openapi: 3.0.0 info: version: '2017-03-31' x-release: v4 title: 'AWS Glue #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.GetJobs API' description: Glue

Defines the public endpoint for the Glue service.

x-logo: url: https://api.apis.guru/v2/cache/logo/https_twitter.com_awscloud_profile_image.png backgroundColor: '#FFFFFF' termsOfService: https://aws.amazon.com/service-terms/ contact: name: Mike Ralphson email: mike.ralphson@gmail.com url: https://github.com/mermade/aws2openapi x-twitter: PermittedSoc license: name: Apache 2.0 License url: http://www.apache.org/licenses/ x-providerName: amazonaws.com x-serviceName: glue x-origin: - contentType: application/json url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/glue-2017-03-31.normal.json converter: url: https://github.com/mermade/aws2openapi version: 1.0.0 x-apisguru-driver: external x-apiClientRegistration: url: https://portal.aws.amazon.com/gp/aws/developer/registration/index.html?nc2=h_ct x-apisguru-categories: - cloud x-preferred: true servers: - url: http://glue.{region}.amazonaws.com variables: region: description: The AWS region enum: - us-east-1 - us-east-2 - us-west-1 - us-west-2 - us-gov-west-1 - us-gov-east-1 - ca-central-1 - eu-north-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-south-1 - af-south-1 - ap-northeast-1 - ap-northeast-2 - ap-northeast-3 - ap-southeast-1 - ap-southeast-2 - ap-east-1 - ap-south-1 - sa-east-1 - me-south-1 default: us-east-1 description: The AWS Glue multi-region endpoint - url: https://glue.{region}.amazonaws.com variables: region: description: The AWS region enum: - us-east-1 - us-east-2 - us-west-1 - us-west-2 - us-gov-west-1 - us-gov-east-1 - ca-central-1 - eu-north-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-south-1 - af-south-1 - ap-northeast-1 - ap-northeast-2 - ap-northeast-3 - ap-southeast-1 - ap-southeast-2 - ap-east-1 - ap-south-1 - sa-east-1 - me-south-1 default: us-east-1 description: The AWS Glue multi-region endpoint - url: http://glue.{region}.amazonaws.com.cn variables: region: description: The AWS region enum: - cn-north-1 - cn-northwest-1 default: cn-north-1 description: The AWS Glue endpoint for China (Beijing) and China (Ningxia) - url: https://glue.{region}.amazonaws.com.cn variables: region: description: The AWS region enum: - cn-north-1 - cn-northwest-1 default: cn-north-1 description: The AWS Glue endpoint for China (Beijing) and China (Ningxia) security: - hmac: [] tags: - name: '#X Amz Target=AWSGlue.GetJobs' paths: /#X-Amz-Target=AWSGlue.GetJobs: parameters: - $ref: '#/components/parameters/X-Amz-Content-Sha256' - $ref: '#/components/parameters/X-Amz-Date' - $ref: '#/components/parameters/X-Amz-Algorithm' - $ref: '#/components/parameters/X-Amz-Credential' - $ref: '#/components/parameters/X-Amz-Security-Token' - $ref: '#/components/parameters/X-Amz-Signature' - $ref: '#/components/parameters/X-Amz-SignedHeaders' post: operationId: GetJobs description: Retrieves all current job definitions. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/GetJobsResponse' examples: GetJobs200Example: summary: Default GetJobs 200 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '480': description: InvalidInputException content: application/json: schema: $ref: '#/components/schemas/InvalidInputException' examples: GetJobs480Example: summary: Default GetJobs 480 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '481': description: EntityNotFoundException content: application/json: schema: $ref: '#/components/schemas/EntityNotFoundException' examples: GetJobs481Example: summary: Default GetJobs 481 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '482': description: InternalServiceException content: application/json: schema: $ref: '#/components/schemas/InternalServiceException' examples: GetJobs482Example: summary: Default GetJobs 482 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED '483': description: OperationTimeoutException content: application/json: schema: $ref: '#/components/schemas/OperationTimeoutException' examples: GetJobs483Example: summary: Default GetJobs 483 response x-microcks-default: true value: JobRunId: jr_abc123 State: SUCCEEDED requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GetJobsRequest' parameters: - name: MaxResults in: query schema: type: string description: Pagination limit required: false - name: NextToken in: query schema: type: string description: Pagination token required: false - name: X-Amz-Target in: header required: true schema: type: string enum: - AWSGlue.GetJobs summary: Amazon Glue Get Jobs x-microcks-operation: delay: 0 dispatcher: FALLBACK tags: - '#X Amz Target=AWSGlue.GetJobs' components: schemas: DQDLString: type: string pattern: ([\u0020-\u007E\r\s\n])* minLength: 1 maxLength: 65536 TwoInputs: type: array items: $ref: '#/components/schemas/NodeId' minItems: 2 maxItems: 2 JDBCConnectorSource: type: object required: - Name - ConnectionName - ConnectorName - ConnectionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection that is associated with the connector. ConnectorName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of a connector that assists with accessing the data store in Glue Studio. ConnectionType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of connection, such as marketplace.jdbc or custom.jdbc, designating a connection to a JDBC data store. AdditionalOptions: allOf: - $ref: '#/components/schemas/JDBCConnectorOptions' - description: Additional connection options for the connector. ConnectionTable: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertyWithQuote' - description: The name of the table in the data source. Query: allOf: - $ref: '#/components/schemas/SqlQuery' - description: The table or SQL query to get the data from. You can specify either ConnectionTable or query, but not both. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the custom JDBC source. description: Specifies a connector to a JDBC data source. S3HudiCatalogTarget: type: object required: - Name - Inputs - Table - Database - AdditionalOptions properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options for the connector. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/CatalogSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a target that writes to a Hudi data source in the Glue Data Catalog. BoxedNonNegativeLong: type: integer minimum: 0 ColumnTypeString: type: string minLength: 0 maxLength: 131072 x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\t]*' S3CatalogDeltaSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Delta Lake data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. AdditionalDeltaOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Delta Lake source. description: Specifies a Delta Lake data source that is registered in the Glue Data Catalog. The data source must be stored in Amazon S3. PostgreSQLCatalogTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. description: Specifies a target that uses Postgres SQL. SqlQuery: type: string x-pattern: \([\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\s]\)* SqlAlias: type: object required: - From - Alias properties: From: allOf: - $ref: '#/components/schemas/NodeId' - description: A table, or a column in a table. Alias: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertyWithQuote' - description: A temporary name given to a table, or a column in a table. description: 'Represents a single entry in the list of values for SqlAliases. ' ParamType: type: string enum: - str - int - float - complex - bool - list - 'null' PageSize: type: integer minimum: 1 maximum: 1000 StreamingDataPreviewOptions: type: object properties: PollingTime: allOf: - $ref: '#/components/schemas/PollingTime' - description: The polling time in milliseconds. RecordPollingLimit: allOf: - $ref: '#/components/schemas/PositiveLong' - description: The limit to the number of records polled. description: Specifies options related to data preview for viewing a sample of your data. QuoteChar: type: string enum: - quote - quillemet - single_quote - disabled S3JsonSource: type: object required: - Name - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Paths: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A list of the Amazon S3 paths to read from. CompressionType: allOf: - $ref: '#/components/schemas/CompressionType' - description: 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"). Exclusions: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: 'A string containing a JSON list of Unix-style glob patterns to exclude. For example, "[\"**.pdf\"]" excludes all PDF files. ' GroupSize: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. GroupFiles: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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". Recurse: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: If set to true, recursively reads files in all subdirectories under the specified paths. MaxBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. MaxFilesInBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3DirectSourceAdditionalOptions' - description: Specifies additional connection options. JsonPath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A JsonPath string defining the JSON data. Multiline: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: 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. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the S3 JSON source. description: Specifies a JSON data store stored in Amazon S3. NullCheckBoxList: type: object properties: IsEmpty: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Specifies that an empty string is considered as a null value. IsNullString: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Specifies that a value spelling out the word 'null' is considered as a null value. IsNegOne: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Specifies that an integer value of -1 is considered as a null value. description: Represents whether certain values are recognized as null values for removal. FilterValues: type: array items: $ref: '#/components/schemas/FilterValue' LimitedStringList: type: array items: $ref: '#/components/schemas/GenericLimitedString' AthenaConnectorSource: type: object required: - Name - ConnectionName - ConnectorName - ConnectionType - SchemaName properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection that is associated with the connector. ConnectorName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of a connector that assists with accessing the data store in Glue Studio. ConnectionType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of connection, such as marketplace.athena or custom.athena, designating a connection to an Amazon Athena data store. ConnectionTable: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertyWithQuote' - description: The name of the table in the data source. SchemaName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the Cloudwatch log group to read from. For example, /aws-glue/jobs/output. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the custom Athena source. description: Specifies a connector to an Amazon Athena data source. S3CsvSource: type: object required: - Name - Paths - Separator - QuoteChar properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Paths: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A list of the Amazon S3 paths to read from. CompressionType: allOf: - $ref: '#/components/schemas/CompressionType' - description: 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"). Exclusions: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: 'A string containing a JSON list of Unix-style glob patterns to exclude. For example, "[\"**.pdf\"]" excludes all PDF files. ' GroupSize: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. GroupFiles: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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". Recurse: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: If set to true, recursively reads files in all subdirectories under the specified paths. MaxBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. MaxFilesInBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3DirectSourceAdditionalOptions' - description: Specifies additional connection options. Separator: allOf: - $ref: '#/components/schemas/Separator' - description: 'Specifies the delimiter character. The default is a comma: ",", but any other character can be specified.' Escaper: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertyWithQuote' - description: 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). QuoteChar: allOf: - $ref: '#/components/schemas/QuoteChar' - description: 'Specifies the character to use for quoting. The default is a double quote: ''"''. Set this to -1 to turn off quoting entirely.' Multiline: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: 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. WithHeader: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: A Boolean value that specifies whether to treat the first line as a header. The default value is False. WriteHeader: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: 'A Boolean value that specifies whether to write the header to output. The default value is True. ' SkipFirst: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: A Boolean value that specifies whether to skip the first data line. The default value is False. OptimizePerformance: allOf: - $ref: '#/components/schemas/BooleanValue' - description: 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. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the S3 CSV source. description: Specifies a command-separated value (CSV) data store stored in Amazon S3. DropFields: type: object required: - Name - Inputs - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Paths: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: A JSON path to a variable in the data structure. description: Specifies a transform that chooses the data property keys that you want to drop. CompressionType: type: string enum: - gzip - bzip2 NullableDouble: type: number format: double FilterExpressions: type: array items: $ref: '#/components/schemas/FilterExpression' SelectFields: type: object required: - Name - Inputs - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Paths: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: A JSON path to a variable in the data structure. description: Specifies a transform that chooses the data property keys that you want to keep. BooleanValue: type: boolean SourceControlAuthStrategy: type: string enum: - PERSONAL_ACCESS_TOKEN - AWS_SECRETS_MANAGER CatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a data store in the Glue Data Catalog. NullValueField: type: object required: - Value - Datatype properties: Value: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The value of the null placeholder. Datatype: allOf: - $ref: '#/components/schemas/Datatype' - description: The datatype of the value. description: Represents a custom null value such as a zeros or other value being used as a null placeholder unique to the dataset. RedshiftTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. RedshiftTmpDir: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon S3 path where temporary data can be staged when copying out of the database. TmpDirIAMRole: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The IAM role with permissions. UpsertRedshiftOptions: allOf: - $ref: '#/components/schemas/UpsertRedshiftTargetOptions' - description: The set of options to configure an upsert operation when writing to a Redshift target. description: Specifies a target that uses Amazon Redshift. GenericString: type: string DirectKinesisSource: type: object required: - Name properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. WindowSize: allOf: - $ref: '#/components/schemas/BoxedPositiveInt' - description: The amount of time to spend processing each micro batch. DetectSchema: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to automatically determine the schema from the incoming data. StreamingOptions: allOf: - $ref: '#/components/schemas/KinesisStreamingSourceOptions' - description: Additional options for the Kinesis streaming data source. DataPreviewOptions: allOf: - $ref: '#/components/schemas/StreamingDataPreviewOptions' - description: Additional options for data preview. description: Specifies a direct Amazon Kinesis data source. AggFunction: type: string enum: - avg - countDistinct - count - first - last - kurtosis - max - min - skewness - stddev_samp - stddev_pop - sum - sumDistinct - var_samp - var_pop NodeId: type: string pattern: '[A-Za-z0-9_-]*' Filter: type: object required: - Name - Inputs - LogicalOperator - Filters properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. LogicalOperator: allOf: - $ref: '#/components/schemas/FilterLogicalOperator' - description: The operator used to filter rows by comparing the key value to a specified value. Filters: allOf: - $ref: '#/components/schemas/FilterExpressions' - description: Specifies a filter expression. description: Specifies a transform that splits a dataset into two, based on a filter condition. GlueSchema: type: object properties: Columns: allOf: - $ref: '#/components/schemas/GlueStudioSchemaColumnList' - description: Specifies the column definitions that make up a Glue schema. description: Specifies a user-defined schema when a schema cannot be determined by Glue. MaskValue: type: string pattern: '[*A-Za-z0-9_-]*' minLength: 0 maxLength: 256 BoxedNonNegativeInt: type: integer minimum: 0 JDBCConnectorTarget: type: object required: - Name - Inputs - ConnectionName - ConnectionTable - ConnectorName - ConnectionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection that is associated with the connector. ConnectionTable: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertyWithQuote' - description: The name of the table in the data target. ConnectorName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of a connector that will be used. ConnectionType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of connection, such as marketplace.jdbc or custom.jdbc, designating a connection to a JDBC data target. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Additional connection options for the connector. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the JDBC target. description: Specifies a data target that writes to Amazon S3 in Apache Parquet columnar storage. GlueStudioSchemaColumn: type: object required: - Name properties: Name: allOf: - $ref: '#/components/schemas/GlueStudioColumnNameString' - description: The name of the column in the Glue Studio schema. Type: allOf: - $ref: '#/components/schemas/ColumnTypeString' - description: The hive type for this column in the Glue Studio schema. description: Specifies a single column in a Glue schema definition. TargetFormat: type: string enum: - json - csv - avro - orc - parquet - hudi - delta LimitedPathList: type: array items: $ref: '#/components/schemas/LimitedStringList' DescriptionString: type: string minLength: 0 maxLength: 2048 x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\r\n\t]*' MicrosoftSQLServerCatalogTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. description: Specifies a target that uses Microsoft SQL. S3DirectTarget: type: object required: - Name - Inputs - Path - Format properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A single Amazon S3 path to write to. Compression: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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"). Format: allOf: - $ref: '#/components/schemas/TargetFormat' - description: Specifies the data output format for the target. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/DirectSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a data target that writes to Amazon S3. GlueRecordType: type: string enum: - DATE - STRING - TIMESTAMP - INT - FLOAT - LONG - BIGDECIMAL - BYTE - SHORT - DOUBLE RoleString: type: string JoinType: type: string enum: - equijoin - left - right - outer - leftsemi - leftanti S3DeltaDirectTarget: type: object required: - Name - Inputs - Path - Compression - Format properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon S3 path of your Delta Lake data source to write to. Compression: allOf: - $ref: '#/components/schemas/DeltaTargetCompressionType' - description: 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"). Format: allOf: - $ref: '#/components/schemas/TargetFormat' - description: Specifies the data output format for the target. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options for the connector. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/DirectSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a target that writes to a Delta Lake data source in Amazon S3. DynamoDBCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a DynamoDB data source in the Glue Data Catalog. Join: type: object required: - Name - Inputs - JoinType - Columns properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/TwoInputs' - description: The data inputs identified by their node names. JoinType: allOf: - $ref: '#/components/schemas/JoinType' - description: Specifies the type of join to be performed on the datasets. Columns: allOf: - $ref: '#/components/schemas/JoinColumns' - description: A list of the two columns to be joined. description: 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. DropNullFields: type: object required: - Name - Inputs properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. NullCheckBoxList: allOf: - $ref: '#/components/schemas/NullCheckBoxList' - description: A structure that represents whether certain values are recognized as null values for removal. NullTextList: allOf: - $ref: '#/components/schemas/NullValueFields' - description:

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.

description: 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. DynamicTransform: type: object required: - Name - TransformName - Inputs - FunctionName - Path properties: Name: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the name of the dynamic transform. TransformName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the name of the dynamic transform as it appears in the Glue Studio visual editor. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: Specifies the inputs for the dynamic transform that are required. Parameters: allOf: - $ref: '#/components/schemas/TransformConfigParameterList' - description: Specifies the parameters of the dynamic transform. FunctionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the name of the function of the dynamic transform. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the path of the dynamic transform source and config files. Version: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: This field is not used and will be deprecated in future release. description: Specifies the set of parameters needed to perform the dynamic transform. SparkConnectorTarget: type: object required: - Name - Inputs - ConnectionName - ConnectorName - ConnectionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of a connection for an Apache Spark connector. ConnectorName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of an Apache Spark connector. ConnectionType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of connection, such as marketplace.spark or custom.spark, designating a connection to an Apache Spark data store. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Additional connection options for the connector. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the custom spark target. description: Specifies a target that uses an Apache Spark connector. MicrosoftSQLServerCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a Microsoft SQL server data source in the Glue Data Catalog. EnclosedInStringPropertiesMinOne: type: array items: $ref: '#/components/schemas/EnclosedInStringProperty' IntegerValue: type: integer ConnectionsList: type: object properties: Connections: allOf: - $ref: '#/components/schemas/OrchestrationStringList' - description: A list of connections used by the job. description: Specifies the connections used by a job. WorkerType: type: string enum: - Standard - G.1X - G.2X - G.025X DQResultsPublishingOptions: type: object properties: EvaluationContext: allOf: - $ref: '#/components/schemas/GenericLimitedString' - description: The context of the evaluation. ResultsS3Prefix: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon S3 prefix prepended to the results. CloudWatchMetricsEnabled: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Enable metrics for your data quality results. ResultsPublishingEnabled: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Enable publishing for your data quality results. description: Options to configure how your data quality evaluation results are published. S3ParquetSource: type: object required: - Name - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Paths: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A list of the Amazon S3 paths to read from. CompressionType: allOf: - $ref: '#/components/schemas/ParquetCompressionType' - description: 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"). Exclusions: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: 'A string containing a JSON list of Unix-style glob patterns to exclude. For example, "[\"**.pdf\"]" excludes all PDF files. ' GroupSize: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. GroupFiles: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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". Recurse: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: If set to true, recursively reads files in all subdirectories under the specified paths. MaxBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. MaxFilesInBand: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3DirectSourceAdditionalOptions' - description: Specifies additional connection options. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the S3 Parquet source. description: Specifies an Apache Parquet data store stored in Amazon S3. ExecutionProperty: type: object properties: MaxConcurrentRuns: allOf: - $ref: '#/components/schemas/MaxConcurrentRuns' - description: 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. description: An execution property of a job. CodeGenConfigurationNode: type: object properties: AthenaConnectorSource: allOf: - $ref: '#/components/schemas/AthenaConnectorSource' - description: Specifies a connector to an Amazon Athena data source. JDBCConnectorSource: allOf: - $ref: '#/components/schemas/JDBCConnectorSource' - description: Specifies a connector to a JDBC data source. SparkConnectorSource: allOf: - $ref: '#/components/schemas/SparkConnectorSource' - description: Specifies a connector to an Apache Spark data source. CatalogSource: allOf: - $ref: '#/components/schemas/CatalogSource' - description: Specifies a data store in the Glue Data Catalog. RedshiftSource: allOf: - $ref: '#/components/schemas/RedshiftSource' - description: Specifies an Amazon Redshift data store. S3CatalogSource: allOf: - $ref: '#/components/schemas/S3CatalogSource' - description: Specifies an Amazon S3 data store in the Glue Data Catalog. S3CsvSource: allOf: - $ref: '#/components/schemas/S3CsvSource' - description: Specifies a command-separated value (CSV) data store stored in Amazon S3. S3JsonSource: allOf: - $ref: '#/components/schemas/S3JsonSource' - description: Specifies a JSON data store stored in Amazon S3. S3ParquetSource: allOf: - $ref: '#/components/schemas/S3ParquetSource' - description: Specifies an Apache Parquet data store stored in Amazon S3. RelationalCatalogSource: allOf: - $ref: '#/components/schemas/RelationalCatalogSource' - description: Specifies a relational catalog data store in the Glue Data Catalog. DynamoDBCatalogSource: allOf: - $ref: '#/components/schemas/DynamoDBCatalogSource' - description: Specifies a DynamoDBC Catalog data store in the Glue Data Catalog. JDBCConnectorTarget: allOf: - $ref: '#/components/schemas/JDBCConnectorTarget' - description: Specifies a data target that writes to Amazon S3 in Apache Parquet columnar storage. SparkConnectorTarget: allOf: - $ref: '#/components/schemas/SparkConnectorTarget' - description: Specifies a target that uses an Apache Spark connector. CatalogTarget: allOf: - $ref: '#/components/schemas/BasicCatalogTarget' - description: Specifies a target that uses a Glue Data Catalog table. RedshiftTarget: allOf: - $ref: '#/components/schemas/RedshiftTarget' - description: Specifies a target that uses Amazon Redshift. S3CatalogTarget: allOf: - $ref: '#/components/schemas/S3CatalogTarget' - description: Specifies a data target that writes to Amazon S3 using the Glue Data Catalog. S3GlueParquetTarget: allOf: - $ref: '#/components/schemas/S3GlueParquetTarget' - description: Specifies a data target that writes to Amazon S3 in Apache Parquet columnar storage. S3DirectTarget: allOf: - $ref: '#/components/schemas/S3DirectTarget' - description: Specifies a data target that writes to Amazon S3. ApplyMapping: allOf: - $ref: '#/components/schemas/ApplyMapping' - description: 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. SelectFields: allOf: - $ref: '#/components/schemas/SelectFields' - description: Specifies a transform that chooses the data property keys that you want to keep. DropFields: allOf: - $ref: '#/components/schemas/DropFields' - description: Specifies a transform that chooses the data property keys that you want to drop. RenameField: allOf: - $ref: '#/components/schemas/RenameField' - description: Specifies a transform that renames a single data property key. Spigot: allOf: - $ref: '#/components/schemas/Spigot' - description: Specifies a transform that writes samples of the data to an Amazon S3 bucket. Join: allOf: - $ref: '#/components/schemas/Join' - description: 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. SplitFields: allOf: - $ref: '#/components/schemas/SplitFields' - description: '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.' SelectFromCollection: allOf: - $ref: '#/components/schemas/SelectFromCollection' - description: 'Specifies a transform that chooses one DynamicFrame from a collection of DynamicFrames. The output is the selected DynamicFrame ' FillMissingValues: allOf: - $ref: '#/components/schemas/FillMissingValues' - description: 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. Filter: allOf: - $ref: '#/components/schemas/Filter' - description: Specifies a transform that splits a dataset into two, based on a filter condition. CustomCode: allOf: - $ref: '#/components/schemas/CustomCode' - description: Specifies a transform that uses custom code you provide to perform the data transformation. The output is a collection of DynamicFrames. SparkSQL: allOf: - $ref: '#/components/schemas/SparkSQL' - description: Specifies a transform where you enter a SQL query using Spark SQL syntax to transform the data. The output is a single DynamicFrame. DirectKinesisSource: allOf: - $ref: '#/components/schemas/DirectKinesisSource' - description: Specifies a direct Amazon Kinesis data source. DirectKafkaSource: allOf: - $ref: '#/components/schemas/DirectKafkaSource' - description: Specifies an Apache Kafka data store. CatalogKinesisSource: allOf: - $ref: '#/components/schemas/CatalogKinesisSource' - description: Specifies a Kinesis data source in the Glue Data Catalog. CatalogKafkaSource: allOf: - $ref: '#/components/schemas/CatalogKafkaSource' - description: Specifies an Apache Kafka data store in the Data Catalog. DropNullFields: allOf: - $ref: '#/components/schemas/DropNullFields' - description: 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. Merge: allOf: - $ref: '#/components/schemas/Merge' - description: '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. ' Union: allOf: - $ref: '#/components/schemas/Union' - description: Specifies a transform that combines the rows from two or more datasets into a single result. PIIDetection: allOf: - $ref: '#/components/schemas/PIIDetection' - description: Specifies a transform that identifies, removes or masks PII data. Aggregate: allOf: - $ref: '#/components/schemas/Aggregate' - description: Specifies a transform that groups rows by chosen fields and computes the aggregated value by specified function. DropDuplicates: allOf: - $ref: '#/components/schemas/DropDuplicates' - description: Specifies a transform that removes rows of repeating data from a data set. GovernedCatalogTarget: allOf: - $ref: '#/components/schemas/GovernedCatalogTarget' - description: Specifies a data target that writes to a goverened catalog. GovernedCatalogSource: allOf: - $ref: '#/components/schemas/GovernedCatalogSource' - description: Specifies a data source in a goverened Data Catalog. MicrosoftSQLServerCatalogSource: allOf: - $ref: '#/components/schemas/MicrosoftSQLServerCatalogSource' - description: Specifies a Microsoft SQL server data source in the Glue Data Catalog. MySQLCatalogSource: allOf: - $ref: '#/components/schemas/MySQLCatalogSource' - description: Specifies a MySQL data source in the Glue Data Catalog. OracleSQLCatalogSource: allOf: - $ref: '#/components/schemas/OracleSQLCatalogSource' - description: Specifies an Oracle data source in the Glue Data Catalog. PostgreSQLCatalogSource: allOf: - $ref: '#/components/schemas/PostgreSQLCatalogSource' - description: Specifies a PostgresSQL data source in the Glue Data Catalog. MicrosoftSQLServerCatalogTarget: allOf: - $ref: '#/components/schemas/MicrosoftSQLServerCatalogTarget' - description: Specifies a target that uses Microsoft SQL. MySQLCatalogTarget: allOf: - $ref: '#/components/schemas/MySQLCatalogTarget' - description: Specifies a target that uses MySQL. OracleSQLCatalogTarget: allOf: - $ref: '#/components/schemas/OracleSQLCatalogTarget' - description: Specifies a target that uses Oracle SQL. PostgreSQLCatalogTarget: allOf: - $ref: '#/components/schemas/PostgreSQLCatalogTarget' - description: Specifies a target that uses Postgres SQL. DynamicTransform: allOf: - $ref: '#/components/schemas/DynamicTransform' - description: Specifies a custom visual transform created by a user. EvaluateDataQuality: allOf: - $ref: '#/components/schemas/EvaluateDataQuality' - description: Specifies your data quality evaluation criteria. S3CatalogHudiSource: allOf: - $ref: '#/components/schemas/S3CatalogHudiSource' - description: Specifies a Hudi data source that is registered in the Glue Data Catalog. The data source must be stored in Amazon S3. CatalogHudiSource: allOf: - $ref: '#/components/schemas/CatalogHudiSource' - description: Specifies a Hudi data source that is registered in the Glue Data Catalog. S3HudiSource: allOf: - $ref: '#/components/schemas/S3HudiSource' - description: Specifies a Hudi data source stored in Amazon S3. S3HudiCatalogTarget: allOf: - $ref: '#/components/schemas/S3HudiCatalogTarget' - description: Specifies a target that writes to a Hudi data source in the Glue Data Catalog. S3HudiDirectTarget: allOf: - $ref: '#/components/schemas/S3HudiDirectTarget' - description: Specifies a target that writes to a Hudi data source in Amazon S3. DirectJDBCSource: $ref: '#/components/schemas/DirectJDBCSource' S3CatalogDeltaSource: allOf: - $ref: '#/components/schemas/S3CatalogDeltaSource' - description: Specifies a Delta Lake data source that is registered in the Glue Data Catalog. The data source must be stored in Amazon S3. CatalogDeltaSource: allOf: - $ref: '#/components/schemas/CatalogDeltaSource' - description: Specifies a Delta Lake data source that is registered in the Glue Data Catalog. S3DeltaSource: allOf: - $ref: '#/components/schemas/S3DeltaSource' - description: Specifies a Delta Lake data source stored in Amazon S3. S3DeltaCatalogTarget: allOf: - $ref: '#/components/schemas/S3DeltaCatalogTarget' - description: Specifies a target that writes to a Delta Lake data source in the Glue Data Catalog. S3DeltaDirectTarget: allOf: - $ref: '#/components/schemas/S3DeltaDirectTarget' - description: Specifies a target that writes to a Delta Lake data source in Amazon S3. description: ' CodeGenConfigurationNode enumerates all valid Node types. One and only one of its member variables can be populated.' Generic512CharString: type: string minLength: 1 maxLength: 512 NonNegativeInt: type: integer minimum: 0 GetJobsResponse: type: object properties: Jobs: allOf: - $ref: '#/components/schemas/JobList' - description: A list of job definitions. NextToken: allOf: - $ref: '#/components/schemas/GenericString' - description: A continuation token, if not all job definitions have yet been returned. RenameField: type: object required: - Name - Inputs - SourcePath - TargetPath properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. SourcePath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A JSON path to a variable in the data structure for the source data. TargetPath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A JSON path to a variable in the data structure for the target data. description: Specifies a transform that renames a single data property key. MySQLCatalogTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. description: Specifies a target that uses MySQL. S3HudiSource: type: object required: - Name - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Hudi source. Paths: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A list of the Amazon S3 paths to read from. AdditionalHudiOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3DirectSourceAdditionalOptions' - description: Specifies additional options for the connector. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Hudi source. description: Specifies a Hudi data source stored in Amazon S3. FilterValueType: type: string enum: - COLUMNEXTRACTED - CONSTANT JoinColumn: type: object required: - From - Keys properties: From: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The column to be joined. Keys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: The key of the column to be joined. description: Specifies a column to be joined. CatalogDeltaSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Delta Lake data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. AdditionalDeltaOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Delta Lake source. description: Specifies a Delta Lake data source that is registered in the Glue Data Catalog. CatalogSchemaChangePolicy: type: object properties: EnableUpdateCatalog: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to use the specified update behavior when the crawler finds a changed schema. UpdateBehavior: allOf: - $ref: '#/components/schemas/UpdateCatalogBehavior' - description: The update behavior when the crawler finds a changed schema. description: A policy that specifies update behavior for the crawler. AggregateOperations: type: array items: $ref: '#/components/schemas/AggregateOperation' minItems: 1 maxItems: 30 OrchestrationStringList: type: array items: $ref: '#/components/schemas/GenericString' MaxRetries: type: integer CatalogHudiSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Hudi data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. AdditionalHudiOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Hudi source. description: Specifies a Hudi data source that is registered in the Glue Data Catalog. S3GlueParquetTarget: type: object required: - Name - Inputs - Path properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A single Amazon S3 path to write to. Compression: allOf: - $ref: '#/components/schemas/ParquetCompressionType' - description: 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"). SchemaChangePolicy: allOf: - $ref: '#/components/schemas/DirectSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a data target that writes to Amazon S3 in Apache Parquet columnar storage. JobCommand: type: object properties: Name: allOf: - $ref: '#/components/schemas/GenericString' - description: 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. ScriptLocation: allOf: - $ref: '#/components/schemas/ScriptLocationString' - description: Specifies the Amazon Simple Storage Service (Amazon S3) path to a script that runs a job. PythonVersion: allOf: - $ref: '#/components/schemas/PythonVersionString' - description: The Python version being used to run a Python shell job. Allowed values are 2 or 3. description: Specifies code that runs when a job is run. CatalogKafkaSource: type: object required: - Name - Table - Database properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. WindowSize: allOf: - $ref: '#/components/schemas/BoxedPositiveInt' - description: The amount of time to spend processing each micro batch. DetectSchema: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to automatically determine the schema from the incoming data. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. StreamingOptions: allOf: - $ref: '#/components/schemas/KafkaStreamingSourceOptions' - description: Specifies the streaming options. DataPreviewOptions: allOf: - $ref: '#/components/schemas/StreamingDataPreviewOptions' - description: Specifies options related to data preview for viewing a sample of your data. description: Specifies an Apache Kafka data store in the Data Catalog. DQTransformOutput: type: string enum: - PrimaryInput - EvaluationResults Spigot: type: object required: - Name - Inputs - Path properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. Topk: allOf: - $ref: '#/components/schemas/Topk' - description: Specifies a number of records to write starting from the beginning of the dataset. Prob: allOf: - $ref: '#/components/schemas/Prob' - description: 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. description: Specifies a transform that writes samples of the data to an Amazon S3 bucket. SplitFields: type: object required: - Name - Inputs - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Paths: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: A JSON path to a variable in the data structure. description: '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.' SourceControlDetails: type: object properties: Provider: allOf: - $ref: '#/components/schemas/SourceControlProvider' - description: The provider for the remote repository. Repository: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: The name of the remote repository that contains the job artifacts. Owner: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: The owner of the remote repository that contains the job artifacts. Branch: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: An optional branch in the remote repository. Folder: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: An optional folder in the remote repository. LastCommitId: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: The last commit ID for a commit in the remote repository. AuthStrategy: allOf: - $ref: '#/components/schemas/SourceControlAuthStrategy' - description: The type of authentication, which can be an authentication token stored in Amazon Web Services Secrets Manager, or a personal access token. AuthToken: allOf: - $ref: '#/components/schemas/Generic512CharString' - description: The value of an authorization token. description: The details for a source control configuration for a job, allowing synchronization of job artifacts to or from a remote repository. FilterLogicalOperator: type: string enum: - AND - OR HudiTargetCompressionType: type: string enum: - gzip - lzo - uncompressed - snappy OracleSQLCatalogTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. description: Specifies a target that uses Oracle SQL. EnclosedInStringProperty: type: string x-pattern: \([\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF]\|[^\S\r\n"']\)* UnionType: type: string enum: - ALL - DISTINCT DQStopJobOnFailureTiming: type: string enum: - Immediate - AfterDataLoad PiiType: type: string enum: - RowAudit - RowMasking - ColumnAudit - ColumnMasking JoinColumns: type: array items: $ref: '#/components/schemas/JoinColumn' minItems: 2 maxItems: 2 PositiveLong: type: integer minimum: 1 CustomCode: type: object required: - Name - Inputs - Code - ClassName properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/ManyInputs' - description: The data inputs identified by their node names. Code: allOf: - $ref: '#/components/schemas/ExtendedString' - description: The custom code that is used to perform the data transformation. ClassName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name defined for the custom code node class. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the custom code transform. description: Specifies a transform that uses custom code you provide to perform the data transformation. The output is a collection of DynamicFrames. S3DeltaSource: type: object required: - Name - Paths properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Delta Lake source. Paths: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: A list of the Amazon S3 paths to read from. AdditionalDeltaOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3DirectSourceAdditionalOptions' - description: Specifies additional options for the connector. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Delta Lake source. description: Specifies a Delta Lake data source stored in Amazon S3. ExtendedString: type: string pattern: '[\s\S]*' EntityNotFoundException: {} EnclosedInStringPropertyWithQuote: type: string x-pattern: \([\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF]\|[^\S\r\n]\)* NodeName: type: string x-pattern: \([\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF]\|[^\r\n]\)* Mappings: type: array items: $ref: '#/components/schemas/Mapping' GovernedCatalogTarget: type: object required: - Name - Inputs - Table - Database properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/CatalogSchemaChangePolicy' - description: A policy that specifies update behavior for the governed catalog. description: Specifies a data target that writes to Amazon S3 using the Glue Data Catalog. Union: type: object required: - Name - Inputs - UnionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/TwoInputs' - description: The node ID inputs to the transform. UnionType: allOf: - $ref: '#/components/schemas/UnionType' - description:

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.

description: Specifies a transform that combines the rows from two or more datasets into a single result. PythonVersionString: type: string pattern: ^([2-3]|3[.]9)$ JobList: type: array items: $ref: '#/components/schemas/Job' ParquetCompressionType: type: string enum: - snappy - lzo - gzip - uncompressed - none UpdateCatalogBehavior: type: string enum: - UPDATE_IN_DATABASE - LOG DQStopJobOnFailureOptions: type: object properties: StopJobOnFailureTiming: allOf: - $ref: '#/components/schemas/DQStopJobOnFailureTiming' - description: When to stop job if your data quality evaluation fails. Options are Immediate or AfterDataLoad. description: Options to configure how your job will stop if your data quality evaluation fails. PIIDetection: type: object required: - Name - Inputs - PiiType - EntityTypesToDetect properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The node ID inputs to the transform. PiiType: allOf: - $ref: '#/components/schemas/PiiType' - description: 'Indicates the type of PIIDetection transform. ' EntityTypesToDetect: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: '

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

' OutputColumnName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 'Indicates the output column name that will contain any entity type detected in that row. ' SampleFraction: allOf: - $ref: '#/components/schemas/BoxedDoubleFraction' - description: 'Indicates the fraction of the data to sample when scanning for PII entities. ' ThresholdFraction: allOf: - $ref: '#/components/schemas/BoxedDoubleFraction' - description: 'Indicates the fraction of the data that must be met in order for a column to be identified as PII data. ' MaskValue: allOf: - $ref: '#/components/schemas/MaskValue' - description: 'Indicates the value that will replace the detected entity. ' description: Specifies a transform that identifies, removes or masks PII data. KafkaStreamingSourceOptions: type: object properties: BootstrapServers: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. SecurityProtocol: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The protocol used to communicate with brokers. The possible values are "SSL" or "PLAINTEXT". ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection. TopicName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The topic name as specified in Apache Kafka. You must specify at least one of "topicName", "assign" or "subscribePattern". Assign: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The specific TopicPartitions to consume. You must specify at least one of "topicName", "assign" or "subscribePattern". SubscribePattern: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A Java regex string that identifies the topic list to subscribe to. You must specify at least one of "topicName", "assign" or "subscribePattern". Classification: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: An optional classification. Delimiter: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the delimiter character. StartingOffsets: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The starting position in the Kafka topic to read data from. The possible values are "earliest" or "latest". The default value is "latest". EndingOffsets: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. PollTimeoutMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The timeout in milliseconds to poll data from Kafka in Spark job executors. The default value is 512. NumRetries: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: The number of times to retry before failing to fetch Kafka offsets. The default value is 3. RetryIntervalMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The time in milliseconds to wait before retrying to fetch Kafka offsets. The default value is 10. MaxOffsetsPerTrigger: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: 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. MinPartitions: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: 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. IncludeHeaders: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: '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.' AddRecordTimestamp: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. EmitConsumerLagMetrics: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. description: Additional options for streaming. GlueStudioSchemaColumnList: type: array items: $ref: '#/components/schemas/GlueStudioSchemaColumn' NullValueFields: type: array items: $ref: '#/components/schemas/NullValueField' minItems: 0 maxItems: 50 S3CatalogHudiSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Hudi data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. AdditionalHudiOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the Hudi source. description: Specifies a Hudi data source that is registered in the Glue Data Catalog. The Hudi data source must be stored in Amazon S3. SparkSQL: type: object required: - Name - Inputs - SqlQuery - SqlAliases properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/ManyInputs' - description: 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. SqlQuery: allOf: - $ref: '#/components/schemas/SqlQuery' - description: A SQL query that must use Spark SQL syntax and return a single data set. SqlAliases: allOf: - $ref: '#/components/schemas/SqlAliases' - description:

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.

OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies the data schema for the SparkSQL transform. description: Specifies a transform where you enter a SQL query using Spark SQL syntax to transform the data. The output is a single DynamicFrame. Timeout: type: integer minimum: 1 FilterExpression: type: object required: - Operation - Values properties: Operation: allOf: - $ref: '#/components/schemas/FilterOperation' - description: The type of operation to perform in the expression. Negated: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether the expression is to be negated. Values: allOf: - $ref: '#/components/schemas/FilterValues' - description: A list of filter values. description: Specifies a filter expression. UriString: type: string GenericLimitedString: type: string pattern: '[A-Za-z0-9_-]*' UpsertRedshiftTargetOptions: type: object properties: TableLocation: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The physical location of the Redshift table. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection to use to write to Redshift. UpsertKeys: allOf: - $ref: '#/components/schemas/EnclosedInStringPropertiesMinOne' - description: The keys used to determine whether to perform an update or insert. description: The options to configure an upsert operation when writing to a Redshift target . Merge: type: object required: - Name - Inputs - Source - PrimaryKeys properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/TwoInputs' - description: The data inputs identified by their node names. Source: allOf: - $ref: '#/components/schemas/NodeId' - description: The source DynamicFrame that will be merged with a staging DynamicFrame. PrimaryKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: The list of primary key fields to match records from the source and staging dynamic frames. description: '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. ' FilterOperation: type: string enum: - EQ - LT - GT - LTE - GTE - REGEX - ISNULL SelectFromCollection: type: object required: - Name - Inputs - Index properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Index: allOf: - $ref: '#/components/schemas/NonNegativeInt' - description: The index for the DynamicFrame to be selected. description: 'Specifies a transform that chooses one DynamicFrame from a collection of DynamicFrames. The output is the selected DynamicFrame ' RedshiftSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the Amazon Redshift data store. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database table to read from. RedshiftTmpDir: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon S3 path where temporary data can be staged when copying out of the database. TmpDirIAMRole: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The IAM role with permissions. description: Specifies an Amazon Redshift data store. JDBCConnectionType: type: string enum: - sqlserver - mysql - oracle - postgresql - redshift GlueVersionString: type: string pattern: ^\w+\.\w+$ minLength: 1 maxLength: 255 KinesisStreamingSourceOptions: type: object properties: EndpointUrl: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The URL of the Kinesis endpoint. StreamName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the Kinesis data stream. Classification: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: An optional classification. Delimiter: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the delimiter character. StartingPosition: allOf: - $ref: '#/components/schemas/StartingPosition' - description: The starting position in the Kinesis data stream to read data from. The possible values are "latest", "trim_horizon", or "earliest". The default value is "latest". MaxFetchTimeInMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: 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. MaxFetchRecordsPerShard: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The maximum number of records to fetch per shard in the Kinesis data stream. The default value is 100000. MaxRecordPerRead: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The maximum number of records to fetch from the Kinesis data stream in each getRecords operation. The default value is 10000. AddIdleTimeBetweenReads: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: 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. IdleTimeBetweenReadsInMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: 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. DescribeShardInterval: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The minimum time interval between two ListShards API calls for your script to consider resharding. The default value is 1s. NumRetries: allOf: - $ref: '#/components/schemas/BoxedNonNegativeInt' - description: The maximum number of retries for Kinesis Data Streams API requests. The default value is 3. RetryIntervalMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The cool-off time period (specified in ms) before retrying the Kinesis Data Streams API call. The default value is 1000. MaxRetryIntervalMs: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The maximum cool-off time period (specified in ms) between two retries of a Kinesis Data Streams API call. The default value is 10000. AvoidEmptyBatches: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: 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". StreamArn: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon Resource Name (ARN) of the Kinesis data stream. RoleArn: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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". RoleSessionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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". AddRecordTimestamp: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. EmitConsumerLagMetrics: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. description: Additional options for the Amazon Kinesis streaming data source. RelationalCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a Relational database data source in the Glue Data Catalog. Mapping: type: object properties: ToKey: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: After the apply mapping, what the name of the column should be. Can be the same as FromPath. FromPath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: The table or column to be modified. FromType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of the data to be modified. ToType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The data type that the data is to be modified to. Dropped: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: If true, then the column is removed. Children: allOf: - $ref: '#/components/schemas/Mappings' - description: '

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, }] }

' description: Specifies the mapping of data property keys. TimestampValue: type: string format: date-time NameString: type: string minLength: 1 maxLength: 255 x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\t]*' FillMissingValues: type: object required: - Name - Inputs - ImputedPath properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. ImputedPath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A JSON path to a variable in the data structure for the dataset that is imputed. FilledPath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: A JSON path to a variable in the data structure for the dataset that is filled. description: 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. InvalidInputException: {} SqlAliases: type: array items: $ref: '#/components/schemas/SqlAlias' TransformConfigParameter: type: object required: - Name - Type properties: Name: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the name of the parameter in the config file of the dynamic transform. Type: allOf: - $ref: '#/components/schemas/ParamType' - description: Specifies the parameter type in the config file of the dynamic transform. ValidationRule: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the validation rule in the config file of the dynamic transform. ValidationMessage: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the validation message in the config file of the dynamic transform. Value: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: Specifies the value of the parameter in the config file of the dynamic transform. ListType: allOf: - $ref: '#/components/schemas/ParamType' - description: Specifies the list type of the parameter in the config file of the dynamic transform. IsOptional: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Specifies whether the parameter is optional or not in the config file of the dynamic transform. description: Specifies the parameters in the config file of the dynamic transform. BoxedDoubleFraction: type: number format: double minimum: 0 maximum: 1 Datatype: type: object required: - Id - Label properties: Id: allOf: - $ref: '#/components/schemas/GenericLimitedString' - description: The datatype of the value. Label: allOf: - $ref: '#/components/schemas/GenericLimitedString' - description: A label assigned to the datatype. description: A structure representing the datatype of the value. JDBCConnectorOptions: type: object properties: FilterPredicate: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description:

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.

PartitionColumn: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: 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. LowerBound: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The minimum value of partitionColumn that is used to decide partition stride. UpperBound: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: The maximum value of partitionColumn that is used to decide partition stride. NumPartitions: allOf: - $ref: '#/components/schemas/BoxedNonNegativeLong' - description: 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. JobBookmarkKeys: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: The name of the job bookmark keys on which to sort. JobBookmarkKeysSortOrder: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies an ascending or descending sort order. DataTypeMapping: allOf: - $ref: '#/components/schemas/JDBCDataTypeMapping' - description: 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. description: Additional connection options for the connector. ScriptLocationString: type: string maxLength: 400000 S3CatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database table to read from. PartitionPredicate: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Partitions satisfying this predicate are deleted. Files within the retention period in these partitions are not deleted. Set to "" – empty by default. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3SourceAdditionalOptions' - description: Specifies additional connection options. description: Specifies an Amazon S3 data store in the Glue Data Catalog. Separator: type: string enum: - comma - ctrla - pipe - semicolon - tab PollingTime: type: integer minimum: 10 CatalogKinesisSource: type: object required: - Name - Table - Database properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. WindowSize: allOf: - $ref: '#/components/schemas/BoxedPositiveInt' - description: The amount of time to spend processing each micro batch. DetectSchema: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to automatically determine the schema from the incoming data. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. StreamingOptions: allOf: - $ref: '#/components/schemas/KinesisStreamingSourceOptions' - description: Additional options for the Kinesis streaming data source. DataPreviewOptions: allOf: - $ref: '#/components/schemas/StreamingDataPreviewOptions' - description: Additional options for data preview. description: Specifies a Kinesis data source in the Glue Data Catalog. SourceControlProvider: type: string enum: - GITHUB - AWS_CODE_COMMIT InternalServiceException: {} GovernedCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database table to read from. PartitionPredicate: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Partitions satisfying this predicate are deleted. Files within the retention period in these partitions are not deleted. Set to "" – empty by default. AdditionalOptions: allOf: - $ref: '#/components/schemas/S3SourceAdditionalOptions' - description: Specifies additional connection options. description: Specifies the data store in the governed Glue Data Catalog. S3DeltaCatalogTarget: type: object required: - Name - Inputs - Table - Database properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options for the connector. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/CatalogSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a target that writes to a Delta Lake data source in the Glue Data Catalog. DirectKafkaSource: type: object required: - Name properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data store. StreamingOptions: allOf: - $ref: '#/components/schemas/KafkaStreamingSourceOptions' - description: Specifies the streaming options. WindowSize: allOf: - $ref: '#/components/schemas/BoxedPositiveInt' - description: The amount of time to spend processing each micro batch. DetectSchema: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to automatically determine the schema from the incoming data. DataPreviewOptions: allOf: - $ref: '#/components/schemas/StreamingDataPreviewOptions' - description: Specifies options related to data preview for viewing a sample of your data. description: Specifies an Apache Kafka data store. S3CatalogTarget: type: object required: - Name - Inputs - Table - Database properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to write to. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to write to. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/CatalogSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a data target that writes to Amazon S3 using the Glue Data Catalog. NullableInteger: type: integer ManyInputs: type: array items: $ref: '#/components/schemas/NodeId' minItems: 1 BoxedBoolean: type: boolean DropDuplicates: type: object required: - Name - Inputs properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Columns: allOf: - $ref: '#/components/schemas/LimitedPathList' - description: The name of the columns to be merged or removed if repeating. description: 'Specifies a transform that removes rows of repeating data from a data set. ' AggregateOperation: type: object required: - Column - AggFunc properties: Column: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: Specifies the column on the data set on which the aggregation function will be applied. AggFunc: allOf: - $ref: '#/components/schemas/AggFunction' - description: '

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

' description: Specifies the set of parameters needed to perform aggregation in the aggregate transform. MaxConcurrentRuns: type: integer OneInput: type: array items: $ref: '#/components/schemas/NodeId' minItems: 1 maxItems: 1 FilterValue: type: object required: - Type - Value properties: Type: allOf: - $ref: '#/components/schemas/FilterValueType' - description: The type of filter value. Value: allOf: - $ref: '#/components/schemas/EnclosedInStringProperties' - description: The value to be associated. description: 'Represents a single entry in the list of values for a FilterExpression. ' OperationTimeoutException: {} MySQLCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a MySQL data source in the Glue Data Catalog. Prob: type: number format: double minimum: 0 maximum: 1 ExecutionClass: type: string enum: - FLEX - STANDARD maxLength: 16 BoxedLong: type: integer S3DirectSourceAdditionalOptions: type: object properties: BoundedSize: allOf: - $ref: '#/components/schemas/BoxedLong' - description: Sets the upper limit for the target size of the dataset in bytes that will be processed. BoundedFiles: allOf: - $ref: '#/components/schemas/BoxedLong' - description: Sets the upper limit for the target number of files that will be processed. EnableSamplePath: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Sets option to enable a sample path. SamplePath: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: If enabled, specifies the sample path. description: Specifies additional connection options for the Amazon S3 data store. Topk: type: integer minimum: 0 maximum: 100 GenericMap: type: object additionalProperties: $ref: '#/components/schemas/GenericString' JDBCDataTypeMapping: type: object additionalProperties: $ref: '#/components/schemas/GlueRecordType' CodeGenConfigurationNodes: type: object additionalProperties: $ref: '#/components/schemas/CodeGenConfigurationNode' GetJobsRequest: type: object title: GetJobsRequest properties: NextToken: allOf: - $ref: '#/components/schemas/GenericString' - description: A continuation token, if this is a continuation call. MaxResults: allOf: - $ref: '#/components/schemas/PageSize' - description: The maximum size of the response. DirectJDBCSource: type: object required: - Name - Database - Table - ConnectionName - ConnectionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the JDBC source connection. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database of the JDBC source connection. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The table of the JDBC source connection. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The connection name of the JDBC source. ConnectionType: allOf: - $ref: '#/components/schemas/JDBCConnectionType' - description: The connection type of the JDBC source. RedshiftTmpDir: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The temp directory of the JDBC Redshift source. description: Specifies the direct JDBC source connection. S3HudiDirectTarget: type: object required: - Name - Inputs - Path - Compression - Format - AdditionalOptions properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Path: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The Amazon S3 path of your Hudi data source to write to. Compression: allOf: - $ref: '#/components/schemas/HudiTargetCompressionType' - description: 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"). PartitionKeys: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies native partitioning using a sequence of keys. Format: allOf: - $ref: '#/components/schemas/TargetFormat' - description: Specifies the data output format for the target. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Specifies additional connection options for the connector. SchemaChangePolicy: allOf: - $ref: '#/components/schemas/DirectSchemaChangePolicy' - description: A policy that specifies update behavior for the crawler. description: Specifies a target that writes to a Hudi data source in Amazon S3. Aggregate: type: object required: - Name - Inputs - Groups - Aggs properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: Specifies the fields and rows to use as inputs for the aggregate transform. Groups: allOf: - $ref: '#/components/schemas/GlueStudioPathList' - description: Specifies the fields to group by. Aggs: allOf: - $ref: '#/components/schemas/AggregateOperations' - description: 'Specifies the aggregate functions to be performed on specified fields. ' description: Specifies a transform that groups rows by chosen fields and computes the aggregated value by specified function. Job: type: object properties: Name: allOf: - $ref: '#/components/schemas/NameString' - description: The name you assign to this job definition. Description: allOf: - $ref: '#/components/schemas/DescriptionString' - description: A description of the job. LogUri: allOf: - $ref: '#/components/schemas/UriString' - description: This field is reserved for future use. Role: allOf: - $ref: '#/components/schemas/RoleString' - description: The name or Amazon Resource Name (ARN) of the IAM role associated with this job. CreatedOn: allOf: - $ref: '#/components/schemas/TimestampValue' - description: The time and date that this job definition was created. LastModifiedOn: allOf: - $ref: '#/components/schemas/TimestampValue' - description: The last point in time when this job definition was modified. ExecutionProperty: allOf: - $ref: '#/components/schemas/ExecutionProperty' - description: An ExecutionProperty specifying the maximum number of concurrent runs allowed for this job. Command: allOf: - $ref: '#/components/schemas/JobCommand' - description: The JobCommand that runs this job. DefaultArguments: allOf: - $ref: '#/components/schemas/GenericMap' - description:

The default arguments for 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.

For information about how to specify and consume your own Job arguments, see the Calling Glue APIs in Python topic in the developer guide.

For information about the key-value pairs that Glue consumes to set up your job, see the Special Parameters Used by Glue topic in the developer guide.

NonOverridableArguments: allOf: - $ref: '#/components/schemas/GenericMap' - description: Non-overridable arguments for this job, specified as name-value pairs. Connections: allOf: - $ref: '#/components/schemas/ConnectionsList' - description: The connections used for this job. MaxRetries: allOf: - $ref: '#/components/schemas/MaxRetries' - description: The maximum number of times to retry this job after a JobRun fails. AllocatedCapacity: allOf: - $ref: '#/components/schemas/IntegerValue' - deprecated: true description:

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.

This property is deprecated, use MaxCapacity instead. Timeout: allOf: - $ref: '#/components/schemas/Timeout' - description: 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). MaxCapacity: allOf: - $ref: '#/components/schemas/NullableDouble' - description:

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.

Do not set Max Capacity 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:

For Glue version 2.0 jobs, you cannot instead specify a Maximum capacity. Instead, you should specify a Worker type and the Number of workers.

WorkerType: allOf: - $ref: '#/components/schemas/WorkerType' - description:

The type of predefined worker that is allocated when a job runs. Accepts a value of Standard, G.1X, G.2X, or G.025X.

NumberOfWorkers: allOf: - $ref: '#/components/schemas/NullableInteger' - description: The number of workers of a defined workerType that are allocated when a job runs. SecurityConfiguration: allOf: - $ref: '#/components/schemas/NameString' - description: The name of the SecurityConfiguration structure to be used with this job. NotificationProperty: allOf: - $ref: '#/components/schemas/NotificationProperty' - description: Specifies configuration properties of a job notification. GlueVersion: allOf: - $ref: '#/components/schemas/GlueVersionString' - description:

Glue version determines the versions of Apache Spark and Python that Glue supports. The Python version indicates the version supported for jobs of type Spark.

For more information about the available Glue versions and corresponding Spark and Python versions, see Glue version in the developer guide.

Jobs that are created without specifying a Glue version default to Glue 0.9.

CodeGenConfigurationNodes: allOf: - $ref: '#/components/schemas/CodeGenConfigurationNodes' - description: The representation of a directed acyclic graph on which both the Glue Studio visual component and Glue Studio code generation is based. ExecutionClass: allOf: - $ref: '#/components/schemas/ExecutionClass' - description:

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.

SourceControlDetails: allOf: - $ref: '#/components/schemas/SourceControlDetails' - description: The details for a source control configuration for a job, allowing synchronization of job artifacts to or from a remote repository. description: Specifies a job definition. AdditionalOptions: type: object additionalProperties: $ref: '#/components/schemas/EnclosedInStringProperty' StartingPosition: type: string enum: - latest - trim_horizon - earliest SparkConnectorSource: type: object required: - Name - ConnectionName - ConnectorName - ConnectionType properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. ConnectionName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the connection that is associated with the connector. ConnectorName: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of a connector that assists with accessing the data store in Glue Studio. ConnectionType: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The type of connection, such as marketplace.spark or custom.spark, designating a connection to an Apache Spark data store. AdditionalOptions: allOf: - $ref: '#/components/schemas/AdditionalOptions' - description: Additional connection options for the connector. OutputSchemas: allOf: - $ref: '#/components/schemas/GlueSchemas' - description: Specifies data schema for the custom spark source. description: Specifies a connector to an Apache Spark data source. PostgreSQLCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies a PostgresSQL data source in the Glue Data Catalog. GlueStudioPathList: type: array items: $ref: '#/components/schemas/EnclosedInStringProperties' NotifyDelayAfter: type: integer minimum: 1 EnclosedInStringProperties: type: array items: $ref: '#/components/schemas/EnclosedInStringProperty' TransformConfigParameterList: type: array items: $ref: '#/components/schemas/TransformConfigParameter' S3SourceAdditionalOptions: type: object properties: BoundedSize: allOf: - $ref: '#/components/schemas/BoxedLong' - description: Sets the upper limit for the target size of the dataset in bytes that will be processed. BoundedFiles: allOf: - $ref: '#/components/schemas/BoxedLong' - description: Sets the upper limit for the target number of files that will be processed. description: Specifies additional connection options for the Amazon S3 data store. BoxedPositiveInt: type: integer minimum: 0 EvaluateDataQuality: type: object required: - Name - Inputs - Ruleset properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data quality evaluation. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The inputs of your data quality evaluation. Ruleset: allOf: - $ref: '#/components/schemas/DQDLString' - description: The ruleset for your data quality evaluation. Output: allOf: - $ref: '#/components/schemas/DQTransformOutput' - description: The output of your data quality evaluation. PublishingOptions: allOf: - $ref: '#/components/schemas/DQResultsPublishingOptions' - description: Options to configure how your results are published. StopJobOnFailureOptions: allOf: - $ref: '#/components/schemas/DQStopJobOnFailureOptions' - description: Options to configure how your job will stop if your data quality evaluation fails. description: Specifies your data quality evaluation criteria. NotificationProperty: type: object properties: NotifyDelayAfter: allOf: - $ref: '#/components/schemas/NotifyDelayAfter' - description: After a job run starts, the number of minutes to wait before sending a job run delay notification. description: Specifies configuration properties of a notification. OracleSQLCatalogSource: type: object required: - Name - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the data source. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the database to read from. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The name of the table in the database to read from. description: Specifies an Oracle data source in the Glue Data Catalog. GlueStudioColumnNameString: type: string minLength: 0 maxLength: 1024 x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\t]*' BasicCatalogTarget: type: object required: - Name - Inputs - Database - Table properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of your data target. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The nodes that are inputs to the data target. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The database that contains the table you want to use as the target. This database must already exist in the Data Catalog. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: The table that defines the schema of your output data. This table must already exist in the Data Catalog. description: Specifies a target that uses a Glue Data Catalog table. DirectSchemaChangePolicy: type: object properties: EnableUpdateCatalog: allOf: - $ref: '#/components/schemas/BoxedBoolean' - description: Whether to use the specified update behavior when the crawler finds a changed schema. UpdateBehavior: allOf: - $ref: '#/components/schemas/UpdateCatalogBehavior' - description: The update behavior when the crawler finds a changed schema. Table: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the table in the database that the schema change policy applies to. Database: allOf: - $ref: '#/components/schemas/EnclosedInStringProperty' - description: Specifies the database that the schema change policy applies to. description: A policy that specifies update behavior for the crawler. DeltaTargetCompressionType: type: string enum: - uncompressed - snappy GlueSchemas: type: array items: $ref: '#/components/schemas/GlueSchema' ApplyMapping: type: object required: - Name - Inputs - Mapping properties: Name: allOf: - $ref: '#/components/schemas/NodeName' - description: The name of the transform node. Inputs: allOf: - $ref: '#/components/schemas/OneInput' - description: The data inputs identified by their node names. Mapping: allOf: - $ref: '#/components/schemas/Mappings' - description: Specifies the mapping of data property keys in the data source to data property keys in the data target. description: 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. parameters: X-Amz-Date: name: X-Amz-Date in: header schema: type: string required: false X-Amz-Credential: name: X-Amz-Credential in: header schema: type: string required: false X-Amz-Signature: name: X-Amz-Signature in: header schema: type: string required: false X-Amz-Security-Token: name: X-Amz-Security-Token in: header schema: type: string required: false X-Amz-Content-Sha256: name: X-Amz-Content-Sha256 in: header schema: type: string required: false X-Amz-Algorithm: name: X-Amz-Algorithm in: header schema: type: string required: false X-Amz-SignedHeaders: name: X-Amz-SignedHeaders in: header schema: type: string required: false securitySchemes: hmac: type: apiKey name: Authorization in: header description: Amazon Signature authorization v4 x-amazon-apigateway-authtype: awsSigv4 externalDocs: description: Amazon Web Services documentation url: https://docs.aws.amazon.com/glue/ x-hasEquivalentPaths: true