1. Packages
  2. AWS Native
  3. API Docs
  4. databrew
  5. Dataset

AWS Native is in preview. AWS Classic is fully supported.

AWS Native v0.103.0 published on Monday, Apr 22, 2024 by Pulumi

aws-native.databrew.Dataset

Explore with Pulumi AI

aws-native logo

AWS Native is in preview. AWS Classic is fully supported.

AWS Native v0.103.0 published on Monday, Apr 22, 2024 by Pulumi

    Resource schema for AWS::DataBrew::Dataset.

    Example Usage

    Example

    using System.Collections.Generic;
    using System.Linq;
    using Pulumi;
    using AwsNative = Pulumi.AwsNative;
    
    return await Deployment.RunAsync(() => 
    {
        var testDataBrewDataset = new AwsNative.DataBrew.Dataset("testDataBrewDataset", new()
        {
            Name = "cf-test-dataset1",
            Input = new AwsNative.DataBrew.Inputs.DatasetInputArgs
            {
                S3InputDefinition = new AwsNative.DataBrew.Inputs.DatasetS3LocationArgs
                {
                    Bucket = "test-location",
                    Key = "test.xlsx",
                },
            },
            FormatOptions = new AwsNative.DataBrew.Inputs.DatasetFormatOptionsArgs
            {
                Excel = new AwsNative.DataBrew.Inputs.DatasetExcelOptionsArgs
                {
                    SheetNames = new[]
                    {
                        "test",
                    },
                },
            },
            Tags = new[]
            {
                new AwsNative.Inputs.CreateOnlyTagArgs
                {
                    Key = "key00AtCreate",
                    Value = "value001AtCreate",
                },
            },
        });
    
    });
    
    package main
    
    import (
    	awsnative "github.com/pulumi/pulumi-aws-native/sdk/go/aws"
    	"github.com/pulumi/pulumi-aws-native/sdk/go/aws/databrew"
    	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
    )
    
    func main() {
    	pulumi.Run(func(ctx *pulumi.Context) error {
    		_, err := databrew.NewDataset(ctx, "testDataBrewDataset", &databrew.DatasetArgs{
    			Name: pulumi.String("cf-test-dataset1"),
    			Input: &databrew.DatasetInputTypeArgs{
    				S3InputDefinition: &databrew.DatasetS3LocationArgs{
    					Bucket: pulumi.String("test-location"),
    					Key:    pulumi.String("test.xlsx"),
    				},
    			},
    			FormatOptions: &databrew.DatasetFormatOptionsArgs{
    				Excel: &databrew.DatasetExcelOptionsArgs{
    					SheetNames: pulumi.StringArray{
    						pulumi.String("test"),
    					},
    				},
    			},
    			Tags: aws.CreateOnlyTagArray{
    				&aws.CreateOnlyTagArgs{
    					Key:   pulumi.String("key00AtCreate"),
    					Value: pulumi.String("value001AtCreate"),
    				},
    			},
    		})
    		if err != nil {
    			return err
    		}
    		return nil
    	})
    }
    

    Coming soon!

    import pulumi
    import pulumi_aws_native as aws_native
    
    test_data_brew_dataset = aws_native.databrew.Dataset("testDataBrewDataset",
        name="cf-test-dataset1",
        input=aws_native.databrew.DatasetInputArgs(
            s3_input_definition=aws_native.databrew.DatasetS3LocationArgs(
                bucket="test-location",
                key="test.xlsx",
            ),
        ),
        format_options=aws_native.databrew.DatasetFormatOptionsArgs(
            excel=aws_native.databrew.DatasetExcelOptionsArgs(
                sheet_names=["test"],
            ),
        ),
        tags=[aws_native.CreateOnlyTagArgs(
            key="key00AtCreate",
            value="value001AtCreate",
        )])
    
    import * as pulumi from "@pulumi/pulumi";
    import * as aws_native from "@pulumi/aws-native";
    
    const testDataBrewDataset = new aws_native.databrew.Dataset("testDataBrewDataset", {
        name: "cf-test-dataset1",
        input: {
            s3InputDefinition: {
                bucket: "test-location",
                key: "test.xlsx",
            },
        },
        formatOptions: {
            excel: {
                sheetNames: ["test"],
            },
        },
        tags: [{
            key: "key00AtCreate",
            value: "value001AtCreate",
        }],
    });
    

    Coming soon!

    Create Dataset Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new Dataset(name: string, args: DatasetArgs, opts?: CustomResourceOptions);
    @overload
    def Dataset(resource_name: str,
                args: DatasetArgs,
                opts: Optional[ResourceOptions] = None)
    
    @overload
    def Dataset(resource_name: str,
                opts: Optional[ResourceOptions] = None,
                input: Optional[DatasetInputArgs] = None,
                format: Optional[DatasetFormat] = None,
                format_options: Optional[DatasetFormatOptionsArgs] = None,
                name: Optional[str] = None,
                path_options: Optional[DatasetPathOptionsArgs] = None,
                tags: Optional[Sequence[_root_inputs.CreateOnlyTagArgs]] = None)
    func NewDataset(ctx *Context, name string, args DatasetArgs, opts ...ResourceOption) (*Dataset, error)
    public Dataset(string name, DatasetArgs args, CustomResourceOptions? opts = null)
    public Dataset(String name, DatasetArgs args)
    public Dataset(String name, DatasetArgs args, CustomResourceOptions options)
    
    type: aws-native:databrew:Dataset
    properties: # The arguments to resource properties.
    options: # Bag of options to control resource's behavior.
    
    

    Parameters

    name string
    The unique name of the resource.
    args DatasetArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args DatasetArgs
    The arguments to resource properties.
    opts ResourceOptions
    Bag of options to control resource's behavior.
    ctx Context
    Context object for the current deployment.
    name string
    The unique name of the resource.
    args DatasetArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args DatasetArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args DatasetArgs
    The arguments to resource properties.
    options CustomResourceOptions
    Bag of options to control resource's behavior.

    Example

    The following reference example uses placeholder values for all input properties.

    Coming soon!
    
    Coming soon!
    
    Coming soon!
    
    Coming soon!
    
    const datasetResource = new aws_native.databrew.Dataset("datasetResource", {
        input: {
            dataCatalogInputDefinition: {
                catalogId: "string",
                databaseName: "string",
                tableName: "string",
                tempDirectory: {
                    bucket: "string",
                    key: "string",
                },
            },
            databaseInputDefinition: {
                glueConnectionName: "string",
                databaseTableName: "string",
                queryString: "string",
                tempDirectory: {
                    bucket: "string",
                    key: "string",
                },
            },
            metadata: {
                sourceArn: "string",
            },
            s3InputDefinition: {
                bucket: "string",
                key: "string",
            },
        },
        format: aws_native.databrew.DatasetFormat.Csv,
        formatOptions: {
            csv: {
                delimiter: "string",
                headerRow: false,
            },
            excel: {
                headerRow: false,
                sheetIndexes: [0],
                sheetNames: ["string"],
            },
            json: {
                multiLine: false,
            },
        },
        name: "string",
        pathOptions: {
            filesLimit: {
                maxFiles: 0,
                order: aws_native.databrew.DatasetFilesLimitOrder.Ascending,
                orderedBy: aws_native.databrew.DatasetFilesLimitOrderedBy.LastModifiedDate,
            },
            lastModifiedDateCondition: {
                expression: "string",
                valuesMap: [{
                    value: "string",
                    valueReference: "string",
                }],
            },
            parameters: [{
                datasetParameter: {
                    name: "string",
                    type: aws_native.databrew.DatasetParameterType.String,
                    createColumn: false,
                    datetimeOptions: {
                        format: "string",
                        localeCode: "string",
                        timezoneOffset: "string",
                    },
                    filter: {
                        expression: "string",
                        valuesMap: [{
                            value: "string",
                            valueReference: "string",
                        }],
                    },
                },
                pathParameterName: "string",
            }],
        },
        tags: [{
            key: "string",
            value: "string",
        }],
    });
    
    Coming soon!
    

    Dataset Resource Properties

    To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

    Inputs

    The Dataset resource accepts the following input properties:

    Outputs

    All input properties are implicitly available as output properties. Additionally, the Dataset resource produces the following output properties:

    Id string
    The provider-assigned unique ID for this managed resource.
    Id string
    The provider-assigned unique ID for this managed resource.
    id String
    The provider-assigned unique ID for this managed resource.
    id string
    The provider-assigned unique ID for this managed resource.
    id str
    The provider-assigned unique ID for this managed resource.
    id String
    The provider-assigned unique ID for this managed resource.

    Supporting Types

    CreateOnlyTag, CreateOnlyTagArgs

    Key string
    The key name of the tag
    Value string
    The value of the tag
    Key string
    The key name of the tag
    Value string
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag
    key string
    The key name of the tag
    value string
    The value of the tag
    key str
    The key name of the tag
    value str
    The value of the tag
    key String
    The key name of the tag
    value String
    The value of the tag

    DatasetCsvOptions, DatasetCsvOptionsArgs

    Delimiter string
    HeaderRow bool
    Delimiter string
    HeaderRow bool
    delimiter String
    headerRow Boolean
    delimiter string
    headerRow boolean
    delimiter String
    headerRow Boolean

    DatasetDataCatalogInputDefinition, DatasetDataCatalogInputDefinitionArgs

    CatalogId string
    Catalog id
    DatabaseName string
    Database name
    TableName string
    Table name
    TempDirectory DatasetS3Location
    catalogId String
    Catalog id
    databaseName String
    Database name
    tableName String
    Table name
    tempDirectory DatasetS3Location
    catalogId string
    Catalog id
    databaseName string
    Database name
    tableName string
    Table name
    tempDirectory DatasetS3Location
    catalog_id str
    Catalog id
    database_name str
    Database name
    table_name str
    Table name
    temp_directory DatasetS3Location
    catalogId String
    Catalog id
    databaseName String
    Database name
    tableName String
    Table name
    tempDirectory Property Map

    DatasetDatabaseInputDefinition, DatasetDatabaseInputDefinitionArgs

    GlueConnectionName string
    Glue connection name
    DatabaseTableName string
    Database table name
    QueryString string
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    TempDirectory Pulumi.AwsNative.DataBrew.Inputs.DatasetS3Location
    GlueConnectionName string
    Glue connection name
    DatabaseTableName string
    Database table name
    QueryString string
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    TempDirectory DatasetS3Location
    glueConnectionName String
    Glue connection name
    databaseTableName String
    Database table name
    queryString String
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    tempDirectory DatasetS3Location
    glueConnectionName string
    Glue connection name
    databaseTableName string
    Database table name
    queryString string
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    tempDirectory DatasetS3Location
    glue_connection_name str
    Glue connection name
    database_table_name str
    Database table name
    query_string str
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    temp_directory DatasetS3Location
    glueConnectionName String
    Glue connection name
    databaseTableName String
    Database table name
    queryString String
    Custom SQL to run against the provided AWS Glue connection. This SQL will be used as the input for DataBrew projects and jobs.
    tempDirectory Property Map

    DatasetDatetimeOptions, DatasetDatetimeOptionsArgs

    Format string
    Date/time format of a date parameter
    LocaleCode string
    Locale code for a date parameter
    TimezoneOffset string
    Timezone offset
    Format string
    Date/time format of a date parameter
    LocaleCode string
    Locale code for a date parameter
    TimezoneOffset string
    Timezone offset
    format String
    Date/time format of a date parameter
    localeCode String
    Locale code for a date parameter
    timezoneOffset String
    Timezone offset
    format string
    Date/time format of a date parameter
    localeCode string
    Locale code for a date parameter
    timezoneOffset string
    Timezone offset
    format str
    Date/time format of a date parameter
    locale_code str
    Locale code for a date parameter
    timezone_offset str
    Timezone offset
    format String
    Date/time format of a date parameter
    localeCode String
    Locale code for a date parameter
    timezoneOffset String
    Timezone offset

    DatasetExcelOptions, DatasetExcelOptionsArgs

    HeaderRow bool
    SheetIndexes List<int>
    SheetNames List<string>
    headerRow Boolean
    sheetIndexes List<Integer>
    sheetNames List<String>
    headerRow boolean
    sheetIndexes number[]
    sheetNames string[]
    header_row bool
    sheet_indexes Sequence[int]
    sheet_names Sequence[str]
    headerRow Boolean
    sheetIndexes List<Number>
    sheetNames List<String>

    DatasetFilesLimit, DatasetFilesLimitArgs

    maxFiles Integer
    Maximum number of files
    order DatasetFilesLimitOrder
    Order
    orderedBy DatasetFilesLimitOrderedBy
    Ordered by
    maxFiles number
    Maximum number of files
    order DatasetFilesLimitOrder
    Order
    orderedBy DatasetFilesLimitOrderedBy
    Ordered by
    maxFiles Number
    Maximum number of files
    order "ASCENDING" | "DESCENDING"
    Order
    orderedBy "LAST_MODIFIED_DATE"
    Ordered by

    DatasetFilesLimitOrder, DatasetFilesLimitOrderArgs

    Ascending
    ASCENDING
    Descending
    DESCENDING
    DatasetFilesLimitOrderAscending
    ASCENDING
    DatasetFilesLimitOrderDescending
    DESCENDING
    Ascending
    ASCENDING
    Descending
    DESCENDING
    Ascending
    ASCENDING
    Descending
    DESCENDING
    ASCENDING
    ASCENDING
    DESCENDING
    DESCENDING
    "ASCENDING"
    ASCENDING
    "DESCENDING"
    DESCENDING

    DatasetFilesLimitOrderedBy, DatasetFilesLimitOrderedByArgs

    LastModifiedDate
    LAST_MODIFIED_DATE
    DatasetFilesLimitOrderedByLastModifiedDate
    LAST_MODIFIED_DATE
    LastModifiedDate
    LAST_MODIFIED_DATE
    LastModifiedDate
    LAST_MODIFIED_DATE
    LAST_MODIFIED_DATE
    LAST_MODIFIED_DATE
    "LAST_MODIFIED_DATE"
    LAST_MODIFIED_DATE

    DatasetFilterExpression, DatasetFilterExpressionArgs

    Expression string
    Filtering expression for a parameter
    ValuesMap []DatasetFilterValue
    expression String
    Filtering expression for a parameter
    valuesMap List<DatasetFilterValue>
    expression string
    Filtering expression for a parameter
    valuesMap DatasetFilterValue[]
    expression str
    Filtering expression for a parameter
    values_map Sequence[DatasetFilterValue]
    expression String
    Filtering expression for a parameter
    valuesMap List<Property Map>

    DatasetFilterValue, DatasetFilterValueArgs

    Value string
    ValueReference string
    Variable name
    Value string
    ValueReference string
    Variable name
    value String
    valueReference String
    Variable name
    value string
    valueReference string
    Variable name
    value str
    value_reference str
    Variable name
    value String
    valueReference String
    Variable name

    DatasetFormat, DatasetFormatArgs

    Csv
    CSV
    Json
    JSON
    Parquet
    PARQUET
    Excel
    EXCEL
    Orc
    ORC
    DatasetFormatCsv
    CSV
    DatasetFormatJson
    JSON
    DatasetFormatParquet
    PARQUET
    DatasetFormatExcel
    EXCEL
    DatasetFormatOrc
    ORC
    Csv
    CSV
    Json
    JSON
    Parquet
    PARQUET
    Excel
    EXCEL
    Orc
    ORC
    Csv
    CSV
    Json
    JSON
    Parquet
    PARQUET
    Excel
    EXCEL
    Orc
    ORC
    CSV
    CSV
    JSON
    JSON
    PARQUET
    PARQUET
    EXCEL
    EXCEL
    ORC
    ORC
    "CSV"
    CSV
    "JSON"
    JSON
    "PARQUET"
    PARQUET
    "EXCEL"
    EXCEL
    "ORC"
    ORC

    DatasetFormatOptions, DatasetFormatOptionsArgs

    DatasetInput, DatasetInputArgs

    DatasetJsonOptions, DatasetJsonOptionsArgs

    multiLine Boolean
    multiLine boolean
    multiLine Boolean

    DatasetMetadata, DatasetMetadataArgs

    SourceArn string
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.
    SourceArn string
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.
    sourceArn String
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.
    sourceArn string
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.
    source_arn str
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.
    sourceArn String
    Arn of the source of the dataset. For e.g.: AppFlow Flow ARN.

    DatasetParameter, DatasetParameterArgs

    Name string
    Type DatasetParameterType
    Parameter type
    CreateColumn bool
    Add the value of this parameter as a column in a dataset.
    DatetimeOptions DatasetDatetimeOptions
    Filter DatasetFilterExpression
    name String
    type DatasetParameterType
    Parameter type
    createColumn Boolean
    Add the value of this parameter as a column in a dataset.
    datetimeOptions DatasetDatetimeOptions
    filter DatasetFilterExpression
    name string
    type DatasetParameterType
    Parameter type
    createColumn boolean
    Add the value of this parameter as a column in a dataset.
    datetimeOptions DatasetDatetimeOptions
    filter DatasetFilterExpression
    name str
    type DatasetParameterType
    Parameter type
    create_column bool
    Add the value of this parameter as a column in a dataset.
    datetime_options DatasetDatetimeOptions
    filter DatasetFilterExpression
    name String
    type "String" | "Number" | "Datetime"
    Parameter type
    createColumn Boolean
    Add the value of this parameter as a column in a dataset.
    datetimeOptions Property Map
    filter Property Map

    DatasetParameterType, DatasetParameterTypeArgs

    String
    String
    Number
    Number
    Datetime
    Datetime
    DatasetParameterTypeString
    String
    DatasetParameterTypeNumber
    Number
    DatasetParameterTypeDatetime
    Datetime
    String
    String
    Number
    Number
    Datetime
    Datetime
    String
    String
    Number
    Number
    Datetime
    Datetime
    STRING
    String
    NUMBER
    Number
    DATETIME
    Datetime
    "String"
    String
    "Number"
    Number
    "Datetime"
    Datetime

    DatasetPathOptions, DatasetPathOptionsArgs

    DatasetPathParameter, DatasetPathParameterArgs

    DatasetS3Location, DatasetS3LocationArgs

    Bucket string
    Key string
    Bucket string
    Key string
    bucket String
    key String
    bucket string
    key string
    bucket str
    key str
    bucket String
    key String

    Package Details

    Repository
    AWS Native pulumi/pulumi-aws-native
    License
    Apache-2.0
    aws-native logo

    AWS Native is in preview. AWS Classic is fully supported.

    AWS Native v0.103.0 published on Monday, Apr 22, 2024 by Pulumi