Docs Packages
  1. Pulumi Registry
  2. MongoDB Atlas
  3. API Docs
  4. DataLake
mongodbatlas logo
MongoDB Atlas v3.7.2, Mar 31 23

mongodbatlas.DataLake

Explore with Pulumi AI

Import

Data Lake can be imported using project ID, name of the data lake and name of the AWS s3 bucket, in the format project_id–name–aws_test_s3_bucket, e.g.

 $ pulumi import mongodbatlas:index/dataLake:DataLake example 1112222b3bf99403840e8934--test-data-lake--s3-test

See MongoDB Atlas API Documentation for more information.

Example Usage

S

using System.Collections.Generic;
using Pulumi;
using Mongodbatlas = Pulumi.Mongodbatlas;

return await Deployment.RunAsync(() => 
{
    var testProject = new Mongodbatlas.Project("testProject", new()
    {
        OrgId = "ORGANIZATION ID",
    });

    var testCloudProviderAccess = new Mongodbatlas.CloudProviderAccess("testCloudProviderAccess", new()
    {
        ProjectId = testProject.Id,
        ProviderName = "AWS",
        IamAssumedRoleArn = "AWS ROLE ID",
    });

    var basicDs = new Mongodbatlas.DataLake("basicDs", new()
    {
        ProjectId = testProject.Id,
        Aws = new Mongodbatlas.Inputs.DataLakeAwsArgs
        {
            RoleId = testCloudProviderAccess.RoleId,
            TestS3Bucket = "TEST S3 BUCKET NAME",
        },
    });

});

package main

import (
	"github.com/pulumi/pulumi-mongodbatlas/sdk/v3/go/mongodbatlas"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		testProject, err := mongodbatlas.NewProject(ctx, "testProject", &mongodbatlas.ProjectArgs{
			OrgId: pulumi.String("ORGANIZATION ID"),
		})
		if err != nil {
			return err
		}
		testCloudProviderAccess, err := mongodbatlas.NewCloudProviderAccess(ctx, "testCloudProviderAccess", &mongodbatlas.CloudProviderAccessArgs{
			ProjectId:         testProject.ID(),
			ProviderName:      pulumi.String("AWS"),
			IamAssumedRoleArn: pulumi.String("AWS ROLE ID"),
		})
		if err != nil {
			return err
		}
		_, err = mongodbatlas.NewDataLake(ctx, "basicDs", &mongodbatlas.DataLakeArgs{
			ProjectId: testProject.ID(),
			Aws: &mongodbatlas.DataLakeAwsArgs{
				RoleId:       testCloudProviderAccess.RoleId,
				TestS3Bucket: pulumi.String("TEST S3 BUCKET NAME"),
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}

package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.mongodbatlas.Project;
import com.pulumi.mongodbatlas.ProjectArgs;
import com.pulumi.mongodbatlas.CloudProviderAccess;
import com.pulumi.mongodbatlas.CloudProviderAccessArgs;
import com.pulumi.mongodbatlas.DataLake;
import com.pulumi.mongodbatlas.DataLakeArgs;
import com.pulumi.mongodbatlas.inputs.DataLakeAwsArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var testProject = new Project("testProject", ProjectArgs.builder()        
            .orgId("ORGANIZATION ID")
            .build());

        var testCloudProviderAccess = new CloudProviderAccess("testCloudProviderAccess", CloudProviderAccessArgs.builder()        
            .projectId(testProject.id())
            .providerName("AWS")
            .iamAssumedRoleArn("AWS ROLE ID")
            .build());

        var basicDs = new DataLake("basicDs", DataLakeArgs.builder()        
            .projectId(testProject.id())
            .aws(DataLakeAwsArgs.builder()
                .roleId(testCloudProviderAccess.roleId())
                .testS3Bucket("TEST S3 BUCKET NAME")
                .build())
            .build());

    }
}

import pulumi
import pulumi_mongodbatlas as mongodbatlas

test_project = mongodbatlas.Project("testProject", org_id="ORGANIZATION ID")
test_cloud_provider_access = mongodbatlas.CloudProviderAccess("testCloudProviderAccess",
    project_id=test_project.id,
    provider_name="AWS",
    iam_assumed_role_arn="AWS ROLE ID")
basic_ds = mongodbatlas.DataLake("basicDs",
    project_id=test_project.id,
    aws=mongodbatlas.DataLakeAwsArgs(
        role_id=test_cloud_provider_access.role_id,
        test_s3_bucket="TEST S3 BUCKET NAME",
    ))

import * as pulumi from "@pulumi/pulumi";
import * as mongodbatlas from "@pulumi/mongodbatlas";

const testProject = new mongodbatlas.Project("testProject", {orgId: "ORGANIZATION ID"});
const testCloudProviderAccess = new mongodbatlas.CloudProviderAccess("testCloudProviderAccess", {
    projectId: testProject.id,
    providerName: "AWS",
    iamAssumedRoleArn: "AWS ROLE ID",
});
const basicDs = new mongodbatlas.DataLake("basicDs", {
    projectId: testProject.id,
    aws: {
        roleId: testCloudProviderAccess.roleId,
        testS3Bucket: "TEST S3 BUCKET NAME",
    },
});

resources:
  testProject:
    type: mongodbatlas:Project
    properties:
      orgId: ORGANIZATION ID
  testCloudProviderAccess:
    type: mongodbatlas:CloudProviderAccess
    properties:
      projectId: ${testProject.id}
      providerName: AWS
      iamAssumedRoleArn: AWS ROLE ID
  basicDs:
    type: mongodbatlas:DataLake
    properties:
      projectId: ${testProject.id}
      aws:
        roleId: ${testCloudProviderAccess.roleId}
        testS3Bucket: TEST S3 BUCKET NAME

Create DataLake Resource

new DataLake(name: string, args: DataLakeArgs, opts?: CustomResourceOptions);
@overload
def DataLake(resource_name: str,
             opts: Optional[ResourceOptions] = None,
             aws: Optional[DataLakeAwsArgs] = None,
             data_process_region: Optional[DataLakeDataProcessRegionArgs] = None,
             name: Optional[str] = None,
             project_id: Optional[str] = None)
@overload
def DataLake(resource_name: str,
             args: DataLakeArgs,
             opts: Optional[ResourceOptions] = None)
func NewDataLake(ctx *Context, name string, args DataLakeArgs, opts ...ResourceOption) (*DataLake, error)
public DataLake(string name, DataLakeArgs args, CustomResourceOptions? opts = null)
public DataLake(String name, DataLakeArgs args)
public DataLake(String name, DataLakeArgs args, CustomResourceOptions options)

type: mongodbatlas:DataLake
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
name string
The unique name of the resource.
args DataLakeArgs
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 DataLakeArgs
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 DataLakeArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name string
The unique name of the resource.
args DataLakeArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name String
The unique name of the resource.
args DataLakeArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

DataLake 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 DataLake resource accepts the following input properties:

Aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
ProjectId string

The unique ID for the project to create a data lake.

DataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
Name string

Name of the Atlas Data Lake.

Aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
ProjectId string

The unique ID for the project to create a data lake.

DataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
Name string

Name of the Atlas Data Lake.

aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
projectId String

The unique ID for the project to create a data lake.

dataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
name String

Name of the Atlas Data Lake.

aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
projectId string

The unique ID for the project to create a data lake.

dataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
name string

Name of the Atlas Data Lake.

aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
project_id str

The unique ID for the project to create a data lake.

data_process_region DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
name str

Name of the Atlas Data Lake.

aws Property Map

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
projectId String

The unique ID for the project to create a data lake.

dataProcessRegion Property Map

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
name String

Name of the Atlas Data Lake.

Outputs

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

Hostnames List<string>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

Id string

The provider-assigned unique ID for this managed resource.

State string

Current state of the Atlas Data Lake:

StorageDatabases List<DataLakeStorageDatabase>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
StorageStores List<DataLakeStorageStore>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
Hostnames []string

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

Id string

The provider-assigned unique ID for this managed resource.

State string

Current state of the Atlas Data Lake:

StorageDatabases []DataLakeStorageDatabase

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
StorageStores []DataLakeStorageStore

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
hostnames List<String>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

id String

The provider-assigned unique ID for this managed resource.

state String

Current state of the Atlas Data Lake:

storageDatabases List<DataLakeStorageDatabase>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores List<DataLakeStorageStore>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
hostnames string[]

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

id string

The provider-assigned unique ID for this managed resource.

state string

Current state of the Atlas Data Lake:

storageDatabases DataLakeStorageDatabase[]

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores DataLakeStorageStore[]

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
hostnames Sequence[str]

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

id str

The provider-assigned unique ID for this managed resource.

state str

Current state of the Atlas Data Lake:

storage_databases Sequence[DataLakeStorageDatabase]

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storage_stores Sequence[DataLakeStorageStore]

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
hostnames List<String>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

id String

The provider-assigned unique ID for this managed resource.

state String

Current state of the Atlas Data Lake:

storageDatabases List<Property Map>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores List<Property Map>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.

Look up Existing DataLake Resource

Get an existing DataLake resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: DataLakeState, opts?: CustomResourceOptions): DataLake
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        aws: Optional[DataLakeAwsArgs] = None,
        data_process_region: Optional[DataLakeDataProcessRegionArgs] = None,
        hostnames: Optional[Sequence[str]] = None,
        name: Optional[str] = None,
        project_id: Optional[str] = None,
        state: Optional[str] = None,
        storage_databases: Optional[Sequence[DataLakeStorageDatabaseArgs]] = None,
        storage_stores: Optional[Sequence[DataLakeStorageStoreArgs]] = None) -> DataLake
func GetDataLake(ctx *Context, name string, id IDInput, state *DataLakeState, opts ...ResourceOption) (*DataLake, error)
public static DataLake Get(string name, Input<string> id, DataLakeState? state, CustomResourceOptions? opts = null)
public static DataLake get(String name, Output<String> id, DataLakeState state, CustomResourceOptions options)
Resource lookup is not supported in YAML
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
resource_name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name
The unique name of the resulting resource.
id
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
The following state arguments are supported:
Aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
DataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
Hostnames List<string>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

Name string

Name of the Atlas Data Lake.

ProjectId string

The unique ID for the project to create a data lake.

State string

Current state of the Atlas Data Lake:

StorageDatabases List<DataLakeStorageDatabaseArgs>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
StorageStores List<DataLakeStorageStoreArgs>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
Aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
DataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
Hostnames []string

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

Name string

Name of the Atlas Data Lake.

ProjectId string

The unique ID for the project to create a data lake.

State string

Current state of the Atlas Data Lake:

StorageDatabases []DataLakeStorageDatabaseArgs

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
StorageStores []DataLakeStorageStoreArgs

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
dataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
hostnames List<String>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

name String

Name of the Atlas Data Lake.

projectId String

The unique ID for the project to create a data lake.

state String

Current state of the Atlas Data Lake:

storageDatabases List<DataLakeStorageDatabaseArgs>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores List<DataLakeStorageStoreArgs>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
dataProcessRegion DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
hostnames string[]

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

name string

Name of the Atlas Data Lake.

projectId string

The unique ID for the project to create a data lake.

state string

Current state of the Atlas Data Lake:

storageDatabases DataLakeStorageDatabaseArgs[]

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores DataLakeStorageStoreArgs[]

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
aws DataLakeAwsArgs

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
data_process_region DataLakeDataProcessRegionArgs

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
hostnames Sequence[str]

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

name str

Name of the Atlas Data Lake.

project_id str

The unique ID for the project to create a data lake.

state str

Current state of the Atlas Data Lake:

storage_databases Sequence[DataLakeStorageDatabaseArgs]

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storage_stores Sequence[DataLakeStorageStoreArgs]

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.
aws Property Map

AWS provider of the cloud service where Data Lake can access the S3 Bucket.

  • aws.0.role_id - (Required) Unique identifier of the role that Data Lake can use to access the data stores. If necessary, use the Atlas UI or API to retrieve the role ID. You must also specify the aws.0.test_s3_bucket.
  • aws.0.test_s3_bucket - (Required) Name of the S3 data bucket that the provided role ID is authorized to access. You must also specify the aws.0.role_id.
dataProcessRegion Property Map

The cloud provider region to which Atlas Data Lake routes client connections for data processing. Set to null to direct Atlas Data Lake to route client connections to the region nearest to the client based on DNS resolution.

  • data_process_region.0.cloud_provider - (Required) Name of the cloud service provider. Atlas Data Lake only supports AWS.
  • data_process_region.0.region - (Required). Name of the region to which Data Lake routes client connections for data processing. Atlas Data Lake only supports the following regions:
hostnames List<String>

The list of hostnames assigned to the Atlas Data Lake. Each string in the array is a hostname assigned to the Atlas Data Lake.

name String

Name of the Atlas Data Lake.

projectId String

The unique ID for the project to create a data lake.

state String

Current state of the Atlas Data Lake:

storageDatabases List<Property Map>

Configuration details for mapping each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see databases. An empty object indicates that the Data Lake has no mapping configuration for any data store.

  • storage_databases.#.name - Name of the database to which Data Lake maps the data contained in the data store.
  • storage_databases.#.collections - Array of objects where each object represents a collection and data sources that map to a stores data store.
  • storage_databases.#.collections.#.name - Name of the collection.
  • storage_databases.#.collections.#.data_sources - Array of objects where each object represents a stores data store to map with the collection.
  • storage_databases.#.collections.#.data_sources.#.store_name - Name of a data store to map to the <collection>. Must match the name of an object in the stores array.
  • storage_databases.#.collections.#.data_sources.#.default_format - Default format that Data Lake assumes if it encounters a file without an extension while searching the storeName.
  • storage_databases.#.collections.#.data_sources.#.path - Controls how Atlas Data Lake searches for and parses files in the storeName before mapping them to the <collection>.
  • storage_databases.#.views - Array of objects where each object represents an aggregation pipeline on a collection. To learn more about views, see Views.
  • storage_databases.#.views.#.name - Name of the view.
  • storage_databases.#.views.#.source - Name of the source collection for the view.
  • storage_databases.#.views.#.pipeline- Aggregation pipeline stage(s) to apply to the source collection.
storageStores List<Property Map>

Each object in the array represents a data store. Data Lake uses the storage.databases configuration details to map data in each data store to queryable databases and collections. For complete documentation on this object and its nested fields, see stores. An empty object indicates that the Data Lake has no configured data stores.

  • storage_stores.#.name - Name of the data store.
  • storage_stores.#.provider - Defines where the data is stored.
  • storage_stores.#.region - Name of the AWS region in which the S3 bucket is hosted.
  • storage_stores.#.bucket - Name of the AWS S3 bucket.
  • storage_stores.#.prefix - Prefix Data Lake applies when searching for files in the S3 bucket .
  • storage_stores.#.delimiter - The delimiter that separates storage_databases.#.collections.#.data_sources.#.path segments in the data store.
  • storage_stores.#.include_tags - Determines whether or not to use S3 tags on the files in the given path as additional partition attributes.

Supporting Types

DataLakeAws

DataLakeDataProcessRegion

CloudProvider string
Region string
CloudProvider string
Region string
cloudProvider String
region String
cloudProvider string
region string
cloudProvider String
region String

DataLakeStorageDatabase

DataLakeStorageDatabaseCollection

dataSources List<Property Map>
name String

Name of the Atlas Data Lake.

DataLakeStorageDatabaseCollectionDataSource

DefaultFormat string
Path string
StoreName string
DefaultFormat string
Path string
StoreName string
defaultFormat String
path String
storeName String
defaultFormat string
path string
storeName string
defaultFormat String
path String
storeName String

DataLakeStorageDatabaseView

Name string

Name of the Atlas Data Lake.

Pipeline string
Source string
Name string

Name of the Atlas Data Lake.

Pipeline string
Source string
name String

Name of the Atlas Data Lake.

pipeline String
source String
name string

Name of the Atlas Data Lake.

pipeline string
source string
name str

Name of the Atlas Data Lake.

pipeline str
source str
name String

Name of the Atlas Data Lake.

pipeline String
source String

DataLakeStorageStore

AdditionalStorageClasses List<string>
Bucket string
Delimiter string
IncludeTags bool
Name string

Name of the Atlas Data Lake.

Prefix string
Provider string
Region string
AdditionalStorageClasses []string
Bucket string
Delimiter string
IncludeTags bool
Name string

Name of the Atlas Data Lake.

Prefix string
Provider string
Region string
additionalStorageClasses List<String>
bucket String
delimiter String
includeTags Boolean
name String

Name of the Atlas Data Lake.

prefix String
provider String
region String
additionalStorageClasses string[]
bucket string
delimiter string
includeTags boolean
name string

Name of the Atlas Data Lake.

prefix string
provider string
region string
additional_storage_classes Sequence[str]
bucket str
delimiter str
include_tags bool
name str

Name of the Atlas Data Lake.

prefix str
provider str
region str
additionalStorageClasses List<String>
bucket String
delimiter String
includeTags Boolean
name String

Name of the Atlas Data Lake.

prefix String
provider String
region String

Package Details

Repository
MongoDB Atlas pulumi/pulumi-mongodbatlas
License
Apache-2.0
Notes

This Pulumi package is based on the mongodbatlas Terraform Provider.