 is the best accuracy. For more information, see F1 score (https://en.wikipedia.org/wiki/F1_score)
	// in Wikipedia.
	F1 *float64

	// The precision metric indicates when often your transform is correct when it
	// predicts a match. Specifically, it measures how well the transform finds true
	// positives from the total true positives possible. For more information, see
	// Precision and recall (https://en.wikipedia.org/wiki/Precision_and_recall) in
	// Wikipedia.
	Precision *float64

	// The recall metric indicates that for an actual match, how often your transform
	// predicts the match. Specifically, it measures how well the transform finds true
	// positives from the total records in the source data. For more information, see
	// Precision and recall (https://en.wikipedia.org/wiki/Precision_and_recall) in
	// Wikipedia.
	Recall *float64

	noSmithyDocumentSerde
}

// The parameters to configure the find matches transform.
type FindMatchesParameters struct {

	// The value that is selected when tuning your transform for a balance between
	// accuracy and cost. A value of 0.5 means that the system balances accuracy and
	// cost concerns. A value of 1.0 means a bias purely for accuracy, which typically
	// results in a higher cost, sometimes substantially higher. A value of 0.0 means a
	// bias purely for cost, which results in a less accurate FindMatches transform,
	// sometimes with unacceptable accuracy. Accuracy measures how well the transform
	// finds true positives and true negatives. Increasing accuracy requires more
	// machine resources and cost. But it also results in increased recall. Cost
	// measures how many compute resources, and thus money, are consumed to run the
	// transform.
	AccuracyCostTradeoff *float64

	// The value to switch on or off to force the output to match the provided labels
	// from users. If the value is True , the find matches transform forces the output
	// to match the provided labels. The results override the normal conflation
	// results. If the value is False , the find matches transform does not ensure all
	// the labels provided are respected, and the results rely on the trained model.
	// Note that setting this value to true may increase the conflation execution time.
	EnforceProvidedLabels *bool

	// The value selected when tuning your transform for a balance between precision
	// and recall. A value of 0.5 means no preference; a value of 1.0 means a bias
	// purely for precision, and a value of 0.0 means a bias for recall. Because this
	// is a tradeoff, choosing values close to 1.0 means very low recall, and choosing
	// values close to 0.0 results in very low precision. The precision metric
	// indicates how often your model is correct when it predicts a match. The recall
	// metric indicates that for an actual match, how often your model predicts the
	// match.
	PrecisionRecallTradeoff *float64

	// The name of a column that uniquely identifies rows in the source table. Used to
	// help identify matching records.
	PrimaryKeyColumnName *string

	noSmithyDocumentSerde
}

// Specifies configuration properties for a Find Matches task run.
type FindMatchesTaskRunProperties struct {

	// The job ID for the Find Matches task run.
	JobId *string

	// The name assigned to the job for the Find Matches task run.
	JobName *string

	// The job run ID for the Find Matches task run.
	JobRunId *string

	noSmithyDocumentSerde
}

// Filters the connection definitions that are returned by the GetConnections API
// operation.
type GetConnectionsFilter struct {

	// The type of connections to return. Currently, SFTP is not supported.
	ConnectionType ConnectionType

	// A criteria string that must match the criteria recorded in the connection
	// definition for that connection definition to be returned.
	MatchCriteria []string

	noSmithyDocumentSerde
}

// A structure for returning a resource policy.
type GluePolicy struct {

	// The date and time at which the policy was created.
	CreateTime *time.Time

	// Contains the hash value associated with this policy.
	PolicyHash *string

	// Contains the requested policy document, in JSON format.
	PolicyInJson *string

	// The date and time at which the policy was last updated.
	UpdateTime *time.Time

	noSmithyDocumentSerde
}

// Specifies a user-defined schema when a schema cannot be determined by Glue.
type GlueSchema struct {

	// Specifies the column definitions that make up a Glue schema.
	Columns []GlueStudioSchemaColumn

	noSmithyDocumentSerde
}

// Specifies a single column in a Glue schema definition.
type GlueStudioSchemaColumn struct {

	// The name of the column in the Glue Studio schema.
	//
	// This member is required.
	Name *string

	// The hive type for this column in the Glue Studio schema.
	Type *string

	noSmithyDocumentSerde
}

// The database and table in the Glue Data Catalog that is used for input or
// output data.
type GlueTable struct {

	// A database name in the Glue Data Catalog.
	//
	// This member is required.
	DatabaseName *string

	// A table name in the Glue Data Catalog.
	//
	// This member is required.
	TableName *string

	// Additional options for the table. Currently there are two keys supported:
	//   - pushDownPredicate : to filter on partitions without having to list and read
	//   all the files in your dataset.
	//   - catalogPartitionPredicate : to use server-side partition pruning using
	//   partition indexes in the Glue Data Catalog.
	AdditionalOptions map[string]string

	// A unique identifier for the Glue Data Catalog.
	CatalogId *string

	// The name of the connection to the Glue Data Catalog.
	ConnectionName *string

	noSmithyDocumentSerde
}

// Specifies the data store in the governed Glue Data Catalog.
type GovernedCatalogSource struct {

	// The database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// The database table to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalOptions *S3SourceAdditionalOptions

	// Partitions satisfying this predicate are deleted. Files within the retention
	// period in these partitions are not deleted. Set to "" – empty by default.
	PartitionPredicate *string

	noSmithyDocumentSerde
}

// Specifies a data target that writes to Amazon S3 using the Glue Data Catalog.
type GovernedCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the governed catalog.
	SchemaChangePolicy *CatalogSchemaChangePolicy

	noSmithyDocumentSerde
}

// A classifier that uses grok patterns.
type GrokClassifier struct {

	// An identifier of the data format that the classifier matches, such as Twitter,
	// JSON, Omniture logs, and so on.
	//
	// This member is required.
	Classification *string

	// The grok pattern applied to a data store by this classifier. For more
	// information, see built-in patterns in Writing Custom Classifiers (https://docs.aws.amazon.com/glue/latest/dg/custom-classifier.html)
	// .
	//
	// This member is required.
	GrokPattern *string

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// The time that this classifier was registered.
	CreationTime *time.Time

	// Optional custom grok patterns defined by this classifier. For more information,
	// see custom patterns in Writing Custom Classifiers (https://docs.aws.amazon.com/glue/latest/dg/custom-classifier.html)
	// .
	CustomPatterns *string

	// The time that this classifier was last updated.
	LastUpdated *time.Time

	// The version of this classifier.
	Version int64

	noSmithyDocumentSerde
}

// Specifies an Apache Hudi data source.
type HudiTarget struct {

	// The name of the connection to use to connect to the Hudi target. If your Hudi
	// files are stored in buckets that require VPC authorization, you can set their
	// connection properties here.
	ConnectionName *string

	// A list of glob patterns used to exclude from the crawl. For more information,
	// see Catalog Tables with a Crawler (https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html)
	// .
	Exclusions []string

	// The maximum depth of Amazon S3 paths that the crawler can traverse to discover
	// the Hudi metadata folder in your Amazon S3 path. Used to limit the crawler run
	// time.
	MaximumTraversalDepth *int32

	// An array of Amazon S3 location strings for Hudi, each indicating the root
	// folder with which the metadata files for a Hudi table resides. The Hudi folder
	// may be located in a child folder of the root folder. The crawler will scan all
	// folders underneath a path for a Hudi folder.
	Paths []string

	noSmithyDocumentSerde
}

// A structure that defines an Apache Iceberg metadata table to create in the
// catalog.
type IcebergInput struct {

	// A required metadata operation. Can only be set to CREATE .
	//
	// This member is required.
	MetadataOperation MetadataOperation

	// The table version for the Iceberg table. Defaults to 2.
	Version *string

	noSmithyDocumentSerde
}

// Specifies an Apache Iceberg data source where Iceberg tables are stored in
// Amazon S3.
type IcebergTarget struct {

	// The name of the connection to use to connect to the Iceberg target.
	ConnectionName *string

	// A list of glob patterns used to exclude from the crawl. For more information,
	// see Catalog Tables with a Crawler (https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html)
	// .
	Exclusions []string

	// The maximum depth of Amazon S3 paths that the crawler can traverse to discover
	// the Iceberg metadata folder in your Amazon S3 path. Used to limit the crawler
	// run time.
	MaximumTraversalDepth *int32

	// One or more Amazon S3 paths that contains Iceberg metadata folders as
	// s3://bucket/prefix .
	Paths []string

	noSmithyDocumentSerde
}

// Specifies configuration properties for an importing labels task run.
type ImportLabelsTaskRunProperties struct {

	// The Amazon Simple Storage Service (Amazon S3) path from where you will import
	// the labels.
	InputS3Path *string

	// Indicates whether to overwrite your existing labels.
	Replace bool

	noSmithyDocumentSerde
}

// Additional connection options for the connector.
type JDBCConnectorOptions struct {

	// Custom data type mapping that builds a mapping from a JDBC data type to an Glue
	// data type. For example, the option "dataTypeMapping":{"FLOAT":"STRING"} maps
	// data fields of JDBC type FLOAT into the Java String type by calling the
	// ResultSet.getString() method of the driver, and uses it to build the Glue
	// record. The ResultSet object is implemented by each driver, so the behavior is
	// specific to the driver you use. Refer to the documentation for your JDBC driver
	// to understand how the driver performs the conversions.
	DataTypeMapping map[string]GlueRecordType

	// Extra condition clause to filter data from source. For example:
	// BillingCity='Mountain View' When using a query instead of a table name, you
	// should validate that the query works with the specified filterPredicate .
	FilterPredicate *string

	// The name of the job bookmark keys on which to sort.
	JobBookmarkKeys []string

	// Specifies an ascending or descending sort order.
	JobBookmarkKeysSortOrder *string

	// The minimum value of partitionColumn that is used to decide partition stride.
	LowerBound *int64

	// The number of partitions. This value, along with lowerBound (inclusive) and
	// upperBound (exclusive), form partition strides for generated WHERE clause
	// expressions that are used to split the partitionColumn .
	NumPartitions *int64

	// The name of an integer column that is used for partitioning. This option works
	// only when it's included with lowerBound , upperBound , and numPartitions . This
	// option works the same way as in the Spark SQL JDBC reader.
	PartitionColumn *string

	// The maximum value of partitionColumn that is used to decide partition stride.
	UpperBound *int64

	noSmithyDocumentSerde
}

// Specifies a connector to a JDBC data source.
type JDBCConnectorSource struct {

	// The name of the connection that is associated with the connector.
	//
	// This member is required.
	ConnectionName *string

	// The type of connection, such as marketplace.jdbc or custom.jdbc, designating a
	// connection to a JDBC data store.
	//
	// This member is required.
	ConnectionType *string

	// The name of a connector that assists with accessing the data store in Glue
	// Studio.
	//
	// This member is required.
	ConnectorName *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// Additional connection options for the connector.
	AdditionalOptions *JDBCConnectorOptions

	// The name of the table in the data source.
	ConnectionTable *string

	// Specifies the data schema for the custom JDBC source.
	OutputSchemas []GlueSchema

	// The table or SQL query to get the data from. You can specify either
	// ConnectionTable or query , but not both.
	Query *string

	noSmithyDocumentSerde
}

// Specifies a data target that writes to Amazon S3 in Apache Parquet columnar
// storage.
type JDBCConnectorTarget struct {

	// The name of the connection that is associated with the connector.
	//
	// This member is required.
	ConnectionName *string

	// The name of the table in the data target.
	//
	// This member is required.
	ConnectionTable *string

	// The type of connection, such as marketplace.jdbc or custom.jdbc, designating a
	// connection to a JDBC data target.
	//
	// This member is required.
	ConnectionType *string

	// The name of a connector that will be used.
	//
	// This member is required.
	ConnectorName *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// Additional connection options for the connector.
	AdditionalOptions map[string]string

	// Specifies the data schema for the JDBC target.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a JDBC data store to crawl.
type JdbcTarget struct {

	// The name of the connection to use to connect to the JDBC target.
	ConnectionName *string

	// Specify a value of RAWTYPES or COMMENTS to enable additional metadata in table
	// responses. RAWTYPES provides the native-level datatype. COMMENTS provides
	// comments associated with a column or table in the database. If you do not need
	// additional metadata, keep the field empty.
	EnableAdditionalMetadata []JdbcMetadataEntry

	// A list of glob patterns used to exclude from the crawl. For more information,
	// see Catalog Tables with a Crawler (https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html)
	// .
	Exclusions []string

	// The path of the JDBC target.
	Path *string

	noSmithyDocumentSerde
}

// Specifies a job definition.
type Job struct {

	// This field is deprecated. Use MaxCapacity instead. The number of Glue data
	// processing units (DPUs) allocated to runs of this job. You can allocate a
	// minimum of 2 DPUs; 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 (https://aws.amazon.com/glue/pricing/) .
	//
	// Deprecated: This property is deprecated, use MaxCapacity instead.
	AllocatedCapacity int32

	// The representation of a directed acyclic graph on which both the Glue Studio
	// visual component and Glue Studio code generation is based.
	CodeGenConfigurationNodes map[string]CodeGenConfigurationNode

	// The JobCommand that runs this job.
	Command *JobCommand

	// The connections used for this job.
	Connections *ConnectionsList

	// The time and date that this job definition was created.
	CreatedOn *time.Time

	// The default arguments for every run of this job, specified as name-value pairs.
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html)
	// in the developer guide.
	DefaultArguments map[string]string

	// A description of the job.
	Description *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.
	ExecutionClass ExecutionClass

	// An ExecutionProperty specifying the maximum number of concurrent runs allowed
	// for this job.
	ExecutionProperty *ExecutionProperty

	// 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 (https://docs.aws.amazon.com/glue/latest/dg/add-job.html)
	// in the developer guide. Jobs that are created without specifying a Glue version
	// default to Glue 0.9.
	GlueVersion *string

	// The last point in time when this job definition was modified.
	LastModifiedOn *time.Time

	// This field is reserved for future use.
	LogUri *string

	// 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 (https://aws.amazon.com/glue/pricing/) . For Glue version 2.0 or
	// later 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.
	MaxCapacity *float64

	// The maximum number of times to retry this job after a JobRun fails.
	MaxRetries int32

	// The name you assign to this job definition.
	Name *string

	// Arguments for this job that are not overridden when providing job arguments in
	// a job run, specified as name-value pairs.
	NonOverridableArguments map[string]string

	// Specifies configuration properties of a job notification.
	NotificationProperty *NotificationProperty

	// The number of workers of a defined workerType that are allocated when a job
	// runs.
	NumberOfWorkers *int32

	// The name or Amazon Resource Name (ARN) of the IAM role associated with this job.
	Role *string

	// The name of the SecurityConfiguration structure to be used with this job.
	SecurityConfiguration *string

	// The details for a source control configuration for a job, allowing
	// synchronization of job artifacts to or from a remote repository.
	SourceControlDetails *SourceControlDetails

	// The job 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).
	Timeout *int32

	// 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.
	WorkerType WorkerType

	noSmithyDocumentSerde
}

// Defines a point that a job can resume processing.
type JobBookmarkEntry struct {

	// The attempt ID number.
	Attempt int32

	// The bookmark itself.
	JobBookmark *string

	// The name of the job in question.
	JobName *string

	// The unique run identifier associated with the previous job run.
	PreviousRunId *string

	// The run ID number.
	Run int32

	// The run ID number.
	RunId *string

	// The version of the job.
	Version int32

	noSmithyDocumentSerde
}

// Specifies how job bookmark data should be encrypted.
type JobBookmarksEncryption struct {

	// The encryption mode to use for job bookmarks data.
	JobBookmarksEncryptionMode JobBookmarksEncryptionMode

	// The Amazon Resource Name (ARN) of the KMS key to be used to encrypt the data.
	KmsKeyArn *string

	noSmithyDocumentSerde
}

// Specifies code that runs when a job is run.
type JobCommand struct {

	// The name of the job command. For an Apache Spark ETL job, this must be glueetl .
	// For a Python shell job, it must be pythonshell . For an Apache Spark streaming
	// ETL job, this must be gluestreaming . For a Ray job, this must be glueray .
	Name *string

	// The Python version being used to run a Python shell job. Allowed values are 2
	// or 3.
	PythonVersion *string

	// In Ray jobs, Runtime is used to specify the versions of Ray, Python and
	// additional libraries available in your environment. This field is not used in
	// other job types. For supported runtime environment values, see Working with Ray
	// jobs (https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-runtimes.html)
	// in the Glue Developer Guide.
	Runtime *string

	// Specifies the Amazon Simple Storage Service (Amazon S3) path to a script that
	// runs a job.
	ScriptLocation *string

	noSmithyDocumentSerde
}

// The details of a Job node present in the workflow.
type JobNodeDetails struct {

	// The information for the job runs represented by the job node.
	JobRuns []JobRun

	noSmithyDocumentSerde
}

// Contains information about a job run.
type JobRun struct {

	// 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 (https://aws.amazon.com/glue/pricing/) .
	//
	// Deprecated: This property is deprecated, use MaxCapacity instead.
	AllocatedCapacity int32

	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html)
	// in the developer guide.
	Arguments map[string]string

	// The number of the attempt to run this job.
	Attempt int32

	// The date and time that this job run completed.
	CompletedOn *time.Time

	// This field populates only for Auto Scaling job runs, 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 .
	DPUSeconds *float64

	// An error message associated with this job run.
	ErrorMessage *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.
	ExecutionClass ExecutionClass

	// The amount of time (in seconds) that the job run consumed resources.
	ExecutionTime int32

	// 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 (https://docs.aws.amazon.com/glue/latest/dg/add-job.html)
	// in the developer guide. Jobs that are created without specifying a Glue version
	// default to Glue 0.9.
	GlueVersion *string

	// The ID of this job run.
	Id *string

	// The name of the job definition being used in this run.
	JobName *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 (https://docs.aws.amazon.com/glue/latest/dg/job-run-statuses.html)
	// .
	JobRunState JobRunState

	// The last time that this job run was modified.
	LastModifiedOn *time.Time

	// 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.
	LogGroupName *string

	// 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 (https://aws.amazon.com/glue/pricing/) . 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.
	MaxCapacity *float64

	// Specifies configuration properties of a job run notification.
	NotificationProperty *NotificationProperty

	// The number of workers of a defined workerType that are allocated when a job
	// runs.
	NumberOfWorkers *int32

	// A list of predecessors to this job run.
	PredecessorRuns []Predecessor

	// The ID of the previous run of this job. For example, the JobRunId specified in
	// the StartJobRun action.
	PreviousRunId *string

	// The name of the SecurityConfiguration structure to be used with this job run.
	SecurityConfiguration *string

	// The date and time at which this job run was started.
	StartedOn *time.Time

	// 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. Streaming jobs do not have a
	// timeout. The default for non-streaming jobs is 2,880 minutes (48 hours).
	Timeout *int32

	// The name of the trigger that started this job run.
	TriggerName *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.
	WorkerType WorkerType

	noSmithyDocumentSerde
}

// Specifies information used to update an existing job definition. The previous
// job definition is completely overwritten by this information.
type JobUpdate struct {

	// This field is deprecated. Use MaxCapacity instead. The number of Glue data
	// processing units (DPUs) to allocate to this job. You can allocate a minimum of 2
	// DPUs; 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 (https://aws.amazon.com/glue/pricing/) .
	//
	// Deprecated: This property is deprecated, use MaxCapacity instead.
	AllocatedCapacity int32

	// The representation of a directed acyclic graph on which both the Glue Studio
	// visual component and Glue Studio code generation is based.
	CodeGenConfigurationNodes map[string]CodeGenConfigurationNode

	// The JobCommand that runs this job (required).
	Command *JobCommand

	// The connections used for this job.
	Connections *ConnectionsList

	// The default arguments for every run of this job, specified as name-value pairs.
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-python-calling.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-glue-arguments.html)
	// 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 (https://docs.aws.amazon.com/glue/latest/dg/author-job-ray-job-parameters.html)
	// in the developer guide.
	DefaultArguments map[string]string

	// Description of the job being defined.
	Description *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.
	ExecutionClass ExecutionClass

	// An ExecutionProperty specifying the maximum number of concurrent runs allowed
	// for this job.
	ExecutionProperty *ExecutionProperty

	// 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 (https://docs.aws.amazon.com/glue/latest/dg/add-job.html)
	// in the developer guide. Jobs that are created without specifying a Glue version
	// default to Glue 0.9.
	GlueVersion *string

	// This field is reserved for future use.
	LogUri *string

	// 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 (https://aws.amazon.com/glue/pricing/) . 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.
	MaxCapacity *float64

	// The maximum number of times to retry this job if it fails.
	MaxRetries int32

	// Arguments for this job that are not overridden when providing job arguments in
	// a job run, specified as name-value pairs.
	NonOverridableArguments map[string]string

	// Specifies the configuration properties of a job notification.
	NotificationProperty *NotificationProperty

	// The number of workers of a defined workerType that are allocated when a job
	// runs.
	NumberOfWorkers *int32

	// The name or Amazon Resource Name (ARN) of the IAM role associated with this job
	// (required).
	Role *string

	// The name of the SecurityConfiguration structure to be used with this job.
	SecurityConfiguration *string

	// The details for a source control configuration for a job, allowing
	// synchronization of job artifacts to or from a remote repository.
	SourceControlDetails *SourceControlDetails

	// The job 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).
	Timeout *int32

	// 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.
	WorkerType WorkerType

	noSmithyDocumentSerde
}

// Specifies a transform that joins two datasets into one dataset using a
// comparison phrase on the specified data property keys. You can use inner, outer,
// left, right, left semi, and left anti joins.
type Join struct {

	// A list of the two columns to be joined.
	//
	// This member is required.
	Columns []JoinColumn

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// Specifies the type of join to be performed on the datasets.
	//
	// This member is required.
	JoinType JoinType

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Specifies a column to be joined.
type JoinColumn struct {

	// The column to be joined.
	//
	// This member is required.
	From *string

	// The key of the column to be joined.
	//
	// This member is required.
	Keys [][]string

	noSmithyDocumentSerde
}

// A classifier for JSON content.
type JsonClassifier struct {

	// A JsonPath string defining the JSON data for the classifier to classify. Glue
	// supports a subset of JsonPath, as described in Writing JsonPath Custom
	// Classifiers (https://docs.aws.amazon.com/glue/latest/dg/custom-classifier.html#custom-classifier-json)
	// .
	//
	// This member is required.
	JsonPath *string

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// The time that this classifier was registered.
	CreationTime *time.Time

	// The time that this classifier was last updated.
	LastUpdated *time.Time

	// The version of this classifier.
	Version int64

	noSmithyDocumentSerde
}

// Additional options for streaming.
type KafkaStreamingSourceOptions struct {

	// When this option is set to 'true', the data output will contain an additional
	// column named "__src_timestamp" that indicates the time when the corresponding
	// record received by the topic. The default value is 'false'. This option is
	// supported in Glue version 4.0 or later.
	AddRecordTimestamp *string

	// The specific TopicPartitions to consume. You must specify at least one of
	// "topicName" , "assign" or "subscribePattern" .
	Assign *string

	// A list of bootstrap server URLs, for example, as
	// b-1.vpc-test-2.o4q88o.c6.kafka.us-east-1.amazonaws.com:9094 . This option must
	// be specified in the API call or defined in the table metadata in the Data
	// Catalog.
	BootstrapServers *string

	// An optional classification.
	Classification *string

	// The name of the connection.
	ConnectionName *string

	// Specifies the delimiter character.
	Delimiter *string

	// When this option is set to 'true', for each batch, it will emit the metrics for
	// the duration between the oldest record received by the topic and the time it
	// arrives in Glue to CloudWatch. The metric's name is
	// "glue.driver.streaming.maxConsumerLagInMs". The default value is 'false'. This
	// option is supported in Glue version 4.0 or later.
	EmitConsumerLagMetrics *string

	// The end point when a batch query is ended. Possible values are either "latest"
	// or a JSON string that specifies an ending offset for each TopicPartition .
	EndingOffsets *string

	// Whether to include the Kafka headers. When the option is set to "true", the
	// data output will contain an additional column named
	// "glue_streaming_kafka_headers" with type Array[Struct(key: String, value:
	// String)] . The default value is "false". This option is available in Glue
	// version 3.0 or later only.
	IncludeHeaders *bool

	// The rate limit on the maximum number of offsets that are processed per trigger
	// interval. The specified total number of offsets is proportionally split across
	// topicPartitions of different volumes. The default value is null, which means
	// that the consumer reads all offsets until the known latest offset.
	MaxOffsetsPerTrigger *int64

	// The desired minimum number of partitions to read from Kafka. The default value
	// is null, which means that the number of spark partitions is equal to the number
	// of Kafka partitions.
	MinPartitions *int32

	// The number of times to retry before failing to fetch Kafka offsets. The default
	// value is 3 .
	NumRetries *int32

	// The timeout in milliseconds to poll data from Kafka in Spark job executors. The
	// default value is 512 .
	PollTimeoutMs *int64

	// The time in milliseconds to wait before retrying to fetch Kafka offsets. The
	// default value is 10 .
	RetryIntervalMs *int64

	// The protocol used to communicate with brokers. The possible values are "SSL" or
	// "PLAINTEXT" .
	SecurityProtocol *string

	// The starting position in the Kafka topic to read data from. The possible values
	// are "earliest" or "latest" . The default value is "latest" .
	StartingOffsets *string

	// The timestamp of the record in the Kafka topic to start reading data from. The
	// possible values are a timestamp string in UTC format of the pattern
	// yyyy-mm-ddTHH:MM:SSZ (where Z represents a UTC timezone offset with a +/-. For
	// example: "2023-04-04T08:00:00+08:00"). Only one of StartingTimestamp or
	// StartingOffsets must be set.
	StartingTimestamp *time.Time

	// A Java regex string that identifies the topic list to subscribe to. You must
	// specify at least one of "topicName" , "assign" or "subscribePattern" .
	SubscribePattern *string

	// The topic name as specified in Apache Kafka. You must specify at least one of
	// "topicName" , "assign" or "subscribePattern" .
	TopicName *string

	noSmithyDocumentSerde
}

// A partition key pair consisting of a name and a type.
type KeySchemaElement struct {

	// The name of a partition key.
	//
	// This member is required.
	Name *string

	// The type of a partition key.
	//
	// This member is required.
	Type *string

	noSmithyDocumentSerde
}

// Additional options for the Amazon Kinesis streaming data source.
type KinesisStreamingSourceOptions struct {

	// Adds a time delay between two consecutive getRecords operations. The default
	// value is "False" . This option is only configurable for Glue version 2.0 and
	// above.
	AddIdleTimeBetweenReads *bool

	// When this option is set to 'true', the data output will contain an additional
	// column named "__src_timestamp" that indicates the time when the corresponding
	// record received by the stream. The default value is 'false'. This option is
	// supported in Glue version 4.0 or later.
	AddRecordTimestamp *string

	// Avoids creating an empty microbatch job by checking for unread data in the
	// Kinesis data stream before the batch is started. The default value is "False" .
	AvoidEmptyBatches *bool

	// An optional classification.
	Classification *string

	// Specifies the delimiter character.
	Delimiter *string

	// The minimum time interval between two ListShards API calls for your script to
	// consider resharding. The default value is 1s .
	DescribeShardInterval *int64

	// When this option is set to 'true', for each batch, it will emit the metrics for
	// the duration between the oldest record received by the stream and the time it
	// arrives in Glue to CloudWatch. The metric's name is
	// "glue.driver.streaming.maxConsumerLagInMs". The default value is 'false'. This
	// option is supported in Glue version 4.0 or later.
	EmitConsumerLagMetrics *string

	// The URL of the Kinesis endpoint.
	EndpointUrl *string

	// The minimum time delay between two consecutive getRecords operations, specified
	// in ms. The default value is 1000 . This option is only configurable for Glue
	// version 2.0 and above.
	IdleTimeBetweenReadsInMs *int64

	// The maximum number of records to fetch per shard in the Kinesis data stream.
	// The default value is 100000 .
	MaxFetchRecordsPerShard *int64

	// The maximum time spent in the job executor to fetch a record from the Kinesis
	// data stream per shard, specified in milliseconds (ms). The default value is 1000
	// .
	MaxFetchTimeInMs *int64

	// The maximum number of records to fetch from the Kinesis data stream in each
	// getRecords operation. The default value is 10000 .
	MaxRecordPerRead *int64

	// The maximum cool-off time period (specified in ms) between two retries of a
	// Kinesis Data Streams API call. The default value is 10000 .
	MaxRetryIntervalMs *int64

	// The maximum number of retries for Kinesis Data Streams API requests. The
	// default value is 3 .
	NumRetries *int32

	// The cool-off time period (specified in ms) before retrying the Kinesis Data
	// Streams API call. The default value is 1000 .
	RetryIntervalMs *int64

	// The Amazon Resource Name (ARN) of the role to assume using AWS Security Token
	// Service (AWS STS). This role must have permissions for describe or read record
	// operations for the Kinesis data stream. You must use this parameter when
	// accessing a data stream in a different account. Used in conjunction with
	// "awsSTSSessionName" .
	RoleArn *string

	// An identifier for the session assuming the role using AWS STS. You must use
	// this parameter when accessing a data stream in a different account. Used in
	// conjunction with "awsSTSRoleARN" .
	RoleSessionName *string

	// The starting position in the Kinesis data stream to read data from. The
	// possible values are "latest" , "trim_horizon" , "earliest" , or a timestamp
	// string in UTC format in the pattern yyyy-mm-ddTHH:MM:SSZ (where Z represents a
	// UTC timezone offset with a +/-. For example: "2023-04-04T08:00:00-04:00"). The
	// default value is "latest" . Note: Using a value that is a timestamp string in
	// UTC format for "startingPosition" is supported only for Glue version 4.0 or
	// later.
	StartingPosition StartingPosition

	// The timestamp of the record in the Kinesis data stream to start reading data
	// from. The possible values are a timestamp string in UTC format of the pattern
	// yyyy-mm-ddTHH:MM:SSZ (where Z represents a UTC timezone offset with a +/-. For
	// example: "2023-04-04T08:00:00+08:00").
	StartingTimestamp *time.Time

	// The Amazon Resource Name (ARN) of the Kinesis data stream.
	StreamArn *string

	// The name of the Kinesis data stream.
	StreamName *string

	noSmithyDocumentSerde
}

// Specifies configuration properties for a labeling set generation task run.
type LabelingSetGenerationTaskRunProperties struct {

	// The Amazon Simple Storage Service (Amazon S3) path where you will generate the
	// labeling set.
	OutputS3Path *string

	noSmithyDocumentSerde
}

// Specifies Lake Formation configuration settings for the crawler.
type LakeFormationConfiguration struct {

	// Required for cross account crawls. For same account crawls as the target data,
	// this can be left as null.
	AccountId *string

	// Specifies whether to use Lake Formation credentials for the crawler instead of
	// the IAM role credentials.
	UseLakeFormationCredentials *bool

	noSmithyDocumentSerde
}

// When there are multiple versions of a blueprint and the latest version has some
// errors, this attribute indicates the last successful blueprint definition that
// is available with the service.
type LastActiveDefinition struct {

	// Specifies a path in Amazon S3 where the blueprint is published by the Glue
	// developer.
	BlueprintLocation *string

	// Specifies a path in Amazon S3 where the blueprint is copied when you create or
	// update the blueprint.
	BlueprintServiceLocation *string

	// The description of the blueprint.
	Description *string

	// The date and time the blueprint was last modified.
	LastModifiedOn *time.Time

	// A JSON string specifying the parameters for the blueprint.
	ParameterSpec *string

	noSmithyDocumentSerde
}

// Status and error information about the most recent crawl.
type LastCrawlInfo struct {

	// If an error occurred, the error information about the last crawl.
	ErrorMessage *string

	// The log group for the last crawl.
	LogGroup *string

	// The log stream for the last crawl.
	LogStream *string

	// The prefix for a message about this crawl.
	MessagePrefix *string

	// The time at which the crawl started.
	StartTime *time.Time

	// Status of the last crawl.
	Status LastCrawlStatus

	noSmithyDocumentSerde
}

// Specifies data lineage configuration settings for the crawler.
type LineageConfiguration struct {

	// Specifies whether data lineage is enabled for the crawler. Valid values are:
	//   - ENABLE: enables data lineage for the crawler
	//   - DISABLE: disables data lineage for the crawler
	CrawlerLineageSettings CrawlerLineageSettings

	noSmithyDocumentSerde
}

// The location of resources.
type Location struct {

	// An Amazon DynamoDB table location.
	DynamoDB []CodeGenNodeArg

	// A JDBC location.
	Jdbc []CodeGenNodeArg

	// An Amazon Simple Storage Service (Amazon S3) location.
	S3 []CodeGenNodeArg

	noSmithyDocumentSerde
}

// Defines column statistics supported for integer data columns.
type LongColumnStatisticsData struct {

	// The number of distinct values in a column.
	//
	// This member is required.
	NumberOfDistinctValues int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	// The highest value in the column.
	MaximumValue int64

	// The lowest value in the column.
	MinimumValue int64

	noSmithyDocumentSerde
}

// Specifies the mapping of data property keys.
type Mapping struct {

	// Only applicable to nested data structures. If you want to change the parent
	// structure, but also one of its children, you can fill out this data strucutre.
	// It is also Mapping , but its FromPath will be the parent's FromPath plus the
	// FromPath from this structure. For the children part, suppose you have the
	// structure: { "FromPath": "OuterStructure", "ToKey": "OuterStructure", "ToType":
	// "Struct", "Dropped": false, "Chidlren": [{ "FromPath": "inner", "ToKey":
	// "inner", "ToType": "Double", "Dropped": false, }] } You can specify a Mapping
	// that looks like: { "FromPath": "OuterStructure", "ToKey": "OuterStructure",
	// "ToType": "Struct", "Dropped": false, "Chidlren": [{ "FromPath": "inner",
	// "ToKey": "inner", "ToType": "Double", "Dropped": false, }] }
	Children []Mapping

	// If true, then the column is removed.
	Dropped *bool

	// The table or column to be modified.
	FromPath []string

	// The type of the data to be modified.
	FromType *string

	// After the apply mapping, what the name of the column should be. Can be the same
	// as FromPath .
	ToKey *string

	// The data type that the data is to be modified to.
	ToType *string

	noSmithyDocumentSerde
}

// Defines a mapping.
type MappingEntry struct {

	// The source path.
	SourcePath *string

	// The name of the source table.
	SourceTable *string

	// The source type.
	SourceType *string

	// The target path.
	TargetPath *string

	// The target table.
	TargetTable *string

	// The target type.
	TargetType *string

	noSmithyDocumentSerde
}

// Specifies a transform that merges a DynamicFrame with a staging DynamicFrame
// based on the specified primary keys to identify records. Duplicate records
// (records with the same primary keys) are not de-duplicated.
type Merge struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// The list of primary key fields to match records from the source and staging
	// dynamic frames.
	//
	// This member is required.
	PrimaryKeys [][]string

	// The source DynamicFrame that will be merged with a staging DynamicFrame .
	//
	// This member is required.
	Source *string

	noSmithyDocumentSerde
}

// A structure containing metadata information for a schema version.
type MetadataInfo struct {

	// The time at which the entry was created.
	CreatedTime *string

	// The metadata key’s corresponding value.
	MetadataValue *string

	// Other metadata belonging to the same metadata key.
	OtherMetadataValueList []OtherMetadataValueListItem

	noSmithyDocumentSerde
}

// A structure containing a key value pair for metadata.
type MetadataKeyValuePair struct {

	// A metadata key.
	MetadataKey *string

	// A metadata key’s corresponding value.
	MetadataValue *string

	noSmithyDocumentSerde
}

// Describes the metric based observation generated based on evaluated data
// quality metrics.
type MetricBasedObservation struct {

	// The name of the data quality metric used for generating the observation.
	MetricName *string

	// An object of type DataQualityMetricValues representing the analysis of the data
	// quality metric value.
	MetricValues *DataQualityMetricValues

	// A list of new data quality rules generated as part of the observation based on
	// the data quality metric value.
	NewRules []string

	noSmithyDocumentSerde
}

// Specifies a Microsoft SQL server data source in the Glue Data Catalog.
type MicrosoftSQLServerCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies a target that uses Microsoft SQL.
type MicrosoftSQLServerCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// A structure for a machine learning transform.
type MLTransform struct {

	// A timestamp. The time and date that this machine learning transform was created.
	CreatedOn *time.Time

	// A user-defined, long-form description text for the machine learning transform.
	// Descriptions are not guaranteed to be unique and can be changed at any time.
	Description *string

	// An EvaluationMetrics object. Evaluation metrics provide an estimate of the
	// quality of your machine learning transform.
	EvaluationMetrics *EvaluationMetrics

	// This value determines which version of Glue this machine learning transform is
	// compatible with. Glue 1.0 is recommended for most customers. If the value is not
	// set, the Glue compatibility defaults to Glue 0.9. For more information, see
	// Glue Versions (https://docs.aws.amazon.com/glue/latest/dg/release-notes.html#release-notes-versions)
	// in the developer guide.
	GlueVersion *string

	// A list of Glue table definitions used by the transform.
	InputRecordTables []GlueTable

	// A count identifier for the labeling files generated by Glue for this transform.
	// As you create a better transform, you can iteratively download, label, and
	// upload the labeling file.
	LabelCount int32

	// A timestamp. The last point in time when this machine learning transform was
	// modified.
	LastModifiedOn *time.Time

	// The number of Glue data processing units (DPUs) that are allocated to task runs
	// for this transform. You can allocate from 2 to 100 DPUs; 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 (http://aws.amazon.com/glue/pricing/) . MaxCapacity is a mutually
	// exclusive option with NumberOfWorkers and WorkerType .
	//   - If either NumberOfWorkers or WorkerType is set, then MaxCapacity cannot be
	//   set.
	//   - If MaxCapacity is set then neither NumberOfWorkers or WorkerType can be set.
	//   - If WorkerType is set, then NumberOfWorkers is required (and vice versa).
	//   - MaxCapacity and NumberOfWorkers must both be at least 1.
	// When the WorkerType field is set to a value other than Standard , the
	// MaxCapacity field is set automatically and becomes read-only.
	MaxCapacity *float64

	// The maximum number of times to retry after an MLTaskRun of the machine learning
	// transform fails.
	MaxRetries *int32

	// A user-defined name for the machine learning transform. Names are not
	// guaranteed unique and can be changed at any time.
	Name *string

	// The number of workers of a defined workerType that are allocated when a task of
	// the transform runs. If WorkerType is set, then NumberOfWorkers is required (and
	// vice versa).
	NumberOfWorkers *int32

	// A TransformParameters object. You can use parameters to tune (customize) the
	// behavior of the machine learning transform by specifying what data it learns
	// from and your preference on various tradeoffs (such as precious vs. recall, or
	// accuracy vs. cost).
	Parameters *TransformParameters

	// The name or Amazon Resource Name (ARN) of the IAM role with the required
	// permissions. The required permissions include both Glue service role permissions
	// to Glue resources, and Amazon S3 permissions required by the transform.
	//   - This role needs Glue service role permissions to allow access to resources
	//   in Glue. See Attach a Policy to IAM Users That Access Glue (https://docs.aws.amazon.com/glue/latest/dg/attach-policy-iam-user.html)
	//   .
	//   - This role needs permission to your Amazon Simple Storage Service (Amazon
	//   S3) sources, targets, temporary directory, scripts, and any libraries used by
	//   the task run for this transform.
	Role *string

	// A map of key-value pairs representing the columns and data types that this
	// transform can run against. Has an upper bound of 100 columns.
	Schema []SchemaColumn

	// The current status of the machine learning transform.
	Status TransformStatusType

	// The timeout in minutes of the machine learning transform.
	Timeout *int32

	// The encryption-at-rest settings of the transform that apply to accessing user
	// data. Machine learning transforms can access user data encrypted in Amazon S3
	// using KMS.
	TransformEncryption *TransformEncryption

	// The unique transform ID that is generated for the machine learning transform.
	// The ID is guaranteed to be unique and does not change.
	TransformId *string

	// The type of predefined worker that is allocated when a task of this transform
	// runs. Accepts a value of Standard, G.1X, or G.2X.
	//   - For the Standard worker type, each worker provides 4 vCPU, 16 GB of memory
	//   and a 50GB disk, and 2 executors per worker.
	//   - For the G.1X worker type, each worker provides 4 vCPU, 16 GB of memory and a
	//   64GB disk, and 1 executor per worker.
	//   - For the G.2X worker type, each worker provides 8 vCPU, 32 GB of memory and a
	//   128GB disk, and 1 executor per worker.
	// MaxCapacity is a mutually exclusive option with NumberOfWorkers and WorkerType .
	//   - If either NumberOfWorkers or WorkerType is set, then MaxCapacity cannot be
	//   set.
	//   - If MaxCapacity is set then neither NumberOfWorkers or WorkerType can be set.
	//   - If WorkerType is set, then NumberOfWorkers is required (and vice versa).
	//   - MaxCapacity and NumberOfWorkers must both be at least 1.
	WorkerType WorkerType

	noSmithyDocumentSerde
}

// The encryption-at-rest settings of the transform that apply to accessing user
// data.
type MLUserDataEncryption struct {

	// The encryption mode applied to user data. Valid values are:
	//   - DISABLED: encryption is disabled
	//   - SSEKMS: use of server-side encryption with Key Management Service (SSE-KMS)
	//   for user data stored in Amazon S3.
	//
	// This member is required.
	MlUserDataEncryptionMode MLUserDataEncryptionModeString

	// The ID for the customer-provided KMS key.
	KmsKeyId *string

	noSmithyDocumentSerde
}

// Specifies an Amazon DocumentDB or MongoDB data store to crawl.
type MongoDBTarget struct {

	// The name of the connection to use to connect to the Amazon DocumentDB or
	// MongoDB target.
	ConnectionName *string

	// The path of the Amazon DocumentDB or MongoDB target (database/collection).
	Path *string

	// Indicates whether to scan all the records, or to sample rows from the table.
	// Scanning all the records can take a long time when the table is not a high
	// throughput table. A value of true means to scan all records, while a value of
	// false means to sample the records. If no value is specified, the value defaults
	// to true .
	ScanAll *bool

	noSmithyDocumentSerde
}

// Specifies a MySQL data source in the Glue Data Catalog.
type MySQLCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies a target that uses MySQL.
type MySQLCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// A node represents an Glue component (trigger, crawler, or job) on a workflow
// graph.
type Node struct {

	// Details of the crawler when the node represents a crawler.
	CrawlerDetails *CrawlerNodeDetails

	// Details of the Job when the node represents a Job.
	JobDetails *JobNodeDetails

	// The name of the Glue component represented by the node.
	Name *string

	// Details of the Trigger when the node represents a Trigger.
	TriggerDetails *TriggerNodeDetails

	// The type of Glue component represented by the node.
	Type NodeType

	// The unique Id assigned to the node within the workflow.
	UniqueId *string

	noSmithyDocumentSerde
}

// Specifies configuration properties of a notification.
type NotificationProperty struct {

	// After a job run starts, the number of minutes to wait before sending a job run
	// delay notification.
	NotifyDelayAfter *int32

	noSmithyDocumentSerde
}

// Represents whether certain values are recognized as null values for removal.
type NullCheckBoxList struct {

	// Specifies that an empty string is considered as a null value.
	IsEmpty *bool

	// Specifies that an integer value of -1 is considered as a null value.
	IsNegOne *bool

	// Specifies that a value spelling out the word 'null' is considered as a null
	// value.
	IsNullString *bool

	noSmithyDocumentSerde
}

// Represents a custom null value such as a zeros or other value being used as a
// null placeholder unique to the dataset.
type NullValueField struct {

	// The datatype of the value.
	//
	// This member is required.
	Datatype *Datatype

	// The value of the null placeholder.
	//
	// This member is required.
	Value *string

	noSmithyDocumentSerde
}

// A structure representing an open format table.
type OpenTableFormatInput struct {

	// Specifies an IcebergInput structure that defines an Apache Iceberg metadata
	// table.
	IcebergInput *IcebergInput

	noSmithyDocumentSerde
}

// Specifies an option value.
type Option struct {

	// Specifies the description of the option.
	Description *string

	// Specifies the label of the option.
	Label *string

	// Specifies the value of the option.
	Value *string

	noSmithyDocumentSerde
}

// Specifies an Oracle data source in the Glue Data Catalog.
type OracleSQLCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies a target that uses Oracle SQL.
type OracleSQLCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies the sort order of a sorted column.
type Order struct {

	// The name of the column.
	//
	// This member is required.
	Column *string

	// Indicates that the column is sorted in ascending order ( == 1 ), or in
	// descending order ( ==0 ).
	//
	// This member is required.
	SortOrder int32

	noSmithyDocumentSerde
}

// A structure containing other metadata for a schema version belonging to the
// same metadata key.
type OtherMetadataValueListItem struct {

	// The time at which the entry was created.
	CreatedTime *string

	// The metadata key’s corresponding value for the other metadata belonging to the
	// same metadata key.
	MetadataValue *string

	noSmithyDocumentSerde
}

// Represents a slice of table data.
type Partition struct {

	// The ID of the Data Catalog in which the partition resides.
	CatalogId *string

	// The time at which the partition was created.
	CreationTime *time.Time

	// The name of the catalog database in which to create the partition.
	DatabaseName *string

	// The last time at which the partition was accessed.
	LastAccessTime *time.Time

	// The last time at which column statistics were computed for this partition.
	LastAnalyzedTime *time.Time

	// These key-value pairs define partition parameters.
	Parameters map[string]string

	// Provides information about the physical location where the partition is stored.
	StorageDescriptor *StorageDescriptor

	// The name of the database table in which to create the partition.
	TableName *string

	// The values of the partition.
	Values []string

	noSmithyDocumentSerde
}

// Contains information about a partition error.
type PartitionError struct {

	// The details about the partition error.
	ErrorDetail *ErrorDetail

	// The values that define the partition.
	PartitionValues []string

	noSmithyDocumentSerde
}

// A structure for a partition index.
type PartitionIndex struct {

	// The name of the partition index.
	//
	// This member is required.
	IndexName *string

	// The keys for the partition index.
	//
	// This member is required.
	Keys []string

	noSmithyDocumentSerde
}

// A descriptor for a partition index in a table.
type PartitionIndexDescriptor struct {

	// The name of the partition index.
	//
	// This member is required.
	IndexName *string

	// The status of the partition index. The possible statuses are:
	//   - CREATING: The index is being created. When an index is in a CREATING state,
	//   the index or its table cannot be deleted.
	//   - ACTIVE: The index creation succeeds.
	//   - FAILED: The index creation fails.
	//   - DELETING: The index is deleted from the list of indexes.
	//
	// This member is required.
	IndexStatus PartitionIndexStatus

	// A list of one or more keys, as KeySchemaElement structures, for the partition
	// index.
	//
	// This member is required.
	Keys []KeySchemaElement

	// A list of errors that can occur when registering partition indexes for an
	// existing table.
	BackfillErrors []BackfillError

	noSmithyDocumentSerde
}

// The structure used to create and update a partition.
type PartitionInput struct {

	// The last time at which the partition was accessed.
	LastAccessTime *time.Time

	// The last time at which column statistics were computed for this partition.
	LastAnalyzedTime *time.Time

	// These key-value pairs define partition parameters.
	Parameters map[string]string

	// Provides information about the physical location where the partition is stored.
	StorageDescriptor *StorageDescriptor

	// The values of the partition. Although this parameter is not required by the
	// SDK, you must specify this parameter for a valid input. The values for the keys
	// for the new partition must be passed as an array of String objects that must be
	// ordered in the same order as the partition keys appearing in the Amazon S3
	// prefix. Otherwise Glue will add the values to the wrong keys.
	Values []string

	noSmithyDocumentSerde
}

// Contains a list of values defining partitions.
type PartitionValueList struct {

	// The list of values.
	//
	// This member is required.
	Values []string

	noSmithyDocumentSerde
}

// Specifies the physical requirements for a connection.
type PhysicalConnectionRequirements struct {

	// The connection's Availability Zone. This field is redundant because the
	// specified subnet implies the Availability Zone to be used. Currently the field
	// must be populated, but it will be deprecated in the future.
	AvailabilityZone *string

	// The security group ID list used by the connection.
	SecurityGroupIdList []string

	// The subnet ID used by the connection.
	SubnetId *string

	noSmithyDocumentSerde
}

// Specifies a transform that identifies, removes or masks PII data.
type PIIDetection struct {

	// Indicates the types of entities the PIIDetection transform will identify as PII
	// data. PII type entities include: PERSON_NAME, DATE, USA_SNN, EMAIL, USA_ITIN,
	// USA_PASSPORT_NUMBER, PHONE_NUMBER, BANK_ACCOUNT, IP_ADDRESS, MAC_ADDRESS,
	// USA_CPT_CODE, USA_HCPCS_CODE, USA_NATIONAL_DRUG_CODE,
	// USA_MEDICARE_BENEFICIARY_IDENTIFIER,
	// USA_HEALTH_INSURANCE_CLAIM_NUMBER,CREDIT_CARD,USA_NATIONAL_PROVIDER_IDENTIFIER,USA_DEA_NUMBER,USA_DRIVING_LICENSE
	//
	// This member is required.
	EntityTypesToDetect []string

	// The node ID inputs to the transform.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// Indicates the type of PIIDetection transform.
	//
	// This member is required.
	PiiType PiiType

	// Indicates the value that will replace the detected entity.
	MaskValue *string

	// Indicates the output column name that will contain any entity type detected in
	// that row.
	OutputColumnName *string

	// Indicates the fraction of the data to sample when scanning for PII entities.
	SampleFraction *float64

	// Indicates the fraction of the data that must be met in order for a column to be
	// identified as PII data.
	ThresholdFraction *float64

	noSmithyDocumentSerde
}

// Specifies a PostgresSQL data source in the Glue Data Catalog.
type PostgreSQLCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies a target that uses Postgres SQL.
type PostgreSQLCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// A job run that was used in the predicate of a conditional trigger that
// triggered this job run.
type Predecessor struct {

	// The name of the job definition used by the predecessor job run.
	JobName *string

	// The job-run ID of the predecessor job run.
	RunId *string

	noSmithyDocumentSerde
}

// Defines the predicate of the trigger, which determines when it fires.
type Predicate struct {

	// A list of the conditions that determine when the trigger will fire.
	Conditions []Condition

	// An optional field if only one condition is listed. If multiple conditions are
	// listed, then this field is required.
	Logical Logical

	noSmithyDocumentSerde
}

// Permissions granted to a principal.
type PrincipalPermissions struct {

	// The permissions that are granted to the principal.
	Permissions []Permission

	// The principal who is granted permissions.
	Principal *DataLakePrincipal

	noSmithyDocumentSerde
}

// Defines a property predicate.
type PropertyPredicate struct {

	// The comparator used to compare this property to others.
	Comparator Comparator

	// The key of the property.
	Key *string

	// The value of the property.
	Value *string

	noSmithyDocumentSerde
}

// A structure used as a protocol between query engines and Lake Formation or
// Glue. Contains both a Lake Formation generated authorization identifier and
// information from the request's authorization context.
type QuerySessionContext struct {

	// An opaque string-string map passed by the query engine.
	AdditionalContext map[string]string

	// An identifier string for the consumer cluster.
	ClusterId *string

	// A cryptographically generated query identifier generated by Glue or Lake
	// Formation.
	QueryAuthorizationId *string

	// A unique identifier generated by the query engine for the query.
	QueryId *string

	// A timestamp provided by the query engine for when the query started.
	QueryStartTime *time.Time

	noSmithyDocumentSerde
}

// A Glue Studio node that uses a Glue DataBrew recipe in Glue jobs.
type Recipe struct {

	// The nodes that are inputs to the recipe node, identified by id.
	//
	// This member is required.
	Inputs []string

	// The name of the Glue Studio node.
	//
	// This member is required.
	Name *string

	// A reference to the DataBrew recipe used by the node.
	//
	// This member is required.
	RecipeReference *RecipeReference

	noSmithyDocumentSerde
}

// A reference to a Glue DataBrew recipe.
type RecipeReference struct {

	// The ARN of the DataBrew recipe.
	//
	// This member is required.
	RecipeArn *string

	// The RecipeVersion of the DataBrew recipe.
	//
	// This member is required.
	RecipeVersion *string

	noSmithyDocumentSerde
}

// When crawling an Amazon S3 data source after the first crawl is complete,
// specifies whether to crawl the entire dataset again or to crawl only folders
// that were added since the last crawler run. For more information, see
// Incremental Crawls in Glue (https://docs.aws.amazon.com/glue/latest/dg/incremental-crawls.html)
// in the developer guide.
type RecrawlPolicy struct {

	// Specifies whether to crawl the entire dataset again or to crawl only folders
	// that were added since the last crawler run. A value of CRAWL_EVERYTHING
	// specifies crawling the entire dataset again. A value of CRAWL_NEW_FOLDERS_ONLY
	// specifies crawling only folders that were added since the last crawler run. A
	// value of CRAWL_EVENT_MODE specifies crawling only the changes identified by
	// Amazon S3 events.
	RecrawlBehavior RecrawlBehavior

	noSmithyDocumentSerde
}

// Specifies an Amazon Redshift data store.
type RedshiftSource struct {

	// The database to read from.
	//
	// This member is required.
	Database *string

	// The name of the Amazon Redshift data store.
	//
	// This member is required.
	Name *string

	// The database table to read from.
	//
	// This member is required.
	Table *string

	// The Amazon S3 path where temporary data can be staged when copying out of the
	// database.
	RedshiftTmpDir *string

	// The IAM role with permissions.
	TmpDirIAMRole *string

	noSmithyDocumentSerde
}

// Specifies a target that uses Amazon Redshift.
type RedshiftTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	// The Amazon S3 path where temporary data can be staged when copying out of the
	// database.
	RedshiftTmpDir *string

	// The IAM role with permissions.
	TmpDirIAMRole *string

	// The set of options to configure an upsert operation when writing to a Redshift
	// target.
	UpsertRedshiftOptions *UpsertRedshiftTargetOptions

	noSmithyDocumentSerde
}

// A wrapper structure that may contain the registry name and Amazon Resource Name
// (ARN).
type RegistryId struct {

	// Arn of the registry to be updated. One of RegistryArn or RegistryName has to be
	// provided.
	RegistryArn *string

	// Name of the registry. Used only for lookup. One of RegistryArn or RegistryName
	// has to be provided.
	RegistryName *string

	noSmithyDocumentSerde
}

// A structure containing the details for a registry.
type RegistryListItem struct {

	// The data the registry was created.
	CreatedTime *string

	// A description of the registry.
	Description *string

	// The Amazon Resource Name (ARN) of the registry.
	RegistryArn *string

	// The name of the registry.
	RegistryName *string

	// The status of the registry.
	Status RegistryStatus

	// The date the registry was updated.
	UpdatedTime *string

	noSmithyDocumentSerde
}

// Specifies a Relational database data source in the Glue Data Catalog.
type RelationalCatalogSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	noSmithyDocumentSerde
}

// Specifies a transform that renames a single data property key.
type RenameField struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A JSON path to a variable in the data structure for the source data.
	//
	// This member is required.
	SourcePath []string

	// A JSON path to a variable in the data structure for the target data.
	//
	// This member is required.
	TargetPath []string

	noSmithyDocumentSerde
}

// The URIs for function resources.
type ResourceUri struct {

	// The type of the resource.
	ResourceType ResourceType

	// The URI for accessing the resource.
	Uri *string

	noSmithyDocumentSerde
}

// Metrics for the optimizer run.
type RunMetrics struct {

	// The duration of the job in hours.
	JobDurationInHour *string

	// The number of bytes removed by the compaction job run.
	NumberOfBytesCompacted *string

	// The number of DPU hours consumed by the job.
	NumberOfDpus *string

	// The number of files removed by the compaction job run.
	NumberOfFilesCompacted *string

	noSmithyDocumentSerde
}

// Specifies a Delta Lake data source that is registered in the Glue Data Catalog.
// The data source must be stored in Amazon S3.
type S3CatalogDeltaSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the Delta Lake data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalDeltaOptions map[string]string

	// Specifies the data schema for the Delta Lake source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a Hudi data source that is registered in the Glue Data Catalog. The
// Hudi data source must be stored in Amazon S3.
type S3CatalogHudiSource struct {

	// The name of the database to read from.
	//
	// This member is required.
	Database *string

	// The name of the Hudi data source.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalHudiOptions map[string]string

	// Specifies the data schema for the Hudi source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies an Amazon S3 data store in the Glue Data Catalog.
type S3CatalogSource struct {

	// The database to read from.
	//
	// This member is required.
	Database *string

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// The database table to read from.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options.
	AdditionalOptions *S3SourceAdditionalOptions

	// Partitions satisfying this predicate are deleted. Files within the retention
	// period in these partitions are not deleted. Set to "" – empty by default.
	PartitionPredicate *string

	noSmithyDocumentSerde
}

// Specifies a data target that writes to Amazon S3 using the Glue Data Catalog.
type S3CatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *CatalogSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a command-separated value (CSV) data store stored in Amazon S3.
type S3CsvSource struct {

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// A list of the Amazon S3 paths to read from.
	//
	// This member is required.
	Paths []string

	// Specifies the character to use for quoting. The default is a double quote: '"' .
	// Set this to -1 to turn off quoting entirely.
	//
	// This member is required.
	QuoteChar QuoteChar

	// Specifies the delimiter character. The default is a comma: ",", but any other
	// character can be specified.
	//
	// This member is required.
	Separator Separator

	// Specifies additional connection options.
	AdditionalOptions *S3DirectSourceAdditionalOptions

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	CompressionType CompressionType

	// Specifies a character to use for escaping. This option is used only when
	// reading CSV files. The default value is none . If enabled, the character which
	// immediately follows is used as-is, except for a small set of well-known escapes
	// ( \n , \r , \t , and \0 ).
	Escaper *string

	// A string containing a JSON list of Unix-style glob patterns to exclude. For
	// example, "[\"**.pdf\"]" excludes all PDF files.
	Exclusions []string

	// Grouping files is turned on by default when the input contains more than 50,000
	// files. To turn on grouping with fewer than 50,000 files, set this parameter to
	// "inPartition". To disable grouping when there are more than 50,000 files, set
	// this parameter to "none" .
	GroupFiles *string

	// The target group size in bytes. The default is computed based on the input data
	// size and the size of your cluster. When there are fewer than 50,000 input files,
	// "groupFiles" must be set to "inPartition" for this to take effect.
	GroupSize *string

	// This option controls the duration in milliseconds after which the s3 listing is
	// likely to be consistent. Files with modification timestamps falling within the
	// last maxBand milliseconds are tracked specially when using JobBookmarks to
	// account for Amazon S3 eventual consistency. Most users don't need to set this
	// option. The default is 900000 milliseconds, or 15 minutes.
	MaxBand *int32

	// This option specifies the maximum number of files to save from the last maxBand
	// seconds. If this number is exceeded, extra files are skipped and only processed
	// in the next job run.
	MaxFilesInBand *int32

	// A Boolean value that specifies whether a single record can span multiple lines.
	// This can occur when a field contains a quoted new-line character. You must set
	// this option to True if any record spans multiple lines. The default value is
	// False , which allows for more aggressive file-splitting during parsing.
	Multiline *bool

	// A Boolean value that specifies whether to use the advanced SIMD CSV reader
	// along with Apache Arrow based columnar memory formats. Only available in Glue
	// version 3.0.
	OptimizePerformance bool

	// Specifies the data schema for the S3 CSV source.
	OutputSchemas []GlueSchema

	// If set to true, recursively reads files in all subdirectories under the
	// specified paths.
	Recurse *bool

	// A Boolean value that specifies whether to skip the first data line. The default
	// value is False .
	SkipFirst *bool

	// A Boolean value that specifies whether to treat the first line as a header. The
	// default value is False .
	WithHeader *bool

	// A Boolean value that specifies whether to write the header to output. The
	// default value is True .
	WriteHeader *bool

	noSmithyDocumentSerde
}

// Specifies a target that writes to a Delta Lake data source in the Glue Data
// Catalog.
type S3DeltaCatalogTarget struct {

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	// Specifies additional connection options for the connector.
	AdditionalOptions map[string]string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *CatalogSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a target that writes to a Delta Lake data source in Amazon S3.
type S3DeltaDirectTarget struct {

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	//
	// This member is required.
	Compression DeltaTargetCompressionType

	// Specifies the data output format for the target.
	//
	// This member is required.
	Format TargetFormat

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The Amazon S3 path of your Delta Lake data source to write to.
	//
	// This member is required.
	Path *string

	// Specifies additional connection options for the connector.
	AdditionalOptions map[string]string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *DirectSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a Delta Lake data source stored in Amazon S3.
type S3DeltaSource struct {

	// The name of the Delta Lake source.
	//
	// This member is required.
	Name *string

	// A list of the Amazon S3 paths to read from.
	//
	// This member is required.
	Paths []string

	// Specifies additional connection options.
	AdditionalDeltaOptions map[string]string

	// Specifies additional options for the connector.
	AdditionalOptions *S3DirectSourceAdditionalOptions

	// Specifies the data schema for the Delta Lake source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies additional connection options for the Amazon S3 data store.
type S3DirectSourceAdditionalOptions struct {

	// Sets the upper limit for the target number of files that will be processed.
	BoundedFiles *int64

	// Sets the upper limit for the target size of the dataset in bytes that will be
	// processed.
	BoundedSize *int64

	// Sets option to enable a sample path.
	EnableSamplePath *bool

	// If enabled, specifies the sample path.
	SamplePath *string

	noSmithyDocumentSerde
}

// Specifies a data target that writes to Amazon S3.
type S3DirectTarget struct {

	// Specifies the data output format for the target.
	//
	// This member is required.
	Format TargetFormat

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// A single Amazon S3 path to write to.
	//
	// This member is required.
	Path *string

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	Compression *string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *DirectSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies how Amazon Simple Storage Service (Amazon S3) data should be
// encrypted.
type S3Encryption struct {

	// The Amazon Resource Name (ARN) of the KMS key to be used to encrypt the data.
	KmsKeyArn *string

	// The encryption mode to use for Amazon S3 data.
	S3EncryptionMode S3EncryptionMode

	noSmithyDocumentSerde
}

// Specifies a data target that writes to Amazon S3 in Apache Parquet columnar
// storage.
type S3GlueParquetTarget struct {

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// A single Amazon S3 path to write to.
	//
	// This member is required.
	Path *string

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	Compression ParquetCompressionType

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *DirectSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a target that writes to a Hudi data source in the Glue Data Catalog.
type S3HudiCatalogTarget struct {

	// Specifies additional connection options for the connector.
	//
	// This member is required.
	AdditionalOptions map[string]string

	// The name of the database to write to.
	//
	// This member is required.
	Database *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The name of the table in the database to write to.
	//
	// This member is required.
	Table *string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *CatalogSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a target that writes to a Hudi data source in Amazon S3.
type S3HudiDirectTarget struct {

	// Specifies additional connection options for the connector.
	//
	// This member is required.
	AdditionalOptions map[string]string

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	//
	// This member is required.
	Compression HudiTargetCompressionType

	// Specifies the data output format for the target.
	//
	// This member is required.
	Format TargetFormat

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// The Amazon S3 path of your Hudi data source to write to.
	//
	// This member is required.
	Path *string

	// Specifies native partitioning using a sequence of keys.
	PartitionKeys [][]string

	// A policy that specifies update behavior for the crawler.
	SchemaChangePolicy *DirectSchemaChangePolicy

	noSmithyDocumentSerde
}

// Specifies a Hudi data source stored in Amazon S3.
type S3HudiSource struct {

	// The name of the Hudi source.
	//
	// This member is required.
	Name *string

	// A list of the Amazon S3 paths to read from.
	//
	// This member is required.
	Paths []string

	// Specifies additional connection options.
	AdditionalHudiOptions map[string]string

	// Specifies additional options for the connector.
	AdditionalOptions *S3DirectSourceAdditionalOptions

	// Specifies the data schema for the Hudi source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a JSON data store stored in Amazon S3.
type S3JsonSource struct {

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// A list of the Amazon S3 paths to read from.
	//
	// This member is required.
	Paths []string

	// Specifies additional connection options.
	AdditionalOptions *S3DirectSourceAdditionalOptions

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	CompressionType CompressionType

	// A string containing a JSON list of Unix-style glob patterns to exclude. For
	// example, "[\"**.pdf\"]" excludes all PDF files.
	Exclusions []string

	// Grouping files is turned on by default when the input contains more than 50,000
	// files. To turn on grouping with fewer than 50,000 files, set this parameter to
	// "inPartition". To disable grouping when there are more than 50,000 files, set
	// this parameter to "none" .
	GroupFiles *string

	// The target group size in bytes. The default is computed based on the input data
	// size and the size of your cluster. When there are fewer than 50,000 input files,
	// "groupFiles" must be set to "inPartition" for this to take effect.
	GroupSize *string

	// A JsonPath string defining the JSON data.
	JsonPath *string

	// This option controls the duration in milliseconds after which the s3 listing is
	// likely to be consistent. Files with modification timestamps falling within the
	// last maxBand milliseconds are tracked specially when using JobBookmarks to
	// account for Amazon S3 eventual consistency. Most users don't need to set this
	// option. The default is 900000 milliseconds, or 15 minutes.
	MaxBand *int32

	// This option specifies the maximum number of files to save from the last maxBand
	// seconds. If this number is exceeded, extra files are skipped and only processed
	// in the next job run.
	MaxFilesInBand *int32

	// A Boolean value that specifies whether a single record can span multiple lines.
	// This can occur when a field contains a quoted new-line character. You must set
	// this option to True if any record spans multiple lines. The default value is
	// False , which allows for more aggressive file-splitting during parsing.
	Multiline *bool

	// Specifies the data schema for the S3 JSON source.
	OutputSchemas []GlueSchema

	// If set to true, recursively reads files in all subdirectories under the
	// specified paths.
	Recurse *bool

	noSmithyDocumentSerde
}

// Specifies an Apache Parquet data store stored in Amazon S3.
type S3ParquetSource struct {

	// The name of the data store.
	//
	// This member is required.
	Name *string

	// A list of the Amazon S3 paths to read from.
	//
	// This member is required.
	Paths []string

	// Specifies additional connection options.
	AdditionalOptions *S3DirectSourceAdditionalOptions

	// Specifies how the data is compressed. This is generally not necessary if the
	// data has a standard file extension. Possible values are "gzip" and "bzip" ).
	CompressionType ParquetCompressionType

	// A string containing a JSON list of Unix-style glob patterns to exclude. For
	// example, "[\"**.pdf\"]" excludes all PDF files.
	Exclusions []string

	// Grouping files is turned on by default when the input contains more than 50,000
	// files. To turn on grouping with fewer than 50,000 files, set this parameter to
	// "inPartition". To disable grouping when there are more than 50,000 files, set
	// this parameter to "none" .
	GroupFiles *string

	// The target group size in bytes. The default is computed based on the input data
	// size and the size of your cluster. When there are fewer than 50,000 input files,
	// "groupFiles" must be set to "inPartition" for this to take effect.
	GroupSize *string

	// This option controls the duration in milliseconds after which the s3 listing is
	// likely to be consistent. Files with modification timestamps falling within the
	// last maxBand milliseconds are tracked specially when using JobBookmarks to
	// account for Amazon S3 eventual consistency. Most users don't need to set this
	// option. The default is 900000 milliseconds, or 15 minutes.
	MaxBand *int32

	// This option specifies the maximum number of files to save from the last maxBand
	// seconds. If this number is exceeded, extra files are skipped and only processed
	// in the next job run.
	MaxFilesInBand *int32

	// Specifies the data schema for the S3 Parquet source.
	OutputSchemas []GlueSchema

	// If set to true, recursively reads files in all subdirectories under the
	// specified paths.
	Recurse *bool

	noSmithyDocumentSerde
}

// Specifies additional connection options for the Amazon S3 data store.
type S3SourceAdditionalOptions struct {

	// Sets the upper limit for the target number of files that will be processed.
	BoundedFiles *int64

	// Sets the upper limit for the target size of the dataset in bytes that will be
	// processed.
	BoundedSize *int64

	noSmithyDocumentSerde
}

// Specifies a data store in Amazon Simple Storage Service (Amazon S3).
type S3Target struct {

	// The name of a connection which allows a job or crawler to access data in Amazon
	// S3 within an Amazon Virtual Private Cloud environment (Amazon VPC).
	ConnectionName *string

	// A valid Amazon dead-letter SQS ARN. For example,
	// arn:aws:sqs:region:account:deadLetterQueue .
	DlqEventQueueArn *string

	// A valid Amazon SQS ARN. For example, arn:aws:sqs:region:account:sqs .
	EventQueueArn *string

	// A list of glob patterns used to exclude from the crawl. For more information,
	// see Catalog Tables with a Crawler (https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html)
	// .
	Exclusions []string

	// The path to the Amazon S3 target.
	Path *string

	// Sets the number of files in each leaf folder to be crawled when crawling sample
	// files in a dataset. If not set, all the files are crawled. A valid value is an
	// integer between 1 and 249.
	SampleSize *int32

	noSmithyDocumentSerde
}

// A scheduling object using a cron statement to schedule an event.
type Schedule struct {

	// A cron expression used to specify the schedule (see Time-Based Schedules for
	// Jobs and Crawlers (https://docs.aws.amazon.com/glue/latest/dg/monitor-data-warehouse-schedule.html)
	// . For example, to run something every day at 12:15 UTC, you would specify:
	// cron(15 12 * * ? *) .
	ScheduleExpression *string

	// The state of the schedule.
	State ScheduleState

	noSmithyDocumentSerde
}

// A policy that specifies update and deletion behaviors for the crawler.
type SchemaChangePolicy struct {

	// The deletion behavior when the crawler finds a deleted object.
	DeleteBehavior DeleteBehavior

	// The update behavior when the crawler finds a changed schema.
	UpdateBehavior UpdateBehavior

	noSmithyDocumentSerde
}

// A key-value pair representing a column and data type that this transform can
// run against. The Schema parameter of the MLTransform may contain up to 100 of
// these structures.
type SchemaColumn struct {

	// The type of data in the column.
	DataType *string

	// The name of the column.
	Name *string

	noSmithyDocumentSerde
}

// The unique ID of the schema in the Glue schema registry.
type SchemaId struct {

	// The name of the schema registry that contains the schema.
	RegistryName *string

	// The Amazon Resource Name (ARN) of the schema. One of SchemaArn or SchemaName
	// has to be provided.
	SchemaArn *string

	// The name of the schema. One of SchemaArn or SchemaName has to be provided.
	SchemaName *string

	noSmithyDocumentSerde
}

// An object that contains minimal details for a schema.
type SchemaListItem struct {

	// The date and time that a schema was created.
	CreatedTime *string

	// A description for the schema.
	Description *string

	// the name of the registry where the schema resides.
	RegistryName *string

	// The Amazon Resource Name (ARN) for the schema.
	SchemaArn *string

	// The name of the schema.
	SchemaName *string

	// The status of the schema.
	SchemaStatus SchemaStatus

	// The date and time that a schema was updated.
	UpdatedTime *string

	noSmithyDocumentSerde
}

// An object that references a schema stored in the Glue Schema Registry.
type SchemaReference struct {

	// A structure that contains schema identity fields. Either this or the
	// SchemaVersionId has to be provided.
	SchemaId *SchemaId

	// The unique ID assigned to a version of the schema. Either this or the SchemaId
	// has to be provided.
	SchemaVersionId *string

	// The version number of the schema.
	SchemaVersionNumber *int64

	noSmithyDocumentSerde
}

// An object that contains the error details for an operation on a schema version.
type SchemaVersionErrorItem struct {

	// The details of the error for the schema version.
	ErrorDetails *ErrorDetails

	// The version number of the schema.
	VersionNumber *int64

	noSmithyDocumentSerde
}

// An object containing the details about a schema version.
type SchemaVersionListItem struct {

	// The date and time the schema version was created.
	CreatedTime *string

	// The Amazon Resource Name (ARN) of the schema.
	SchemaArn *string

	// The unique identifier of the schema version.
	SchemaVersionId *string

	// The status of the schema version.
	Status SchemaVersionStatus

	// The version number of the schema.
	VersionNumber *int64

	noSmithyDocumentSerde
}

// A structure containing the schema version information.
type SchemaVersionNumber struct {

	// The latest version available for the schema.
	LatestVersion bool

	// The version number of the schema.
	VersionNumber *int64

	noSmithyDocumentSerde
}

// Specifies a security configuration.
type SecurityConfiguration struct {

	// The time at which this security configuration was created.
	CreatedTimeStamp *time.Time

	// The encryption configuration associated with this security configuration.
	EncryptionConfiguration *EncryptionConfiguration

	// The name of the security configuration.
	Name *string

	noSmithyDocumentSerde
}

// Defines a non-overlapping region of a table's partitions, allowing multiple
// requests to be run in parallel.
type Segment struct {

	// The zero-based index number of the segment. For example, if the total number of
	// segments is 4, SegmentNumber values range from 0 through 3.
	//
	// This member is required.
	SegmentNumber int32

	// The total number of segments.
	//
	// This member is required.
	TotalSegments *int32

	noSmithyDocumentSerde
}

// Specifies a transform that chooses the data property keys that you want to keep.
type SelectFields struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A JSON path to a variable in the data structure.
	//
	// This member is required.
	Paths [][]string

	noSmithyDocumentSerde
}

// Specifies a transform that chooses one DynamicFrame from a collection of
// DynamicFrames . The output is the selected DynamicFrame
type SelectFromCollection struct {

	// The index for the DynamicFrame to be selected.
	//
	// This member is required.
	Index int32

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	noSmithyDocumentSerde
}

// Information about a serialization/deserialization program (SerDe) that serves
// as an extractor and loader.
type SerDeInfo struct {

	// Name of the SerDe.
	Name *string

	// These key-value pairs define initialization parameters for the SerDe.
	Parameters map[string]string

	// Usually the class that implements the SerDe. An example is
	// org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe .
	SerializationLibrary *string

	noSmithyDocumentSerde
}

// The period in which a remote Spark runtime environment is running.
type Session struct {

	// The command object.See SessionCommand.
	Command *SessionCommand

	// The date and time that this session is completed.
	CompletedOn *time.Time

	// The number of connections used for the session.
	Connections *ConnectionsList

	// The time and date when the session was created.
	CreatedOn *time.Time

	// The DPUs consumed by the session (formula: ExecutionTime * MaxCapacity).
	DPUSeconds *float64

	// A map array of key-value pairs. Max is 75 pairs.
	DefaultArguments map[string]string

	// The description of the session.
	Description *string

	// The error message displayed during the session.
	ErrorMessage *string

	// The total time the session ran for.
	ExecutionTime *float64

	// The Glue version determines the versions of Apache Spark and Python that Glue
	// supports. The GlueVersion must be greater than 2.0.
	GlueVersion *string

	// The ID of the session.
	Id *string

	// The number of minutes when idle before the session times out.
	IdleTimeout *int32

	// The number of Glue data processing units (DPUs) that can be allocated when the
	// job runs. A DPU is a relative measure of processing power that consists of 4
	// vCPUs of compute capacity and 16 GB memory.
	MaxCapacity *float64

	// The number of workers of a defined WorkerType to use for the session.
	NumberOfWorkers *int32

	// The code execution progress of the session.
	Progress float64

	// The name or Amazon Resource Name (ARN) of the IAM role associated with the
	// Session.
	Role *string

	// The name of the SecurityConfiguration structure to be used with the session.
	SecurityConfiguration *string

	// The session status.
	Status SessionStatus

	// The type of predefined worker that is allocated when a session runs. Accepts a
	// value of G.1X , G.2X , G.4X , or G.8X for Spark sessions. Accepts the value Z.2X
	// for Ray sessions.
	WorkerType WorkerType

	noSmithyDocumentSerde
}

// The SessionCommand that runs the job.
type SessionCommand struct {

	// Specifies the name of the SessionCommand. Can be 'glueetl' or 'gluestreaming'.
	Name *string

	// Specifies the Python version. The Python version indicates the version
	// supported for jobs of type Spark.
	PythonVersion *string

	noSmithyDocumentSerde
}

// Specifies skewed values in a table. Skewed values are those that occur with
// very high frequency.
type SkewedInfo struct {

	// A list of names of columns that contain skewed values.
	SkewedColumnNames []string

	// A mapping of skewed values to the columns that contain them.
	SkewedColumnValueLocationMaps map[string]string

	// A list of values that appear so frequently as to be considered skewed.
	SkewedColumnValues []string

	noSmithyDocumentSerde
}

// Specifies configuration for Snowflake nodes in Glue Studio.
type SnowflakeNodeData struct {

	// Specifies what action to take when writing to a table with preexisting data.
	// Valid values: append , merge , truncate , drop .
	Action *string

	// Specifies additional options passed to the Snowflake connector. If options are
	// specified elsewhere in this node, this will take precedence.
	AdditionalOptions map[string]string

	// Specifies whether automatic query pushdown is enabled. If pushdown is enabled,
	// then when a query is run on Spark, if part of the query can be "pushed down" to
	// the Snowflake server, it is pushed down. This improves performance of some
	// queries.
	AutoPushdown bool

	// Specifies a Glue Data Catalog Connection to a Snowflake endpoint.
	Connection *Option

	// Specifies a Snowflake database for your node to use.
	Database *string

	// Not currently used.
	IamRole *Option

	// Specifies a merge action. Valid values: simple , custom . If simple, merge
	// behavior is defined by MergeWhenMatched and  MergeWhenNotMatched . If custom,
	// defined by MergeClause .
	MergeAction *string

	// A SQL statement that specifies a custom merge behavior.
	MergeClause *string

	// Specifies how to resolve records that match preexisting data when merging.
	// Valid values: update , delete .
	MergeWhenMatched *string

	// Specifies how to process records that do not match preexisting data when
	// merging. Valid values: insert , none .
	MergeWhenNotMatched *string

	// A SQL string run after the Snowflake connector performs its standard actions.
	PostAction *string

	// A SQL string run before the Snowflake connector performs its standard actions.
	PreAction *string

	// A SQL string used to retrieve data with the query sourcetype.
	SampleQuery *string

	// Specifies a Snowflake database schema for your node to use.
	Schema *string

	// Specifies the columns combined to identify a record when detecting matches for
	// merges and upserts. A list of structures with value , label and  description
	// keys. Each structure describes a column.
	SelectedColumns []Option

	// Specifies how retrieved data is specified. Valid values: "table" ,  "query" .
	SourceType *string

	// The name of a staging table used when performing merge or upsert append
	// actions. Data is written to this table, then moved to table by a generated
	// postaction.
	StagingTable *string

	// Specifies a Snowflake table for your node to use.
	Table *string

	// Manually defines the target schema for the node. A list of structures with value
	// , label and description keys. Each structure defines a column.
	TableSchema []Option

	// Not currently used.
	TempDir *string

	// Used when Action is append . Specifies the resolution behavior when a row
	// already exists. If true, preexisting rows will be updated. If false, those rows
	// will be inserted.
	Upsert bool

	noSmithyDocumentSerde
}

// Specifies a Snowflake data source.
type SnowflakeSource struct {

	// Configuration for the Snowflake data source.
	//
	// This member is required.
	Data *SnowflakeNodeData

	// The name of the Snowflake data source.
	//
	// This member is required.
	Name *string

	// Specifies user-defined schemas for your output data.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a Snowflake target.
type SnowflakeTarget struct {

	// Specifies the data of the Snowflake target node.
	//
	// This member is required.
	Data *SnowflakeNodeData

	// The name of the Snowflake target.
	//
	// This member is required.
	Name *string

	// The nodes that are inputs to the data target.
	Inputs []string

	noSmithyDocumentSerde
}

// Specifies a field to sort by and a sort order.
type SortCriterion struct {

	// The name of the field on which to sort.
	FieldName *string

	// An ascending or descending sort.
	Sort Sort

	noSmithyDocumentSerde
}

// The details for a source control configuration for a job, allowing
// synchronization of job artifacts to or from a remote repository.
type SourceControlDetails struct {

	// The type of authentication, which can be an authentication token stored in
	// Amazon Web Services Secrets Manager, or a personal access token.
	AuthStrategy SourceControlAuthStrategy

	// The value of an authorization token.
	AuthToken *string

	// An optional branch in the remote repository.
	Branch *string

	// An optional folder in the remote repository.
	Folder *string

	// The last commit ID for a commit in the remote repository.
	LastCommitId *string

	// The owner of the remote repository that contains the job artifacts.
	Owner *string

	// The provider for the remote repository.
	Provider SourceControlProvider

	// The name of the remote repository that contains the job artifacts.
	Repository *string

	noSmithyDocumentSerde
}

// Specifies a connector to an Apache Spark data source.
type SparkConnectorSource struct {

	// The name of the connection that is associated with the connector.
	//
	// This member is required.
	ConnectionName *string

	// The type of connection, such as marketplace.spark or custom.spark, designating
	// a connection to an Apache Spark data store.
	//
	// This member is required.
	ConnectionType *string

	// The name of a connector that assists with accessing the data store in Glue
	// Studio.
	//
	// This member is required.
	ConnectorName *string

	// The name of the data source.
	//
	// This member is required.
	Name *string

	// Additional connection options for the connector.
	AdditionalOptions map[string]string

	// Specifies data schema for the custom spark source.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a target that uses an Apache Spark connector.
type SparkConnectorTarget struct {

	// The name of a connection for an Apache Spark connector.
	//
	// This member is required.
	ConnectionName *string

	// The type of connection, such as marketplace.spark or custom.spark, designating
	// a connection to an Apache Spark data store.
	//
	// This member is required.
	ConnectionType *string

	// The name of an Apache Spark connector.
	//
	// This member is required.
	ConnectorName *string

	// The nodes that are inputs to the data target.
	//
	// This member is required.
	Inputs []string

	// The name of the data target.
	//
	// This member is required.
	Name *string

	// Additional connection options for the connector.
	AdditionalOptions map[string]string

	// Specifies the data schema for the custom spark target.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a transform where you enter a SQL query using Spark SQL syntax to
// transform the data. The output is a single DynamicFrame .
type SparkSQL struct {

	// The data inputs identified by their node names. You can associate a table name
	// with each input node to use in the SQL query. The name you choose must meet the
	// Spark SQL naming restrictions.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A list of aliases. An alias allows you to specify what name to use in the SQL
	// for a given input. For example, you have a datasource named "MyDataSource". If
	// you specify From as MyDataSource, and Alias as SqlName, then in your SQL you
	// can do: select * from SqlName and that gets data from MyDataSource.
	//
	// This member is required.
	SqlAliases []SqlAlias

	// A SQL query that must use Spark SQL syntax and return a single data set.
	//
	// This member is required.
	SqlQuery *string

	// Specifies the data schema for the SparkSQL transform.
	OutputSchemas []GlueSchema

	noSmithyDocumentSerde
}

// Specifies a transform that writes samples of the data to an Amazon S3 bucket.
type Spigot struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A path in Amazon S3 where the transform will write a subset of records from the
	// dataset to a JSON file in an Amazon S3 bucket.
	//
	// This member is required.
	Path *string

	// The probability (a decimal value with a maximum value of 1) of picking any
	// given record. A value of 1 indicates that each row read from the dataset should
	// be included in the sample output.
	Prob *float64

	// Specifies a number of records to write starting from the beginning of the
	// dataset.
	Topk *int32

	noSmithyDocumentSerde
}

// Specifies a transform that splits data property keys into two DynamicFrames .
// The output is a collection of DynamicFrames : one with selected data property
// keys, and one with the remaining data property keys.
type SplitFields struct {

	// The data inputs identified by their node names.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// A JSON path to a variable in the data structure.
	//
	// This member is required.
	Paths [][]string

	noSmithyDocumentSerde
}

// Represents a single entry in the list of values for SqlAliases .
type SqlAlias struct {

	// A temporary name given to a table, or a column in a table.
	//
	// This member is required.
	Alias *string

	// A table, or a column in a table.
	//
	// This member is required.
	From *string

	noSmithyDocumentSerde
}

// The batch condition that started the workflow run. Either the number of events
// in the batch size arrived, in which case the BatchSize member is non-zero, or
// the batch window expired, in which case the BatchWindow member is non-zero.
type StartingEventBatchCondition struct {

	// Number of events in the batch.
	BatchSize *int32

	// Duration of the batch window in seconds.
	BatchWindow *int32

	noSmithyDocumentSerde
}

// The statement or request for a particular action to occur in a session.
type Statement struct {

	// The execution code of the statement.
	Code *string

	// The unix time and date that the job definition was completed.
	CompletedOn int64

	// The ID of the statement.
	Id int32

	// The output in JSON.
	Output *StatementOutput

	// The code execution progress.
	Progress float64

	// The unix time and date that the job definition was started.
	StartedOn int64

	// The state while request is actioned.
	State StatementState

	noSmithyDocumentSerde
}

// The code execution output in JSON format.
type StatementOutput struct {

	// The code execution output.
	Data *StatementOutputData

	// The name of the error in the output.
	ErrorName *string

	// The error value of the output.
	ErrorValue *string

	// The execution count of the output.
	ExecutionCount int32

	// The status of the code execution output.
	Status StatementState

	// The traceback of the output.
	Traceback []string

	noSmithyDocumentSerde
}

// The code execution output in JSON format.
type StatementOutputData struct {

	// The code execution output in text format.
	TextPlain *string

	noSmithyDocumentSerde
}

// Describes the physical storage of table data.
type StorageDescriptor struct {

	// A list of locations that point to the path where a Delta table is located.
	AdditionalLocations []string

	// A list of reducer grouping columns, clustering columns, and bucketing columns
	// in the table.
	BucketColumns []string

	// A list of the Columns in the table.
	Columns []Column

	// True if the data in the table is compressed, or False if not.
	Compressed bool

	// The input format: SequenceFileInputFormat (binary), or TextInputFormat , or a
	// custom format.
	InputFormat *string

	// The physical location of the table. By default, this takes the form of the
	// warehouse location, followed by the database location in the warehouse, followed
	// by the table name.
	Location *string

	// Must be specified if the table contains any dimension columns.
	NumberOfBuckets int32

	// The output format: SequenceFileOutputFormat (binary), or
	// IgnoreKeyTextOutputFormat , or a custom format.
	OutputFormat *string

	// The user-supplied properties in key-value form.
	Parameters map[string]string

	// An object that references a schema stored in the Glue Schema Registry. When
	// creating a table, you can pass an empty list of columns for the schema, and
	// instead use a schema reference.
	SchemaReference *SchemaReference

	// The serialization/deserialization (SerDe) information.
	SerdeInfo *SerDeInfo

	// The information about values that appear frequently in a column (skewed values).
	SkewedInfo *SkewedInfo

	// A list specifying the sort order of each bucket in the table.
	SortColumns []Order

	// True if the table data is stored in subdirectories, or False if not.
	StoredAsSubDirectories bool

	noSmithyDocumentSerde
}

// Specifies options related to data preview for viewing a sample of your data.
type StreamingDataPreviewOptions struct {

	// The polling time in milliseconds.
	PollingTime *int64

	// The limit to the number of records polled.
	RecordPollingLimit *int64

	noSmithyDocumentSerde
}

// Defines column statistics supported for character sequence data values.
type StringColumnStatisticsData struct {

	// The average string length in the column.
	//
	// This member is required.
	AverageLength float64

	// The size of the longest string in the column.
	//
	// This member is required.
	MaximumLength int64

	// The number of distinct values in a column.
	//
	// This member is required.
	NumberOfDistinctValues int64

	// The number of null values in the column.
	//
	// This member is required.
	NumberOfNulls int64

	noSmithyDocumentSerde
}

// A structure specifying the dialect and dialect version used by the query engine.
type SupportedDialect struct {

	// The dialect of the query engine.
	Dialect ViewDialect

	// The version of the dialect of the query engine. For example, 3.0.0.
	DialectVersion *string

	noSmithyDocumentSerde
}

// Represents a collection of related data organized in columns and rows.
type Table struct {

	// The table name. For Hive compatibility, this must be entirely lowercase.
	//
	// This member is required.
	Name *string

	// The ID of the Data Catalog in which the table resides.
	CatalogId *string

	// The time when the table definition was created in the Data Catalog.
	CreateTime *time.Time

	// The person or entity who created the table.
	CreatedBy *string

	// The name of the database where the table metadata resides. For Hive
	// compatibility, this must be all lowercase.
	DatabaseName *string

	// A description of the table.
	Description *string

	// A FederatedTable structure that references an entity outside the Glue Data
	// Catalog.
	FederatedTable *FederatedTable

	// Indicates whether the table has been registered with Lake Formation.
	IsRegisteredWithLakeFormation bool

	// The last time that the table was accessed. This is usually taken from HDFS, and
	// might not be reliable.
	LastAccessTime *time.Time

	// The last time that column statistics were computed for this table.
	LastAnalyzedTime *time.Time

	// The owner of the table.
	Owner *string

	// These key-value pairs define properties associated with the table.
	Parameters map[string]string

	// A list of columns by which the table is partitioned. Only primitive types are
	// supported as partition keys. When you create a table used by Amazon Athena, and
	// you do not specify any partitionKeys , you must at least set the value of
	// partitionKeys to an empty list. For example: "PartitionKeys": []
	PartitionKeys []Column

	// The retention time for this table.
	Retention int32

	// A storage descriptor containing information about the physical storage of this
	// table.
	StorageDescriptor *StorageDescriptor

	// The type of this table. Glue will create tables with the EXTERNAL_TABLE type.
	// Other services, such as Athena, may create tables with additional table types.
	// Glue related table types: EXTERNAL_TABLE Hive compatible attribute - indicates a
	// non-Hive managed table. GOVERNED Used by Lake Formation. The Glue Data Catalog
	// understands GOVERNED .
	TableType *string

	// A TableIdentifier structure that describes a target table for resource linking.
	TargetTable *TableIdentifier

	// The last time that the table was updated.
	UpdateTime *time.Time

	// The ID of the table version.
	VersionId *string

	// Included for Apache Hive compatibility. Not used in the normal course of Glue
	// operations.
	ViewExpandedText *string

	// Included for Apache Hive compatibility. Not used in the normal course of Glue
	// operations. If the table is a VIRTUAL_VIEW , certain Athena configuration
	// encoded in base64.
	ViewOriginalText *string

	noSmithyDocumentSerde
}

// An error record for table operations.
type TableError struct {

	// The details about the error.
	ErrorDetail *ErrorDetail

	// The name of the table. For Hive compatibility, this must be entirely lowercase.
	TableName *string

	noSmithyDocumentSerde
}

// A structure that describes a target table for resource linking.
type TableIdentifier struct {

	// The ID of the Data Catalog in which the table resides.
	CatalogId *string

	// The name of the catalog database that contains the target table.
	DatabaseName *string

	// The name of the target table.
	Name *string

	// Region of the target table.
	Region *string

	noSmithyDocumentSerde
}

// A structure used to define a table.
type TableInput struct {

	// The table name. For Hive compatibility, this is folded to lowercase when it is
	// stored.
	//
	// This member is required.
	Name *string

	// A description of the table.
	Description *string

	// The last time that the table was accessed.
	LastAccessTime *time.Time

	// The last time that column statistics were computed for this table.
	LastAnalyzedTime *time.Time

	// The table owner. Included for Apache Hive compatibility. Not used in the normal
	// course of Glue operations.
	Owner *string

	// These key-value pairs define properties associated with the table.
	Parameters map[string]string

	// A list of columns by which the table is partitioned. Only primitive types are
	// supported as partition keys. When you create a table used by Amazon Athena, and
	// you do not specify any partitionKeys , you must at least set the value of
	// partitionKeys to an empty list. For example: "PartitionKeys": []
	PartitionKeys []Column

	// The retention time for this table.
	Retention int32

	// A storage descriptor containing information about the physical storage of this
	// table.
	StorageDescriptor *StorageDescriptor

	// The type of this table. Glue will create tables with the EXTERNAL_TABLE type.
	// Other services, such as Athena, may create tables with additional table types.
	// Glue related table types: EXTERNAL_TABLE Hive compatible attribute - indicates a
	// non-Hive managed table. GOVERNED Used by Lake Formation. The Glue Data Catalog
	// understands GOVERNED .
	TableType *string

	// A TableIdentifier structure that describes a target table for resource linking.
	TargetTable *TableIdentifier

	// Included for Apache Hive compatibility. Not used in the normal course of Glue
	// operations.
	ViewExpandedText *string

	// Included for Apache Hive compatibility. Not used in the normal course of Glue
	// operations. If the table is a VIRTUAL_VIEW , certain Athena configuration
	// encoded in base64.
	ViewOriginalText *string

	noSmithyDocumentSerde
}

// Contains details about an optimizer associated with a table.
type TableOptimizer struct {

	// A TableOptimizerConfiguration object that was specified when creating or
	// updating a table optimizer.
	Configuration *TableOptimizerConfiguration

	// A TableOptimizerRun object representing the last run of the table optimizer.
	LastRun *TableOptimizerRun

	// The type of table optimizer. Currently, the only valid value is compaction .
	Type TableOptimizerType

	noSmithyDocumentSerde
}

// Contains details on the configuration of a table optimizer. You pass this
// configuration when creating or updating a table optimizer.
type TableOptimizerConfiguration struct {

	// Whether table optimization is enabled.
	Enabled *bool

	// A role passed by the caller which gives the service permission to update the
	// resources associated with the optimizer on the caller's behalf.
	RoleArn *string

	noSmithyDocumentSerde
}

// Contains details for a table optimizer run.
type TableOptimizerRun struct {

	// Represents the epoch timestamp at which the compaction job ended.
	EndTimestamp *time.Time

	// An error that occured during the optimizer run.
	Error *string

	// An event type representing the status of the table optimizer run.
	EventType TableOptimizerEventType

	// A RunMetrics object containing metrics for the optimizer run.
	Metrics *RunMetrics

	// Represents the epoch timestamp at which the compaction job was started within
	// Lake Formation.
	StartTimestamp *time.Time

	noSmithyDocumentSerde
}

// Specifies a version of a table.
type TableVersion struct {

	// The table in question.
	Table *Table

	// The ID value that identifies this table version. A VersionId is a string
	// representation of an integer. Each version is incremented by 1.
	VersionId *string

	noSmithyDocumentSerde
}

// An error record for table-version operations.
type TableVersionError struct {

	// The details about the error.
	ErrorDetail *ErrorDetail

	// The name of the table in question.
	TableName *string

	// The ID value of the version in question. A VersionID is a string representation
	// of an integer. Each version is incremented by 1.
	VersionId *string

	noSmithyDocumentSerde
}

// The sampling parameters that are associated with the machine learning transform.
type TaskRun struct {

	// The last point in time that the requested task run was completed.
	CompletedOn *time.Time

	// The list of error strings associated with this task run.
	ErrorString *string

	// The amount of time (in seconds) that the task run consumed resources.
	ExecutionTime int32

	// The last point in time that the requested task run was updated.
	LastModifiedOn *time.Time

	// The names of the log group for secure logging, associated with this task run.
	LogGroupName *string

	// Specifies configuration properties associated with this task run.
	Properties *TaskRunProperties

	// The date and time that this task run started.
	StartedOn *time.Time

	// The current status of the requested task run.
	Status TaskStatusType

	// The unique identifier for this task run.
	TaskRunId *string

	// The unique identifier for the transform.
	TransformId *string

	noSmithyDocumentSerde
}

// The criteria that are used to filter the task runs for the machine learning
// transform.
type TaskRunFilterCriteria struct {

	// Filter on task runs started after this date.
	StartedAfter *time.Time

	// Filter on task runs started before this date.
	StartedBefore *time.Time

	// The current status of the task run.
	Status TaskStatusType

	// The type of task run.
	TaskRunType TaskType

	noSmithyDocumentSerde
}

// The configuration properties for the task run.
type TaskRunProperties struct {

	// The configuration properties for an exporting labels task run.
	ExportLabelsTaskRunProperties *ExportLabelsTaskRunProperties

	// The configuration properties for a find matches task run.
	FindMatchesTaskRunProperties *FindMatchesTaskRunProperties

	// The configuration properties for an importing labels task run.
	ImportLabelsTaskRunProperties *ImportLabelsTaskRunProperties

	// The configuration properties for a labeling set generation task run.
	LabelingSetGenerationTaskRunProperties *LabelingSetGenerationTaskRunProperties

	// The type of task run.
	TaskType TaskType

	noSmithyDocumentSerde
}

// The sorting criteria that are used to sort the list of task runs for the
// machine learning transform.
type TaskRunSortCriteria struct {

	// The column to be used to sort the list of task runs for the machine learning
	// transform.
	//
	// This member is required.
	Column TaskRunSortColumnType

	// The sort direction to be used to sort the list of task runs for the machine
	// learning transform.
	//
	// This member is required.
	SortDirection SortDirectionType

	noSmithyDocumentSerde
}

// Specifies the parameters in the config file of the dynamic transform.
type TransformConfigParameter struct {

	// Specifies the name of the parameter in the config file of the dynamic transform.
	//
	// This member is required.
	Name *string

	// Specifies the parameter type in the config file of the dynamic transform.
	//
	// This member is required.
	Type ParamType

	// Specifies whether the parameter is optional or not in the config file of the
	// dynamic transform.
	IsOptional *bool

	// Specifies the list type of the parameter in the config file of the dynamic
	// transform.
	ListType ParamType

	// Specifies the validation message in the config file of the dynamic transform.
	ValidationMessage *string

	// Specifies the validation rule in the config file of the dynamic transform.
	ValidationRule *string

	// Specifies the value of the parameter in the config file of the dynamic
	// transform.
	Value []string

	noSmithyDocumentSerde
}

// The encryption-at-rest settings of the transform that apply to accessing user
// data. Machine learning transforms can access user data encrypted in Amazon S3
// using KMS. Additionally, imported labels and trained transforms can now be
// encrypted using a customer provided KMS key.
type TransformEncryption struct {

	// An MLUserDataEncryption object containing the encryption mode and
	// customer-provided KMS key ID.
	MlUserDataEncryption *MLUserDataEncryption

	// The name of the security configuration.
	TaskRunSecurityConfigurationName *string

	noSmithyDocumentSerde
}

// The criteria used to filter the machine learning transforms.
type TransformFilterCriteria struct {

	// The time and date after which the transforms were created.
	CreatedAfter *time.Time

	// The time and date before which the transforms were created.
	CreatedBefore *time.Time

	// This value determines which version of Glue this machine learning transform is
	// compatible with. Glue 1.0 is recommended for most customers. If the value is not
	// set, the Glue compatibility defaults to Glue 0.9. For more information, see
	// Glue Versions (https://docs.aws.amazon.com/glue/latest/dg/release-notes.html#release-notes-versions)
	// in the developer guide.
	GlueVersion *string

	// Filter on transforms last modified after this date.
	LastModifiedAfter *time.Time

	// Filter on transforms last modified before this date.
	LastModifiedBefore *time.Time

	// A unique transform name that is used to filter the machine learning transforms.
	Name *string

	// Filters on datasets with a specific schema. The Map object is an array of
	// key-value pairs representing the schema this transform accepts, where Column is
	// the name of a column, and Type is the type of the data such as an integer or
	// string. Has an upper bound of 100 columns.
	Schema []SchemaColumn

	// Filters the list of machine learning transforms by the last known status of the
	// transforms (to indicate whether a transform can be used or not). One of
	// "NOT_READY", "READY", or "DELETING".
	Status TransformStatusType

	// The type of machine learning transform that is used to filter the machine
	// learning transforms.
	TransformType TransformType

	noSmithyDocumentSerde
}

// The algorithm-specific parameters that are associated with the machine learning
// transform.
type TransformParameters struct {

	// The type of machine learning transform. For information about the types of
	// machine learning transforms, see Creating Machine Learning Transforms (https://docs.aws.amazon.com/glue/latest/dg/add-job-machine-learning-transform.html)
	// .
	//
	// This member is required.
	TransformType TransformType

	// The parameters for the find matches algorithm.
	FindMatchesParameters *FindMatchesParameters

	noSmithyDocumentSerde
}

// The sorting criteria that are associated with the machine learning transform.
type TransformSortCriteria struct {

	// The column to be used in the sorting criteria that are associated with the
	// machine learning transform.
	//
	// This member is required.
	Column TransformSortColumnType

	// The sort direction to be used in the sorting criteria that are associated with
	// the machine learning transform.
	//
	// This member is required.
	SortDirection SortDirectionType

	noSmithyDocumentSerde
}

// Information about a specific trigger.
type Trigger struct {

	// The actions initiated by this trigger.
	Actions []Action

	// A description of this trigger.
	Description *string

	// Batch condition that must be met (specified number of events received or batch
	// time window expired) before EventBridge event trigger fires.
	EventBatchingCondition *EventBatchingCondition

	// Reserved for future use.
	Id *string

	// The name of the trigger.
	Name *string

	// The predicate of this trigger, which defines when it will fire.
	Predicate *Predicate

	// A cron expression used to specify the schedule (see Time-Based Schedules for
	// Jobs and Crawlers (https://docs.aws.amazon.com/glue/latest/dg/monitor-data-warehouse-schedule.html)
	// . For example, to run something every day at 12:15 UTC, you would specify:
	// cron(15 12 * * ? *) .
	Schedule *string

	// The current state of the trigger.
	State TriggerState

	// The type of trigger that this is.
	Type TriggerType

	// The name of the workflow associated with the trigger.
	WorkflowName *string

	noSmithyDocumentSerde
}

// The details of a Trigger node present in the workflow.
type TriggerNodeDetails struct {

	// The information of the trigger represented by the trigger node.
	Trigger *Trigger

	noSmithyDocumentSerde
}

// A structure used to provide information used to update a trigger. This object
// updates the previous trigger definition by overwriting it completely.
type TriggerUpdate struct {

	// The actions initiated by this trigger.
	Actions []Action

	// A description of this trigger.
	Description *string

	// Batch condition that must be met (specified number of events received or batch
	// time window expired) before EventBridge event trigger fires.
	EventBatchingCondition *EventBatchingCondition

	// Reserved for future use.
	Name *string

	// The predicate of this trigger, which defines when it will fire.
	Predicate *Predicate

	// A cron expression used to specify the schedule (see Time-Based Schedules for
	// Jobs and Crawlers (https://docs.aws.amazon.com/glue/latest/dg/monitor-data-warehouse-schedule.html)
	// . For example, to run something every day at 12:15 UTC, you would specify:
	// cron(15 12 * * ? *) .
	Schedule *string

	noSmithyDocumentSerde
}

// A partition that contains unfiltered metadata.
type UnfilteredPartition struct {

	// The list of columns the user has permissions to access.
	AuthorizedColumns []string

	// A Boolean value indicating that the partition location is registered with Lake
	// Formation.
	IsRegisteredWithLakeFormation bool

	// The partition object.
	Partition *Partition

	noSmithyDocumentSerde
}

// Specifies a transform that combines the rows from two or more datasets into a
// single result.
type Union struct {

	// The node ID inputs to the transform.
	//
	// This member is required.
	Inputs []string

	// The name of the transform node.
	//
	// This member is required.
	Name *string

	// Indicates the type of Union transform. Specify ALL to join all rows from data
	// sources to the resulting DynamicFrame. The resulting union does not remove
	// duplicate rows. Specify DISTINCT to remove duplicate rows in the resulting
	// DynamicFrame.
	//
	// This member is required.
	UnionType UnionType

	noSmithyDocumentSerde
}

// Specifies a custom CSV classifier to be updated.
type UpdateCsvClassifierRequest struct {

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// Enables the processing of files that contain only one column.
	AllowSingleColumn *bool

	// Indicates whether the CSV file contains a header.
	ContainsHeader CsvHeaderOption

	// Specifies the configuration of custom datatypes.
	CustomDatatypeConfigured *bool

	// Specifies a list of supported custom datatypes.
	CustomDatatypes []string

	// A custom symbol to denote what separates each column entry in the row.
	Delimiter *string

	// Specifies not to trim values before identifying the type of column values. The
	// default value is true.
	DisableValueTrimming *bool

	// A list of strings representing column names.
	Header []string

	// A custom symbol to denote what combines content into a single column value. It
	// must be different from the column delimiter.
	QuoteSymbol *string

	// Sets the SerDe for processing CSV in the classifier, which will be applied in
	// the Data Catalog. Valid values are OpenCSVSerDe , LazySimpleSerDe , and None .
	// You can specify the None value when you want the crawler to do the detection.
	Serde CsvSerdeOption

	noSmithyDocumentSerde
}

// Specifies a grok classifier to update when passed to UpdateClassifier .
type UpdateGrokClassifierRequest struct {

	// The name of the GrokClassifier .
	//
	// This member is required.
	Name *string

	// An identifier of the data format that the classifier matches, such as Twitter,
	// JSON, Omniture logs, Amazon CloudWatch Logs, and so on.
	Classification *string

	// Optional custom grok patterns used by this classifier.
	CustomPatterns *string

	// The grok pattern used by this classifier.
	GrokPattern *string

	noSmithyDocumentSerde
}

// Specifies a JSON classifier to be updated.
type UpdateJsonClassifierRequest struct {

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// A JsonPath string defining the JSON data for the classifier to classify. Glue
	// supports a subset of JsonPath, as described in Writing JsonPath Custom
	// Classifiers (https://docs.aws.amazon.com/glue/latest/dg/custom-classifier.html#custom-classifier-json)
	// .
	JsonPath *string

	noSmithyDocumentSerde
}

// Specifies an XML classifier to be updated.
type UpdateXMLClassifierRequest struct {

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// An identifier of the data format that the classifier matches.
	Classification *string

	// The XML tag designating the element that contains each record in an XML
	// document being parsed. This cannot identify a self-closing element (closed by />
	// ). An empty row element that contains only attributes can be parsed as long as
	// it ends with a closing tag (for example, is okay, but  is not).
	RowTag *string

	noSmithyDocumentSerde
}

// The options to configure an upsert operation when writing to a Redshift target .
type UpsertRedshiftTargetOptions struct {

	// The name of the connection to use to write to Redshift.
	ConnectionName *string

	// The physical location of the Redshift table.
	TableLocation *string

	// The keys used to determine whether to perform an update or insert.
	UpsertKeys []string

	noSmithyDocumentSerde
}

// Represents the equivalent of a Hive user-defined function ( UDF ) definition.
type UserDefinedFunction struct {

	// The ID of the Data Catalog in which the function resides.
	CatalogId *string

	// The Java class that contains the function code.
	ClassName *string

	// The time at which the function was created.
	CreateTime *time.Time

	// The name of the catalog database that contains the function.
	DatabaseName *string

	// The name of the function.
	FunctionName *string

	// The owner of the function.
	OwnerName *string

	// The owner type.
	OwnerType PrincipalType

	// The resource URIs for the function.
	ResourceUris []ResourceUri

	noSmithyDocumentSerde
}

// A structure used to create or update a user-defined function.
type UserDefinedFunctionInput struct {

	// The Java class that contains the function code.
	ClassName *string

	// The name of the function.
	FunctionName *string

	// The owner of the function.
	OwnerName *string

	// The owner type.
	OwnerType PrincipalType

	// The resource URIs for the function.
	ResourceUris []ResourceUri

	noSmithyDocumentSerde
}

// 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.
type Workflow struct {

	// This structure indicates the details of the blueprint that this particular
	// workflow is created from.
	BlueprintDetails *BlueprintDetails

	// The date and time when the workflow was created.
	CreatedOn *time.Time

	// 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.
	DefaultRunProperties map[string]string

	// A description of the workflow.
	Description *string

	// The graph representing all the Glue components that belong to the workflow as
	// nodes and directed connections between them as edges.
	Graph *WorkflowGraph

	// The date and time when the workflow was last modified.
	LastModifiedOn *time.Time

	// The information about the last execution of the workflow.
	LastRun *WorkflowRun

	// 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.
	MaxConcurrentRuns *int32

	// The name of the workflow.
	Name *string

	noSmithyDocumentSerde
}

// A workflow graph represents the complete workflow containing all the Glue
// components present in the workflow and all the directed connections between
// them.
type WorkflowGraph struct {

	// A list of all the directed connections between the nodes belonging to the
	// workflow.
	Edges []Edge

	// A list of the the Glue components belong to the workflow represented as nodes.
	Nodes []Node

	noSmithyDocumentSerde
}

// A workflow run is an execution of a workflow providing all the runtime
// information.
type WorkflowRun struct {

	// The date and time when the workflow run completed.
	CompletedOn *time.Time

	// 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 ."
	ErrorMessage *string

	// The graph representing all the Glue components that belong to the workflow as
	// nodes and directed connections between them as edges.
	Graph *WorkflowGraph

	// Name of the workflow that was run.
	Name *string

	// The ID of the previous workflow run.
	PreviousRunId *string

	// The date and time when the workflow run was started.
	StartedOn *time.Time

	// The batch condition that started the workflow run.
	StartingEventBatchCondition *StartingEventBatchCondition

	// The statistics of the run.
	Statistics *WorkflowRunStatistics

	// The status of the workflow run.
	Status WorkflowRunStatus

	// The ID of this workflow run.
	WorkflowRunId *string

	// The workflow run properties which were set during the run.
	WorkflowRunProperties map[string]string

	noSmithyDocumentSerde
}

// Workflow run statistics provides statistics about the workflow run.
type WorkflowRunStatistics struct {

	// Indicates the count of job runs in the ERROR state in the workflow run.
	ErroredActions int32

	// Total number of Actions that have failed.
	FailedActions int32

	// Total number Actions in running state.
	RunningActions int32

	// Total number of Actions that have stopped.
	StoppedActions int32

	// Total number of Actions that have succeeded.
	SucceededActions int32

	// Total number of Actions that timed out.
	TimeoutActions int32

	// Total number of Actions in the workflow run.
	TotalActions int32

	// Indicates the count of job runs in WAITING state in the workflow run.
	WaitingActions int32

	noSmithyDocumentSerde
}

// A classifier for XML content.
type XMLClassifier struct {

	// An identifier of the data format that the classifier matches.
	//
	// This member is required.
	Classification *string

	// The name of the classifier.
	//
	// This member is required.
	Name *string

	// The time that this classifier was registered.
	CreationTime *time.Time

	// The time that this classifier was last updated.
	LastUpdated *time.Time

	// The XML tag designating the element that contains each record in an XML
	// document being parsed. This can't identify a self-closing element (closed by />
	// ). An empty row element that contains only attributes can be parsed as long as
	// it ends with a closing tag (for example, is okay, but  is not).
	RowTag *string

	// The version of this classifier.
	Version int64

	noSmithyDocumentSerde
}

type noSmithyDocumentSerde = smithydocument.NoSerde