Configuration of statistics that are allowed to be run on columns that * contain detected entities. When undefined, no statistics will be computed * on columns that contain detected entities.
* @public */ export interface AllowedStatistics { /** *One or more column statistics to allow for columns that contain detected entities.
* @public */ Statistics: string[] | undefined; } /** * @public */ export interface BatchDeleteRecipeVersionRequest { /** *The name of the recipe whose versions are to be deleted.
* @public */ Name: string | undefined; /** *An array of version identifiers, for the recipe versions to be deleted. You can
* specify numeric versions (X.Y) or LATEST_WORKING.
* LATEST_PUBLISHED is not supported.
Represents any errors encountered when attempting to delete multiple recipe * versions.
* @public */ export interface RecipeVersionErrorDetail { /** *The HTTP status code for the error.
* @public */ ErrorCode?: string | undefined; /** *The text of the error message.
* @public */ ErrorMessage?: string | undefined; /** *The identifier for the recipe version associated with this error.
* @public */ RecipeVersion?: string | undefined; } /** * @public */ export interface BatchDeleteRecipeVersionResponse { /** *The name of the recipe that was modified.
* @public */ Name: string | undefined; /** *Errors, if any, that occurred while attempting to delete the recipe versions.
* @public */ Errors?: RecipeVersionErrorDetail[] | undefined; } /** *Represents a set of options that define how DataBrew will read a * comma-separated value (CSV) file when creating a dataset from that file.
* @public */ export interface CsvOptions { /** *A single character that specifies the delimiter being used in the CSV file.
* @public */ Delimiter?: string | undefined; /** *A variable that specifies whether the first row in the file is parsed as the * header. If this value is false, column names are auto-generated.
* @public */ HeaderRow?: boolean | undefined; } /** *Represents a set of options that define how DataBrew will interpret a Microsoft Excel file when * creating a dataset from that file.
* @public */ export interface ExcelOptions { /** *One or more named sheets in the Excel file that will be included in the dataset.
* @public */ SheetNames?: string[] | undefined; /** *One or more sheet numbers in the Excel file that will be included in the * dataset.
* @public */ SheetIndexes?: number[] | undefined; /** *A variable that specifies whether the first row in the file is parsed as the * header. If this value is false, column names are auto-generated.
* @public */ HeaderRow?: boolean | undefined; } /** *Represents the JSON-specific options that define how input is to be interpreted by Glue DataBrew.
* @public */ export interface JsonOptions { /** *A value that specifies whether JSON input contains embedded new line * characters.
* @public */ MultiLine?: boolean | undefined; } /** *Represents a set of options that define the structure of either comma-separated value (CSV), * Excel, or JSON input.
* @public */ export interface FormatOptions { /** *Options that define how JSON input is to be interpreted by DataBrew.
* @public */ Json?: JsonOptions | undefined; /** *Options that define how Excel input is to be interpreted by DataBrew.
* @public */ Excel?: ExcelOptions | undefined; /** *Options that define how CSV input is to be interpreted by DataBrew.
* @public */ Csv?: CsvOptions | undefined; } /** *Represents an Amazon S3 location (bucket name, bucket owner, and object key) where DataBrew can read * input data, or write output from a job.
* @public */ export interface S3Location { /** *The Amazon S3 bucket name.
* @public */ Bucket: string | undefined; /** *The unique name of the object in the bucket.
* @public */ Key?: string | undefined; /** *The Amazon Web Services account ID of the bucket owner.
* @public */ BucketOwner?: string | undefined; } /** *Connection information for dataset input files stored in a database.
* @public */ export interface DatabaseInputDefinition { /** *The Glue Connection that stores the connection information for the target * database.
* @public */ GlueConnectionName: string | undefined; /** *The table within the target database.
* @public */ DatabaseTableName?: string | undefined; /** *Represents an Amazon S3 location (bucket name, bucket owner, and object key) where DataBrew can read * input data, or write output from a job.
* @public */ TempDirectory?: S3Location | undefined; /** *Custom SQL to run against the provided Glue connection. This SQL will be used as * the input for DataBrew projects and jobs.
* @public */ QueryString?: string | undefined; } /** *Represents how metadata stored in the Glue Data Catalog is defined in a DataBrew * dataset.
* @public */ export interface DataCatalogInputDefinition { /** *The unique identifier of the Amazon Web Services account that holds the Data Catalog that stores the * data.
* @public */ CatalogId?: string | undefined; /** *The name of a database in the Data Catalog.
* @public */ DatabaseName: string | undefined; /** *The name of a database table in the Data Catalog. This table corresponds to a DataBrew * dataset.
* @public */ TableName: string | undefined; /** *Represents an Amazon location where DataBrew can store intermediate results.
* @public */ TempDirectory?: S3Location | undefined; } /** *Contains additional resource information needed for specific datasets.
* @public */ export interface Metadata { /** *The Amazon Resource Name (ARN) associated with the dataset. Currently, DataBrew * only supports ARNs from Amazon AppFlow.
* @public */ SourceArn?: string | undefined; } /** *Represents information on how DataBrew can find data, in either the Glue Data Catalog or * Amazon S3.
* @public */ export interface Input { /** *The Amazon S3 location where the data is stored.
* @public */ S3InputDefinition?: S3Location | undefined; /** *The Glue Data Catalog parameters for the data.
* @public */ DataCatalogInputDefinition?: DataCatalogInputDefinition | undefined; /** *Connection information for dataset input files stored in a database.
* @public */ DatabaseInputDefinition?: DatabaseInputDefinition | undefined; /** *Contains additional resource information needed for specific datasets.
* @public */ Metadata?: Metadata | undefined; } /** *Represents a limit imposed on number of Amazon S3 files that should be selected for a * dataset from a connected Amazon S3 path.
* @public */ export interface FilesLimit { /** *The number of Amazon S3 files to select.
* @public */ MaxFiles: number | undefined; /** *A criteria to use for Amazon S3 files sorting before their selection. By default uses LAST_MODIFIED_DATE as * a sorting criteria. Currently it's the only allowed value.
* @public */ OrderedBy?: OrderedBy | undefined; /** *A criteria to use for Amazon S3 files sorting before their selection. By * default uses DESCENDING order, i.e. most recent files are selected first. Another * possible value is ASCENDING.
* @public */ Order?: Order | undefined; } /** *Represents a structure for defining parameter conditions. Supported conditions are described * here: Supported * conditions for dynamic datasets in the * Glue DataBrew Developer Guide.
* @public */ export interface FilterExpression { /** *The expression which includes condition names followed by substitution variables, possibly grouped * and combined with other conditions. For example, "(starts_with :prefix1 or starts_with :prefix2) and * (ends_with :suffix1 or ends_with :suffix2)". Substitution variables should start with ':' symbol.
* @public */ Expression: string | undefined; /** *The map of substitution variable names to their values used in this filter expression.
* @public */ ValuesMap: RecordRepresents additional options for correct interpretation of datetime parameters used in * the Amazon S3 path of a dataset.
* @public */ export interface DatetimeOptions { /** *Required option, that defines the datetime format used for a date parameter in the * Amazon S3 path. Should use only supported datetime specifiers and separation characters, all * literal a-z or A-Z characters should be escaped with single quotes. E.g. "MM.dd.yyyy-'at'-HH:mm".
* @public */ Format: string | undefined; /** *Optional value for a timezone offset of the datetime parameter value in the Amazon S3 * path. Shouldn't be used if Format for this parameter includes timezone fields. * If no offset specified, UTC is assumed.
* @public */ TimezoneOffset?: string | undefined; /** *Optional value for a non-US locale code, needed for correct interpretation of some date formats.
* @public */ LocaleCode?: string | undefined; } /** *Represents a dataset parameter that defines type and conditions for a parameter in the * Amazon S3 path of the dataset.
* @public */ export interface DatasetParameter { /** *The name of the parameter that is used in the dataset's Amazon S3 path.
* @public */ Name: string | undefined; /** *The type of the dataset parameter, can be one of a 'String', 'Number' or 'Datetime'.
* @public */ Type: ParameterType | undefined; /** *Additional parameter options such as a format and a timezone. Required for datetime parameters.
* @public */ DatetimeOptions?: DatetimeOptions | undefined; /** *Optional boolean value that defines whether the captured value of this parameter * should be used to create a new column in a dataset.
* @public */ CreateColumn?: boolean | undefined; /** *The optional filter expression structure to apply additional matching criteria to the parameter.
* @public */ Filter?: FilterExpression | undefined; } /** *Represents a set of options that define how DataBrew selects files for a given Amazon S3 * path in a dataset.
* @public */ export interface PathOptions { /** *If provided, this structure defines a date range for matching Amazon S3 objects based on their * LastModifiedDate attribute in Amazon S3.
* @public */ LastModifiedDateCondition?: FilterExpression | undefined; /** *If provided, this structure imposes a limit on a number of files that should be selected.
* @public */ FilesLimit?: FilesLimit | undefined; /** *A structure that maps names of parameters used in the Amazon S3 path of a dataset to their definitions.
* @public */ Parameters?: RecordThe name of the dataset to be created. Valid characters are alphanumeric (A-Z, a-z, * 0-9), hyphen (-), period (.), and space.
* @public */ Name: string | undefined; /** *The file format of a dataset that is created from an Amazon S3 file or folder.
* @public */ Format?: InputFormat | undefined; /** *Represents a set of options that define the structure of either comma-separated value (CSV), * Excel, or JSON input.
* @public */ FormatOptions?: FormatOptions | undefined; /** *Represents information on how DataBrew can find data, in either the Glue Data Catalog or * Amazon S3.
* @public */ Input: Input | undefined; /** *A set of options that defines how DataBrew interprets an Amazon S3 path of the dataset.
* @public */ PathOptions?: PathOptions | undefined; /** *Metadata tags to apply to this dataset.
* @public */ Tags?: RecordThe name of the dataset that you created.
* @public */ Name: string | undefined; } /** *Selector of a column from a dataset for profile job configuration. * One selector includes either a column name or a regular expression.
* @public */ export interface ColumnSelector { /** *A regular expression for selecting a column from a dataset.
* @public */ Regex?: string | undefined; /** *The name of a column from a dataset.
* @public */ Name?: string | undefined; } /** *Override of a particular evaluation for a profile job.
* @public */ export interface StatisticOverride { /** *The name of an evaluation
* @public */ Statistic: string | undefined; /** *A map that includes overrides of an evaluation’s parameters.
* @public */ Parameters: RecordConfiguration of evaluations for a profile job. This configuration can be used to select * evaluations and override the parameters of selected evaluations. *
* @public */ export interface StatisticsConfiguration { /** *List of included evaluations. When the list is undefined, all supported * evaluations will be included.
* @public */ IncludedStatistics?: string[] | undefined; /** *List of overrides for evaluations.
* @public */ Overrides?: StatisticOverride[] | undefined; } /** *Configuration for column evaluations for a profile job. ColumnStatisticsConfiguration can be used to select * evaluations and override parameters of evaluations for particular columns. *
* @public */ export interface ColumnStatisticsConfiguration { /** *List of column selectors. Selectors can be used to select columns from the dataset. * When selectors are undefined, configuration will be applied to all supported columns. *
* @public */ Selectors?: ColumnSelector[] | undefined; /** *Configuration for evaluations. Statistics can be used to select evaluations and override * parameters of evaluations. *
* @public */ Statistics: StatisticsConfiguration | undefined; } /** *Configuration of entity detection for a profile job. When undefined, entity * detection is disabled.
* @public */ export interface EntityDetectorConfiguration { /** *Entity types to detect. Can be any of the following:
*USA_SSN
*USA_ITIN
*USA_PASSPORT_NUMBER
*PHONE_NUMBER
*USA_DRIVING_LICENSE
*BANK_ACCOUNT
*CREDIT_CARD
*IP_ADDRESS
*MAC_ADDRESS
*USA_DEA_NUMBER
*USA_HCPCS_CODE
*USA_NATIONAL_PROVIDER_IDENTIFIER
*USA_NATIONAL_DRUG_CODE
*USA_HEALTH_INSURANCE_CLAIM_NUMBER
*USA_MEDICARE_BENEFICIARY_IDENTIFIER
*USA_CPT_CODE
*PERSON_NAME
*DATE
*The Entity type group USA_ALL is also supported, and includes all of the * above entity types except PERSON_NAME and DATE.
* @public */ EntityTypes: string[] | undefined; /** *Configuration of statistics that are allowed to be run on columns that * contain detected entities. When undefined, no statistics will be computed * on columns that contain detected entities.
* @public */ AllowedStatistics?: AllowedStatistics[] | undefined; } /** *Configuration for profile jobs. Configuration can be used to select columns, do evaluations, and override default * parameters of evaluations. When configuration is undefined, the profile job will apply default settings to all * supported columns. *
* @public */ export interface ProfileConfiguration { /** *Configuration for inter-column evaluations. Configuration can be used to select evaluations and override * parameters of evaluations. When configuration is undefined, the profile job will run all supported * inter-column evaluations. *
* @public */ DatasetStatisticsConfiguration?: StatisticsConfiguration | undefined; /** *List of column selectors. ProfileColumns can be used to select columns from the dataset. When * ProfileColumns is undefined, the profile job will profile all supported columns. *
* @public */ ProfileColumns?: ColumnSelector[] | undefined; /** *List of configurations for column evaluations. ColumnStatisticsConfigurations are used to * select evaluations and override parameters of evaluations for particular columns. When * ColumnStatisticsConfigurations is undefined, the profile job will profile all supported columns * and run all supported evaluations. *
* @public */ ColumnStatisticsConfigurations?: ColumnStatisticsConfiguration[] | undefined; /** *Configuration of entity detection for a profile job. When undefined, entity detection is disabled.
* @public */ EntityDetectorConfiguration?: EntityDetectorConfiguration | undefined; } /** *A sample configuration for profile jobs only, which determines the number of rows on which the
* profile job is run. If a JobSample value isn't provided, the
* default is used. The default value is CUSTOM_ROWS for the mode parameter and
* 20,000 for the size parameter.
A value that determines whether the profile job is run on the entire dataset or a * specified number of rows. This value must be one of the following:
*FULL_DATASET - The profile job is run on the entire dataset.
*CUSTOM_ROWS - The profile job is run on the number of rows specified in the
* Size parameter.
The Size parameter is only required when the mode is CUSTOM_ROWS. The
* profile job is run on the specified number of rows. The maximum value for size is
* Long.MAX_VALUE.
Long.MAX_VALUE = 9223372036854775807
* @public */ Size?: number | undefined; } /** *Configuration for data quality validation. Used to select the Rulesets and Validation Mode * to be used in the profile job. When ValidationConfiguration is null, the profile * job will run without data quality validation.
* @public */ export interface ValidationConfiguration { /** *The Amazon Resource Name (ARN) for the ruleset to be validated in the profile job. * The TargetArn of the selected ruleset should be the same as the Amazon Resource Name (ARN) of * the dataset that is associated with the profile job.
* @public */ RulesetArn: string | undefined; /** *Mode of data quality validation. Default mode is “CHECK_ALL” which verifies all rules * defined in the selected ruleset.
* @public */ ValidationMode?: ValidationMode | undefined; } /** * @public */ export interface CreateProfileJobRequest { /** *The name of the dataset that this job is to act upon.
* @public */ DatasetName: string | undefined; /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the * job.
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - SSE-KMS - Server-side encryption with
* KMS-managed keys.
* SSE-S3 - Server-side encryption with keys managed by Amazon S3.
The name of the job to be created. Valid characters are alphanumeric (A-Z, a-z, 0-9), * hyphen (-), period (.), and space.
* @public */ Name: string | undefined; /** *Enables or disables Amazon CloudWatch logging for the job. If logging is enabled, * CloudWatch writes one log stream for each job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of nodes that DataBrew can use when the job processes data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *Represents an Amazon S3 location (bucket name, bucket owner, and object key) where DataBrew can read * input data, or write output from a job.
* @public */ OutputLocation: S3Location | undefined; /** *Configuration for profile jobs. Used to select columns, do evaluations, * and override default parameters of evaluations. When configuration is null, the * profile job will run with default settings.
* @public */ Configuration?: ProfileConfiguration | undefined; /** *List of validation configurations that are applied to the profile job.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; /** *The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to * be assumed when DataBrew runs the job.
* @public */ RoleArn: string | undefined; /** *Metadata tags to apply to this job.
* @public */ Tags?: RecordThe job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
Sample configuration for profile jobs only. Determines the number of rows on which the * profile job will be executed. If a JobSample value is not provided, the default value * will be used. The default value is CUSTOM_ROWS for the mode parameter and 20000 for the * size parameter.
* @public */ JobSample?: JobSample | undefined; } /** * @public */ export interface CreateProfileJobResponse { /** *The name of the job that was created.
* @public */ Name: string | undefined; } /** *Represents the sample size and sampling type for DataBrew to use for interactive data * analysis.
* @public */ export interface Sample { /** *The number of rows in the sample.
* @public */ Size?: number | undefined; /** *The way in which DataBrew obtains rows from a dataset.
* @public */ Type: SampleType | undefined; } /** * @public */ export interface CreateProjectRequest { /** *The name of an existing dataset to associate this project with.
* @public */ DatasetName: string | undefined; /** *A unique name for the new project. Valid characters are alphanumeric (A-Z, a-z, 0-9), * hyphen (-), period (.), and space.
* @public */ Name: string | undefined; /** *The name of an existing recipe to associate with the project.
* @public */ RecipeName: string | undefined; /** *Represents the sample size and sampling type for DataBrew to use for interactive data * analysis.
* @public */ Sample?: Sample | undefined; /** *The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to * be assumed for this request.
* @public */ RoleArn: string | undefined; /** *Metadata tags to apply to this project.
* @public */ Tags?: RecordThe name of the project that you created.
* @public */ Name: string | undefined; } /** *Represents a transformation and associated parameters that are used to apply a change * to a DataBrew dataset. For more information, see Recipe * actions reference.
* @public */ export interface RecipeAction { /** *The name of a valid DataBrew transformation to be performed on the data.
* @public */ Operation: string | undefined; /** *Contextual parameters for the transformation.
* @public */ Parameters?: RecordRepresents an individual condition that evaluates to true or false.
*Conditions are used with recipe actions. The action is only performed for column values where the * condition evaluates to true.
*If a recipe requires more than one condition, then the recipe must specify multiple
* ConditionExpression elements. Each condition is applied to the rows in a dataset first, before
* the recipe action is performed.
A specific condition to apply to a recipe action. For more information, see Recipe * structure in the Glue DataBrew Developer * Guide.
* @public */ Condition: string | undefined; /** *A value that the condition must evaluate to for the condition to succeed.
* @public */ Value?: string | undefined; /** *A column to apply this condition to.
* @public */ TargetColumn: string | undefined; } /** *Represents a single step from a DataBrew recipe to be performed.
* @public */ export interface RecipeStep { /** *The particular action to be performed in the recipe step.
* @public */ Action: RecipeAction | undefined; /** *One or more conditions that must be met for the recipe step to succeed.
*All of the conditions in the array must be met. In other words, all of the * conditions must be combined using a logical AND operation.
*A description for the recipe.
* @public */ Description?: string | undefined; /** *A unique name for the recipe. Valid characters are alphanumeric (A-Z, a-z, 0-9), * hyphen (-), period (.), and space.
* @public */ Name: string | undefined; /** *An array containing the steps to be performed by the recipe. Each recipe step consists * of one recipe action and (optionally) an array of condition expressions.
* @public */ Steps: RecipeStep[] | undefined; /** *Metadata tags to apply to this recipe.
* @public */ Tags?: RecordThe name of the recipe that you created.
* @public */ Name: string | undefined; } /** *Represents options that specify how and where DataBrew writes the database * output generated by recipe jobs.
* @public */ export interface DatabaseTableOutputOptions { /** *Represents an Amazon S3 location (bucket name and object key) where DataBrew can store * intermediate results.
* @public */ TempDirectory?: S3Location | undefined; /** *A prefix for the name of a table DataBrew will create in the database.
* @public */ TableName: string | undefined; } /** *Represents a JDBC database output object which defines the output destination for * a DataBrew recipe job to write into.
* @public */ export interface DatabaseOutput { /** *The Glue connection that stores the connection information for the * target database.
* @public */ GlueConnectionName: string | undefined; /** *Represents options that specify how and where DataBrew writes the database output * generated by recipe jobs.
* @public */ DatabaseOptions: DatabaseTableOutputOptions | undefined; /** *The output mode to write into the database. Currently supported option: NEW_TABLE.
* @public */ DatabaseOutputMode?: DatabaseOutputMode | undefined; } /** *Represents options that specify how and where DataBrew writes the Amazon S3 output * generated by recipe jobs.
* @public */ export interface S3TableOutputOptions { /** *Represents an Amazon S3 location (bucket name and object key) where DataBrew can write output * from a job.
* @public */ Location: S3Location | undefined; } /** *Represents options that specify how and where in the Glue Data Catalog DataBrew * writes the output generated by recipe jobs.
* @public */ export interface DataCatalogOutput { /** *The unique identifier of the Amazon Web Services account that holds the Data Catalog that * stores the data.
* @public */ CatalogId?: string | undefined; /** *The name of a database in the Data Catalog.
* @public */ DatabaseName: string | undefined; /** *The name of a table in the Data Catalog.
* @public */ TableName: string | undefined; /** *Represents options that specify how and where DataBrew writes the Amazon S3 * output generated by recipe jobs.
* @public */ S3Options?: S3TableOutputOptions | undefined; /** *Represents options that specify how and where DataBrew writes the database output * generated by recipe jobs.
* @public */ DatabaseOptions?: DatabaseTableOutputOptions | undefined; /** *A value that, if true, means that any data in the location specified for output * is overwritten with new output. Not supported with DatabaseOptions.
* @public */ Overwrite?: boolean | undefined; } /** *Represents a set of options that define how DataBrew will write a * comma-separated value (CSV) file.
* @public */ export interface CsvOutputOptions { /** *A single character that specifies the delimiter used to create CSV job output.
* @public */ Delimiter?: string | undefined; } /** *Represents a set of options that define the structure of comma-separated (CSV) job output.
* @public */ export interface OutputFormatOptions { /** *Represents a set of options that define the structure of comma-separated value (CSV) * job output.
* @public */ Csv?: CsvOutputOptions | undefined; } /** *Represents options that specify how and where in Amazon S3 DataBrew writes the output generated by * recipe jobs or profile jobs.
* @public */ export interface Output { /** *The compression algorithm used to compress the output text of the job.
* @public */ CompressionFormat?: CompressionFormat | undefined; /** *The data format of the output of the job.
* @public */ Format?: OutputFormat | undefined; /** *The names of one or more partition columns for the output of the job.
* @public */ PartitionColumns?: string[] | undefined; /** *The location in Amazon S3 where the job writes its output.
* @public */ Location: S3Location | undefined; /** *A value that, if true, means that any data in the location specified for output is * overwritten with new output.
* @public */ Overwrite?: boolean | undefined; /** *Represents options that define how DataBrew formats job output files.
* @public */ FormatOptions?: OutputFormatOptions | undefined; /** *Maximum number of files to be generated by the job and written to the output folder. For output partitioned * by column(s), the MaxOutputFiles value is the maximum number of files per partition.
* @public */ MaxOutputFiles?: number | undefined; } /** *Represents the name and version of a DataBrew recipe.
* @public */ export interface RecipeReference { /** *The name of the recipe.
* @public */ Name: string | undefined; /** *The identifier for the version for the recipe.
* @public */ RecipeVersion?: string | undefined; } /** * @public */ export interface CreateRecipeJobRequest { /** *The name of the dataset that this job processes.
* @public */ DatasetName?: string | undefined; /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the * job.
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - Server-side encryption with keys managed by KMS.
* SSE-S3 - Server-side encryption with keys managed by Amazon S3.
A unique name for the job. Valid characters are alphanumeric (A-Z, a-z, 0-9), hyphen * (-), period (.), and space.
* @public */ Name: string | undefined; /** *Enables or disables Amazon CloudWatch logging for the job. If logging is enabled, * CloudWatch writes one log stream for each job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of nodes that DataBrew can consume when the job processes * data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *One or more artifacts that represent the output from running the job.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output destination for * a DataBrew recipe job to write to.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *Either the name of an existing project, or a combination of a recipe and a dataset to * associate with the recipe.
* @public */ ProjectName?: string | undefined; /** *Represents the name and version of a DataBrew recipe.
* @public */ RecipeReference?: RecipeReference | undefined; /** *The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to * be assumed when DataBrew runs the job.
* @public */ RoleArn: string | undefined; /** *Metadata tags to apply to this job.
* @public */ Tags?: RecordThe job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
The name of the job that you created.
* @public */ Name: string | undefined; } /** *The threshold used with a non-aggregate check expression. The non-aggregate check expression * will be applied to each row in a specific column. Then the threshold will be used to determine * whether the validation succeeds.
* @public */ export interface Threshold { /** *The value of a threshold.
* @public */ Value: number | undefined; /** *The type of a threshold. Used for comparison of an actual count of rows that satisfy the * rule to the threshold value.
* @public */ Type?: ThresholdType | undefined; /** *Unit of threshold value. Can be either a COUNT or PERCENTAGE of the full sample size * used for validation.
* @public */ Unit?: ThresholdUnit | undefined; } /** *Represents a single data quality requirement that should be validated in the * scope of this dataset.
* @public */ export interface Rule { /** *The name of the rule.
* @public */ Name: string | undefined; /** *A value that specifies whether the rule is disabled. Once a rule is * disabled, a profile job will not validate it during a job run. Default * value is false.
* @public */ Disabled?: boolean | undefined; /** *The expression which includes column references, condition names followed by variable
* references, possibly grouped and combined with other conditions. For example,
* (:col1 starts_with :prefix1 or :col1 starts_with :prefix2) and (:col1
* ends_with :suffix1 or :col1 ends_with :suffix2). Column and value references
* are substitution variables that should start with the ':' symbol. Depending on the
* context, substitution variables' values can be either an actual value or a column name.
* These values are defined in the SubstitutionMap. If a CheckExpression starts with a
* column reference, then ColumnSelectors in the rule should be null. If ColumnSelectors
* has been defined, then there should be no column reference in the left side of a
* condition, for example, is_between :val1 and :val2.
For more information, see Available checks *
* @public */ CheckExpression: string | undefined; /** *The map of substitution variable names to their values used in a check
* expression. Variable names should start with a ':' (colon). Variable values can either
* be actual values or column names. To differentiate between the two, column names
* should be enclosed in backticks, for example, ":col1": "`Column A`".
*
The threshold used with a non-aggregate check expression. Non-aggregate check expressions * will be applied to each row in a specific column, and the threshold will be used to determine * whether the validation succeeds.
* @public */ Threshold?: Threshold | undefined; /** *List of column selectors. Selectors can be used to select columns using a name or regular * expression from the dataset. Rule will be applied to selected columns.
* @public */ ColumnSelectors?: ColumnSelector[] | undefined; } /** * @public */ export interface CreateRulesetRequest { /** *The name of the ruleset to be created. Valid characters are alphanumeric * (A-Z, a-z, 0-9), hyphen (-), period (.), and space.
* @public */ Name: string | undefined; /** *The description of the ruleset.
* @public */ Description?: string | undefined; /** *The Amazon Resource Name (ARN) of a resource (dataset) that the * ruleset is associated with.
* @public */ TargetArn: string | undefined; /** *A list of rules that are defined with the ruleset. A rule includes * one or more checks to be validated on a DataBrew dataset.
* @public */ Rules: Rule[] | undefined; /** *Metadata tags to apply to the ruleset.
* @public */ Tags?: RecordThe unique name of the created ruleset.
* @public */ Name: string | undefined; } /** * @public */ export interface CreateScheduleRequest { /** *The name or names of one or more jobs to be run.
* @public */ JobNames?: string[] | undefined; /** *The date or dates and time or times when the jobs are to be run. For more information, * see Cron * expressions in the Glue DataBrew Developer * Guide.
* @public */ CronExpression: string | undefined; /** *Metadata tags to apply to this schedule.
* @public */ Tags?: RecordA unique name for the schedule. Valid characters are alphanumeric (A-Z, a-z, 0-9), * hyphen (-), period (.), and space.
* @public */ Name: string | undefined; } /** * @public */ export interface CreateScheduleResponse { /** *The name of the schedule that was created.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteDatasetRequest { /** *The name of the dataset to be deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteDatasetResponse { /** *The name of the dataset that you deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteJobRequest { /** *The name of the job to be deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteJobResponse { /** *The name of the job that you deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteProjectRequest { /** *The name of the project to be deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteProjectResponse { /** *The name of the project that you deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteRecipeVersionRequest { /** *The name of the recipe.
* @public */ Name: string | undefined; /** *The version of the recipe to be deleted. You can specify a numeric versions
* (X.Y) or LATEST_WORKING. LATEST_PUBLISHED is
* not supported.
The name of the recipe that was deleted.
* @public */ Name: string | undefined; /** *The version of the recipe that was deleted.
* @public */ RecipeVersion: string | undefined; } /** * @public */ export interface DeleteRulesetRequest { /** *The name of the ruleset to be deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteRulesetResponse { /** *The name of the deleted ruleset.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteScheduleRequest { /** *The name of the schedule to be deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DeleteScheduleResponse { /** *The name of the schedule that was deleted.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeDatasetRequest { /** *The name of the dataset to be described.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeDatasetResponse { /** *The identifier (user name) of the user who created the dataset.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the dataset was created.
* @public */ CreateDate?: Date | undefined; /** *The name of the dataset.
* @public */ Name: string | undefined; /** *The file format of a dataset that is created from an Amazon S3 file * or folder.
* @public */ Format?: InputFormat | undefined; /** *Represents a set of options that define the structure of either comma-separated value (CSV), * Excel, or JSON input.
* @public */ FormatOptions?: FormatOptions | undefined; /** *Represents information on how DataBrew can find data, in either the Glue Data Catalog or * Amazon S3.
* @public */ Input: Input | undefined; /** *The date and time that the dataset was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The identifier (user name) of the user who last modified the dataset.
* @public */ LastModifiedBy?: string | undefined; /** *The location of the data for this dataset, Amazon S3 or the * Glue Data Catalog.
* @public */ Source?: Source | undefined; /** *A set of options that defines how DataBrew interprets an Amazon S3 * path of the dataset.
* @public */ PathOptions?: PathOptions | undefined; /** *Metadata tags associated with this dataset.
* @public */ Tags?: RecordThe Amazon Resource Name (ARN) of the dataset.
* @public */ ResourceArn?: string | undefined; } /** * @public */ export interface DescribeJobRequest { /** *The name of the job to be described.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeJobResponse { /** *The date and time that the job was created.
* @public */ CreateDate?: Date | undefined; /** *The identifier (user name) of the user associated with the creation of the job.
* @public */ CreatedBy?: string | undefined; /** *The dataset that the job acts upon.
* @public */ DatasetName?: string | undefined; /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the * job.
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - Server-side encryption with keys managed by KMS.
* SSE-S3 - Server-side encryption with keys managed by Amazon
* S3.
The name of the job.
* @public */ Name: string | undefined; /** *The job type, which must be one of the following:
*
* PROFILE - The job analyzes the dataset to determine its size,
* data types, data distribution, and more.
* RECIPE - The job applies one or more transformations to a
* dataset.
The identifier (user name) of the user who last modified the job.
* @public */ LastModifiedBy?: string | undefined; /** *The date and time that the job was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *Indicates whether Amazon CloudWatch logging is enabled for this job.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of compute nodes that DataBrew can consume when the job processes * data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *One or more artifacts that represent the output from running the job.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output * destination for a DataBrew recipe job to write into.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *The DataBrew project associated with this job.
* @public */ ProjectName?: string | undefined; /** *Configuration for profile jobs. Used to select columns, do evaluations, * and override default parameters of evaluations. When configuration is null, the * profile job will run with default settings.
* @public */ ProfileConfiguration?: ProfileConfiguration | undefined; /** *List of validation configurations that are applied to the profile job.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; /** *Represents the name and version of a DataBrew recipe.
* @public */ RecipeReference?: RecipeReference | undefined; /** *The Amazon Resource Name (ARN) of the job.
* @public */ ResourceArn?: string | undefined; /** *The ARN of the Identity and Access Management (IAM) role to be assumed when * DataBrew runs the job.
* @public */ RoleArn?: string | undefined; /** *Metadata tags associated with this job.
* @public */ Tags?: RecordThe job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
Sample configuration for profile jobs only. Determines the number of rows on which the * profile job will be executed.
* @public */ JobSample?: JobSample | undefined; } /** * @public */ export interface DescribeJobRunRequest { /** *The name of the job being processed during this run.
* @public */ Name: string | undefined; /** *The unique identifier of the job run.
* @public */ RunId: string | undefined; } /** * @public */ export interface DescribeJobRunResponse { /** *The number of times that DataBrew has attempted to run the job.
* @public */ Attempt?: number | undefined; /** *The date and time when the job completed processing.
* @public */ CompletedOn?: Date | undefined; /** *The name of the dataset for the job to process.
* @public */ DatasetName?: string | undefined; /** *A message indicating an error (if any) that was encountered when the job ran.
* @public */ ErrorMessage?: string | undefined; /** *The amount of time, in seconds, during which the job run consumed resources.
* @public */ ExecutionTime?: number | undefined; /** *The name of the job being processed during this run.
* @public */ JobName: string | undefined; /** *Configuration for profile jobs. Used to select columns, do evaluations, * and override default parameters of evaluations. When configuration is null, the * profile job will run with default settings.
* @public */ ProfileConfiguration?: ProfileConfiguration | undefined; /** *List of validation configurations that are applied to the profile job.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; /** *The unique identifier of the job run.
* @public */ RunId?: string | undefined; /** *The current state of the job run entity itself.
* @public */ State?: JobRunState | undefined; /** *The current status of Amazon CloudWatch logging for the job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The name of an Amazon CloudWatch log group, where the job writes diagnostic messages * when it runs.
* @public */ LogGroupName?: string | undefined; /** *One or more output artifacts from a job run.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output * destination for a DataBrew recipe job to write into.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *Represents the name and version of a DataBrew recipe.
* @public */ RecipeReference?: RecipeReference | undefined; /** *The Amazon Resource Name (ARN) of the user who started the job run.
* @public */ StartedBy?: string | undefined; /** *The date and time when the job run began.
* @public */ StartedOn?: Date | undefined; /** *Sample configuration for profile jobs only. Determines the number of rows on which the * profile job will be executed. If a JobSample value is not provided, the default value * will be used. The default value is CUSTOM_ROWS for the mode parameter and 20000 for the * size parameter.
* @public */ JobSample?: JobSample | undefined; } /** * @public */ export interface DescribeProjectRequest { /** *The name of the project to be described.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeProjectResponse { /** *The date and time that the project was created.
* @public */ CreateDate?: Date | undefined; /** *The identifier (user name) of the user who created the project.
* @public */ CreatedBy?: string | undefined; /** *The dataset associated with the project.
* @public */ DatasetName?: string | undefined; /** *The date and time that the project was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The identifier (user name) of the user who last modified the project.
* @public */ LastModifiedBy?: string | undefined; /** *The name of the project.
* @public */ Name: string | undefined; /** *The recipe associated with this job.
* @public */ RecipeName?: string | undefined; /** *The Amazon Resource Name (ARN) of the project.
* @public */ ResourceArn?: string | undefined; /** *Represents the sample size and sampling type for DataBrew to use for interactive data * analysis.
* @public */ Sample?: Sample | undefined; /** *The ARN of the Identity and Access Management (IAM) role to be assumed when * DataBrew runs the job.
* @public */ RoleArn?: string | undefined; /** *Metadata tags associated with this project.
* @public */ Tags?: RecordDescribes the current state of the session:
*
* PROVISIONING - allocating resources for the session.
* INITIALIZING - getting the session ready for first use.
* ASSIGNED - the session is ready for use.
The identifier (user name) of the user that opened the project for use.
* @public */ OpenedBy?: string | undefined; /** *The date and time when the project was opened.
* @public */ OpenDate?: Date | undefined; } /** * @public */ export interface DescribeRecipeRequest { /** *The name of the recipe to be described.
* @public */ Name: string | undefined; /** *The recipe version identifier. If this parameter isn't specified, then the latest * published version is returned.
* @public */ RecipeVersion?: string | undefined; } /** * @public */ export interface DescribeRecipeResponse { /** *The identifier (user name) of the user who created the recipe.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the recipe was created.
* @public */ CreateDate?: Date | undefined; /** *The identifier (user name) of the user who last modified the recipe.
* @public */ LastModifiedBy?: string | undefined; /** *The date and time that the recipe was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The name of the project associated with this recipe.
* @public */ ProjectName?: string | undefined; /** *The identifier (user name) of the user who last published the recipe.
* @public */ PublishedBy?: string | undefined; /** *The date and time when the recipe was last published.
* @public */ PublishedDate?: Date | undefined; /** *The description of the recipe.
* @public */ Description?: string | undefined; /** *The name of the recipe.
* @public */ Name: string | undefined; /** *One or more steps to be performed by the recipe. Each step consists of an action, and * the conditions under which the action should succeed.
* @public */ Steps?: RecipeStep[] | undefined; /** *Metadata tags associated with this project.
* @public */ Tags?: RecordThe ARN of the recipe.
* @public */ ResourceArn?: string | undefined; /** *The recipe version identifier.
* @public */ RecipeVersion?: string | undefined; } /** * @public */ export interface DescribeRulesetRequest { /** *The name of the ruleset to be described.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeRulesetResponse { /** *The name of the ruleset.
* @public */ Name: string | undefined; /** *The description of the ruleset.
* @public */ Description?: string | undefined; /** *The Amazon Resource Name (ARN) of a resource (dataset) that the ruleset is * associated with.
* @public */ TargetArn?: string | undefined; /** *A list of rules that are defined with the ruleset. A rule includes one * or more checks to be validated on a DataBrew dataset.
* @public */ Rules?: Rule[] | undefined; /** *The date and time that the ruleset was created.
* @public */ CreateDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the user who created the ruleset.
* @public */ CreatedBy?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the ruleset.
* @public */ LastModifiedBy?: string | undefined; /** *The modification date and time of the ruleset.
* @public */ LastModifiedDate?: Date | undefined; /** *The Amazon Resource Name (ARN) for the ruleset.
* @public */ ResourceArn?: string | undefined; /** *Metadata tags that have been applied to the ruleset.
* @public */ Tags?: RecordThe name of the schedule to be described.
* @public */ Name: string | undefined; } /** * @public */ export interface DescribeScheduleResponse { /** *The date and time that the schedule was created.
* @public */ CreateDate?: Date | undefined; /** *The identifier (user name) of the user who created the schedule.
* @public */ CreatedBy?: string | undefined; /** *The name or names of one or more jobs to be run by using the schedule.
* @public */ JobNames?: string[] | undefined; /** *The identifier (user name) of the user who last modified the schedule.
* @public */ LastModifiedBy?: string | undefined; /** *The date and time that the schedule was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the schedule.
* @public */ ResourceArn?: string | undefined; /** *The date or dates and time or times when the jobs are to be run for the schedule. For * more information, see Cron expressions in the * Glue DataBrew Developer Guide.
* @public */ CronExpression?: string | undefined; /** *Metadata tags associated with this schedule.
* @public */ Tags?: RecordThe name of the schedule.
* @public */ Name: string | undefined; } /** * @public */ export interface ListDatasetsRequest { /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; } /** *Represents a dataset that can be processed by DataBrew.
* @public */ export interface Dataset { /** *The ID of the Amazon Web Services account that owns the dataset.
* @public */ AccountId?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who created the dataset.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the dataset was created.
* @public */ CreateDate?: Date | undefined; /** *The unique name of the dataset.
* @public */ Name: string | undefined; /** *The file format of a dataset that is created from an Amazon S3 file or folder.
* @public */ Format?: InputFormat | undefined; /** *A set of options that define how DataBrew interprets the data in the dataset.
* @public */ FormatOptions?: FormatOptions | undefined; /** *Information on how DataBrew can find the dataset, in either the Glue Data Catalog * or Amazon S3.
* @public */ Input: Input | undefined; /** *The last modification date and time of the dataset.
* @public */ LastModifiedDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the dataset.
* @public */ LastModifiedBy?: string | undefined; /** *The location of the data for the dataset, either Amazon S3 or the Glue Data Catalog.
* @public */ Source?: Source | undefined; /** *A set of options that defines how DataBrew interprets an Amazon S3 * path of the dataset.
* @public */ PathOptions?: PathOptions | undefined; /** *Metadata tags that have been applied to the dataset.
* @public */ Tags?: RecordThe unique Amazon Resource Name (ARN) for the dataset.
* @public */ ResourceArn?: string | undefined; } /** * @public */ export interface ListDatasetsResponse { /** *A list of datasets that are defined.
* @public */ Datasets: Dataset[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListJobRunsRequest { /** *The name of the job.
* @public */ Name: string | undefined; /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; } /** *Represents one run of a DataBrew job.
* @public */ export interface JobRun { /** *The number of times that DataBrew has attempted to run the job.
* @public */ Attempt?: number | undefined; /** *The date and time when the job completed processing.
* @public */ CompletedOn?: Date | undefined; /** *The name of the dataset for the job to process.
* @public */ DatasetName?: string | undefined; /** *A message indicating an error (if any) that was encountered when the job ran.
* @public */ ErrorMessage?: string | undefined; /** *The amount of time, in seconds, during which a job run consumed resources.
* @public */ ExecutionTime?: number | undefined; /** *The name of the job being processed during this run.
* @public */ JobName?: string | undefined; /** *The unique identifier of the job run.
* @public */ RunId?: string | undefined; /** *The current state of the job run entity itself.
* @public */ State?: JobRunState | undefined; /** *The current status of Amazon CloudWatch logging for the job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The name of an Amazon CloudWatch log group, where the job writes diagnostic messages * when it runs.
* @public */ LogGroupName?: string | undefined; /** *One or more output artifacts from a job run.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output * from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output * destination for a DataBrew recipe job to write into.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *The set of steps processed by the job.
* @public */ RecipeReference?: RecipeReference | undefined; /** *The Amazon Resource Name (ARN) of the user who initiated the job run.
* @public */ StartedBy?: string | undefined; /** *The date and time when the job run began.
* @public */ StartedOn?: Date | undefined; /** *A sample configuration for profile jobs only, which determines the number of rows on which the
* profile job is run. If a JobSample value isn't provided, the default
* is used. The default value is CUSTOM_ROWS for the mode parameter and 20,000 for the
* size parameter.
List of validation configurations that are applied to the profile job run.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; } /** * @public */ export interface ListJobRunsResponse { /** *A list of job runs that have occurred for the specified job.
* @public */ JobRuns: JobRun[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListJobsRequest { /** *The name of a dataset. Using this parameter indicates to return only those jobs that * act on the specified dataset.
* @public */ DatasetName?: string | undefined; /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *A token generated by DataBrew that specifies where to continue pagination if a * previous request was truncated. To get the next set of pages, pass in the NextToken * value from the response object of the previous page call.
* @public */ NextToken?: string | undefined; /** *The name of a project. Using this parameter indicates to return only those jobs that * are associated with the specified project.
* @public */ ProjectName?: string | undefined; } /** *Represents all of the attributes of a DataBrew job.
* @public */ export interface Job { /** *The ID of the Amazon Web Services account that owns the job.
* @public */ AccountId?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who created the job.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the job was created.
* @public */ CreateDate?: Date | undefined; /** *A dataset that the job is to process.
* @public */ DatasetName?: string | undefined; /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the job * output. For more information, see Encrypting data * written by DataBrew jobs *
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - Server-side encryption with keys managed by KMS.
* SSE-S3 - Server-side encryption with keys managed by Amazon S3.
The unique name of the job.
* @public */ Name: string | undefined; /** *The job type of the job, which must be one of the following:
*
* PROFILE - A job to analyze a dataset, to determine its size, data
* types, data distribution, and more.
* RECIPE - A job to apply one or more transformations to a
* dataset.
The Amazon Resource Name (ARN) of the user who last modified the job.
* @public */ LastModifiedBy?: string | undefined; /** *The modification date and time of the job.
* @public */ LastModifiedDate?: Date | undefined; /** *The current status of Amazon CloudWatch logging for the job.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of nodes that can be consumed when the job processes data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *One or more artifacts that represent output from running the job.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output * from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output * destination for a DataBrew recipe job to write into.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *The name of the project that the job is associated with.
* @public */ ProjectName?: string | undefined; /** *A set of steps that the job runs.
* @public */ RecipeReference?: RecipeReference | undefined; /** *The unique Amazon Resource Name (ARN) for the job.
* @public */ ResourceArn?: string | undefined; /** *The Amazon Resource Name (ARN) of the role to be assumed for this job.
* @public */ RoleArn?: string | undefined; /** *The job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
Metadata tags that have been applied to the job.
* @public */ Tags?: RecordA sample configuration for profile jobs only, which determines the number of rows on which the
* profile job is run. If a JobSample value isn't provided, the default value
* is used. The default value is CUSTOM_ROWS for the mode parameter and 20,000 for the
* size parameter.
List of validation configurations that are applied to the profile job.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; } /** * @public */ export interface ListJobsResponse { /** *A list of jobs that are defined.
* @public */ Jobs: Job[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListProjectsRequest { /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; } /** *Represents all of the attributes of a DataBrew project.
* @public */ export interface Project { /** *The ID of the Amazon Web Services account that owns the project.
* @public */ AccountId?: string | undefined; /** *The date and time that the project was created.
* @public */ CreateDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the user who crated the project.
* @public */ CreatedBy?: string | undefined; /** *The dataset that the project is to act upon.
* @public */ DatasetName?: string | undefined; /** *The last modification date and time for the project.
* @public */ LastModifiedDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the project.
* @public */ LastModifiedBy?: string | undefined; /** *The unique name of a project.
* @public */ Name: string | undefined; /** *The name of a recipe that will be developed during a project session.
* @public */ RecipeName: string | undefined; /** *The Amazon Resource Name (ARN) for the project.
* @public */ ResourceArn?: string | undefined; /** *The sample size and sampling type to apply to the data. If this parameter isn't * specified, then the sample consists of the first 500 rows from the dataset.
* @public */ Sample?: Sample | undefined; /** *Metadata tags that have been applied to the project.
* @public */ Tags?: RecordThe Amazon Resource Name (ARN) of the role that will be assumed for this * project.
* @public */ RoleArn?: string | undefined; /** *The Amazon Resource Name (ARN) of the user that opened the project for use.
* @public */ OpenedBy?: string | undefined; /** *The date and time when the project was opened.
* @public */ OpenDate?: Date | undefined; } /** * @public */ export interface ListProjectsResponse { /** *A list of projects that are defined .
* @public */ Projects: Project[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListRecipesRequest { /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; /** *Return only those recipes with a version identifier of LATEST_WORKING or
* LATEST_PUBLISHED. If RecipeVersion is omitted,
* ListRecipes returns all of the LATEST_PUBLISHED recipe
* versions.
Valid values: LATEST_WORKING | LATEST_PUBLISHED
*
Represents one or more actions to be performed on a DataBrew dataset.
* @public */ export interface Recipe { /** *The Amazon Resource Name (ARN) of the user who created the recipe.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the recipe was created.
* @public */ CreateDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the recipe.
* @public */ LastModifiedBy?: string | undefined; /** *The last modification date and time of the recipe.
* @public */ LastModifiedDate?: Date | undefined; /** *The name of the project that the recipe is associated with.
* @public */ ProjectName?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who published the recipe.
* @public */ PublishedBy?: string | undefined; /** *The date and time when the recipe was published.
* @public */ PublishedDate?: Date | undefined; /** *The description of the recipe.
* @public */ Description?: string | undefined; /** *The unique name for the recipe.
* @public */ Name: string | undefined; /** *The Amazon Resource Name (ARN) for the recipe.
* @public */ ResourceArn?: string | undefined; /** *A list of steps that are defined by the recipe.
* @public */ Steps?: RecipeStep[] | undefined; /** *Metadata tags that have been applied to the recipe.
* @public */ Tags?: RecordThe identifier for the version for the recipe. Must be one of the following:
*Numeric version (X.Y) - X and Y stand
* for major and minor version numbers. The maximum length of each is 6 digits, and
* neither can be negative values. Both X and Y are
* required, and "0.0" isn't a valid version.
* LATEST_WORKING - the most recent valid version being developed in
* a DataBrew project.
* LATEST_PUBLISHED - the most recent published version.
A list of recipes that are defined.
* @public */ Recipes: Recipe[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListRecipeVersionsRequest { /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; /** *The name of the recipe for which to return version information.
* @public */ Name: string | undefined; } /** * @public */ export interface ListRecipeVersionsResponse { /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; /** *A list of versions for the specified recipe.
* @public */ Recipes: Recipe[] | undefined; } /** * @public */ export interface ListRulesetsRequest { /** *The Amazon Resource Name (ARN) of a resource (dataset). Using this parameter * indicates to return only those rulesets that are associated with the specified resource.
* @public */ TargetArn?: string | undefined; /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *A token generated by DataBrew that specifies where to continue pagination * if a previous request was truncated. To get the next set of pages, pass in * the NextToken value from the response object of the previous page call.
* @public */ NextToken?: string | undefined; } /** *Contains metadata about the ruleset.
* @public */ export interface RulesetItem { /** *The ID of the Amazon Web Services account that owns the ruleset.
* @public */ AccountId?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who created the ruleset.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the ruleset was created.
* @public */ CreateDate?: Date | undefined; /** *The description of the ruleset.
* @public */ Description?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the ruleset.
* @public */ LastModifiedBy?: string | undefined; /** *The modification date and time of the ruleset.
* @public */ LastModifiedDate?: Date | undefined; /** *The name of the ruleset.
* @public */ Name: string | undefined; /** *The Amazon Resource Name (ARN) for the ruleset.
* @public */ ResourceArn?: string | undefined; /** *The number of rules that are defined in the ruleset.
* @public */ RuleCount?: number | undefined; /** *Metadata tags that have been applied to the ruleset.
* @public */ Tags?: RecordThe Amazon Resource Name (ARN) of a resource (dataset) that the ruleset is * associated with.
* @public */ TargetArn: string | undefined; } /** * @public */ export interface ListRulesetsResponse { /** *A list of RulesetItem. RulesetItem contains meta data of a ruleset.
* @public */ Rulesets: RulesetItem[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListSchedulesRequest { /** *The name of the job that these schedules apply to.
* @public */ JobName?: string | undefined; /** *The maximum number of results to return in this request.
* @public */ MaxResults?: number | undefined; /** *The token returned by a previous call to retrieve the next set of results.
* @public */ NextToken?: string | undefined; } /** *Represents one or more dates and times when a job is to run.
* @public */ export interface Schedule { /** *The ID of the Amazon Web Services account that owns the schedule.
* @public */ AccountId?: string | undefined; /** *The Amazon Resource Name (ARN) of the user who created the schedule.
* @public */ CreatedBy?: string | undefined; /** *The date and time that the schedule was created.
* @public */ CreateDate?: Date | undefined; /** *A list of jobs to be run, according to the schedule.
* @public */ JobNames?: string[] | undefined; /** *The Amazon Resource Name (ARN) of the user who last modified the schedule.
* @public */ LastModifiedBy?: string | undefined; /** *The date and time when the schedule was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The Amazon Resource Name (ARN) of the schedule.
* @public */ ResourceArn?: string | undefined; /** *The dates and times when the job is to run. For more information, see Cron * expressions in the Glue DataBrew Developer * Guide.
* @public */ CronExpression?: string | undefined; /** *Metadata tags that have been applied to the schedule.
* @public */ Tags?: RecordThe name of the schedule.
* @public */ Name: string | undefined; } /** * @public */ export interface ListSchedulesResponse { /** *A list of schedules that are defined.
* @public */ Schedules: Schedule[] | undefined; /** *A token that you can use in a subsequent call to retrieve the next set of * results.
* @public */ NextToken?: string | undefined; } /** * @public */ export interface ListTagsForResourceRequest { /** *The Amazon Resource Name (ARN) string that uniquely identifies the DataBrew resource. *
* @public */ ResourceArn: string | undefined; } /** * @public */ export interface ListTagsForResourceResponse { /** *A list of tags associated with the DataBrew resource.
* @public */ Tags?: RecordA description of the recipe to be published, for this version of the recipe.
* @public */ Description?: string | undefined; /** *The name of the recipe to be published.
* @public */ Name: string | undefined; } /** * @public */ export interface PublishRecipeResponse { /** *The name of the recipe that you published.
* @public */ Name: string | undefined; } /** *Represents the data being transformed during an action.
* @public */ export interface ViewFrame { /** *The starting index for the range of columns to return in the view frame.
* @public */ StartColumnIndex: number | undefined; /** *The number of columns to include in the view frame, beginning with the
* StartColumnIndex value and ignoring any columns in the
* HiddenColumns list.
A list of columns to hide in the view frame.
* @public */ HiddenColumns?: string[] | undefined; /** *The starting index for the range of rows to return in the view frame.
* @public */ StartRowIndex?: number | undefined; /** *The number of rows to include in the view frame, beginning with the
* StartRowIndex value.
Controls if analytics computation is enabled or disabled. Enabled by default.
* @public */ Analytics?: AnalyticsMode | undefined; } /** * @public */ export interface SendProjectSessionActionRequest { /** *If true, the result of the recipe step will be returned, but not applied.
* @public */ Preview?: boolean | undefined; /** *The name of the project to apply the action to.
* @public */ Name: string | undefined; /** *Represents a single step from a DataBrew recipe to be performed.
* @public */ RecipeStep?: RecipeStep | undefined; /** *The index from which to preview a step. This index is used to preview the result of * steps that have already been applied, so that the resulting view frame is from earlier * in the view frame stack.
* @public */ StepIndex?: number | undefined; /** *A unique identifier for an interactive session that's currently open and ready for * work. The action will be performed on this session.
* @public */ ClientSessionId?: string | undefined; /** *Represents the data being transformed during an action.
* @public */ ViewFrame?: ViewFrame | undefined; } /** * @public */ export interface SendProjectSessionActionResponse { /** *A message indicating the result of performing the action.
* @public */ Result?: string | undefined; /** *The name of the project that was affected by the action.
* @public */ Name: string | undefined; /** *A unique identifier for the action that was performed.
* @public */ ActionId?: number | undefined; } /** * @public */ export interface StartJobRunRequest { /** *The name of the job to be run.
* @public */ Name: string | undefined; } /** * @public */ export interface StartJobRunResponse { /** *A system-generated identifier for this particular job run.
* @public */ RunId: string | undefined; } /** * @public */ export interface StartProjectSessionRequest { /** *The name of the project to act upon.
* @public */ Name: string | undefined; /** *A value that, if true, enables you to take control of a session, even if a different * client is currently accessing the project.
* @public */ AssumeControl?: boolean | undefined; } /** * @public */ export interface StartProjectSessionResponse { /** *The name of the project to be acted upon.
* @public */ Name: string | undefined; /** *A system-generated identifier for the session.
* @public */ ClientSessionId?: string | undefined; } /** * @public */ export interface StopJobRunRequest { /** *The name of the job to be stopped.
* @public */ Name: string | undefined; /** *The ID of the job run to be stopped.
* @public */ RunId: string | undefined; } /** * @public */ export interface StopJobRunResponse { /** *The ID of the job run that you stopped.
* @public */ RunId: string | undefined; } /** * @public */ export interface TagResourceRequest { /** *The DataBrew resource to which tags should be added. The value for this parameter is * an Amazon Resource Name (ARN). For DataBrew, you can tag a dataset, a job, a project, or * a recipe.
* @public */ ResourceArn: string | undefined; /** *One or more tags to be assigned to the resource.
* @public */ Tags: RecordA DataBrew resource from which you want to remove a tag or tags. The value for this * parameter is an Amazon Resource Name (ARN).
* @public */ ResourceArn: string | undefined; /** *The tag keys (names) of one or more tags to be removed.
* @public */ TagKeys: string[] | undefined; } /** * @public */ export interface UntagResourceResponse { } /** * @public */ export interface UpdateDatasetRequest { /** *The name of the dataset to be updated.
* @public */ Name: string | undefined; /** *The file format of a dataset that is created from an Amazon S3 file or folder.
* @public */ Format?: InputFormat | undefined; /** *Represents a set of options that define the structure of either comma-separated value (CSV), * Excel, or JSON input.
* @public */ FormatOptions?: FormatOptions | undefined; /** *Represents information on how DataBrew can find data, in either the Glue Data Catalog or * Amazon S3.
* @public */ Input: Input | undefined; /** *A set of options that defines how DataBrew interprets an Amazon S3 path of the dataset.
* @public */ PathOptions?: PathOptions | undefined; } /** * @public */ export interface UpdateDatasetResponse { /** *The name of the dataset that you updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateProfileJobRequest { /** *Configuration for profile jobs. Used to select columns, do evaluations, * and override default parameters of evaluations. When configuration is null, the * profile job will run with default settings.
* @public */ Configuration?: ProfileConfiguration | undefined; /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the * job.
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - Server-side encryption with keys managed by KMS.
* SSE-S3 - Server-side encryption with keys managed by Amazon
* S3.
The name of the job to be updated.
* @public */ Name: string | undefined; /** *Enables or disables Amazon CloudWatch logging for the job. If logging is enabled, * CloudWatch writes one log stream for each job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of compute nodes that DataBrew can use when the job processes * data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *Represents an Amazon S3 location (bucket name, bucket owner, and object key) where DataBrew can read * input data, or write output from a job.
* @public */ OutputLocation: S3Location | undefined; /** *List of validation configurations that are applied to the profile job.
* @public */ ValidationConfigurations?: ValidationConfiguration[] | undefined; /** *The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to * be assumed when DataBrew runs the job.
* @public */ RoleArn: string | undefined; /** *The job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
Sample configuration for Profile Jobs only. Determines the number of rows on which the * Profile job will be executed. If a JobSample value is not provided for profile jobs, the * default value will be used. The default value is CUSTOM_ROWS for the mode parameter and * 20000 for the size parameter.
* @public */ JobSample?: JobSample | undefined; } /** * @public */ export interface UpdateProfileJobResponse { /** *The name of the job that was updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateProjectRequest { /** *Represents the sample size and sampling type for DataBrew to use for interactive data * analysis.
* @public */ Sample?: Sample | undefined; /** *The Amazon Resource Name (ARN) of the IAM role to be assumed for this request.
* @public */ RoleArn: string | undefined; /** *The name of the project to be updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateProjectResponse { /** *The date and time that the project was last modified.
* @public */ LastModifiedDate?: Date | undefined; /** *The name of the project that you updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateRecipeRequest { /** *A description of the recipe.
* @public */ Description?: string | undefined; /** *The name of the recipe to be updated.
* @public */ Name: string | undefined; /** *One or more steps to be performed by the recipe. Each step consists of an action, and * the conditions under which the action should succeed.
* @public */ Steps?: RecipeStep[] | undefined; } /** * @public */ export interface UpdateRecipeResponse { /** *The name of the recipe that was updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateRecipeJobRequest { /** *The Amazon Resource Name (ARN) of an encryption key that is used to protect the * job.
* @public */ EncryptionKeyArn?: string | undefined; /** *The encryption mode for the job, which can be one of the following:
*
* SSE-KMS - Server-side encryption with keys managed by KMS.
* SSE-S3 - Server-side encryption with keys managed by Amazon S3.
The name of the job to update.
* @public */ Name: string | undefined; /** *Enables or disables Amazon CloudWatch logging for the job. If logging is enabled, * CloudWatch writes one log stream for each job run.
* @public */ LogSubscription?: LogSubscription | undefined; /** *The maximum number of nodes that DataBrew can consume when the job processes * data.
* @public */ MaxCapacity?: number | undefined; /** *The maximum number of times to retry the job after a job run fails.
* @public */ MaxRetries?: number | undefined; /** *One or more artifacts that represent the output from running the job.
* @public */ Outputs?: Output[] | undefined; /** *One or more artifacts that represent the Glue Data Catalog output from running the job.
* @public */ DataCatalogOutputs?: DataCatalogOutput[] | undefined; /** *Represents a list of JDBC database output objects which defines the output destination for a * DataBrew recipe job to write into.
* @public */ DatabaseOutputs?: DatabaseOutput[] | undefined; /** *The Amazon Resource Name (ARN) of the Identity and Access Management (IAM) role to * be assumed when DataBrew runs the job.
* @public */ RoleArn: string | undefined; /** *The job's timeout in minutes. A job that attempts to run longer than this timeout
* period ends with a status of TIMEOUT.
The name of the job that you updated.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateRulesetRequest { /** *The name of the ruleset to be updated.
* @public */ Name: string | undefined; /** *The description of the ruleset.
* @public */ Description?: string | undefined; /** *A list of rules that are defined with the ruleset. A rule includes one or more * checks to be validated on a DataBrew dataset.
* @public */ Rules: Rule[] | undefined; } /** * @public */ export interface UpdateRulesetResponse { /** *The name of the updated ruleset.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateScheduleRequest { /** *The name or names of one or more jobs to be run for this schedule.
* @public */ JobNames?: string[] | undefined; /** *The date or dates and time or times when the jobs are to be run. For more information, * see Cron * expressions in the Glue DataBrew Developer * Guide.
* @public */ CronExpression: string | undefined; /** *The name of the schedule to update.
* @public */ Name: string | undefined; } /** * @public */ export interface UpdateScheduleResponse { /** *The name of the schedule that was updated.
* @public */ Name: string | undefined; }