Dataset
Example Usage
Bigquery Dataset Basic
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.serviceAccount.Account;
import com.pulumi.gcp.serviceAccount.AccountArgs;
import com.pulumi.gcp.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessArgs;
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 bqowner = new Account("bqowner", AccountArgs.builder()
.accountId("bqowner")
.build());
var dataset = new Dataset("dataset", DatasetArgs.builder()
.datasetId("example_dataset")
.friendlyName("test")
.description("This is a test description")
.location("EU")
.defaultTableExpirationMs(3600000)
.labels(Map.of("env", "default"))
.accesses(
DatasetAccessArgs.builder()
.role("OWNER")
.userByEmail(bqowner.email())
.build(),
DatasetAccessArgs.builder()
.role("READER")
.domain("hashicorp.com")
.build())
.build());
}
}Bigquery Dataset Cmek
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.kms.KeyRing;
import com.pulumi.gcp.kms.KeyRingArgs;
import com.pulumi.gcp.kms.CryptoKey;
import com.pulumi.gcp.kms.CryptoKeyArgs;
import com.pulumi.gcp.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetDefaultEncryptionConfigurationArgs;
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 keyRing = new KeyRing("keyRing", KeyRingArgs.builder()
.location("us")
.build());
var cryptoKey = new CryptoKey("cryptoKey", CryptoKeyArgs.builder()
.keyRing(keyRing.id())
.build());
var dataset = new Dataset("dataset", DatasetArgs.builder()
.datasetId("example_dataset")
.friendlyName("test")
.description("This is a test description")
.location("US")
.defaultTableExpirationMs(3600000)
.defaultEncryptionConfiguration(DatasetDefaultEncryptionConfigurationArgs.builder()
.kmsKeyName(cryptoKey.id())
.build())
.build());
}
}Bigquery Dataset Authorized Dataset
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.serviceAccount.Account;
import com.pulumi.gcp.serviceAccount.AccountArgs;
import com.pulumi.gcp.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessDatasetArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessDatasetDatasetArgs;
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 bqowner = new Account("bqowner", AccountArgs.builder()
.accountId("bqowner")
.build());
var public_ = new Dataset("public", DatasetArgs.builder()
.datasetId("public")
.friendlyName("test")
.description("This dataset is public")
.location("EU")
.defaultTableExpirationMs(3600000)
.labels(Map.of("env", "default"))
.accesses(
DatasetAccessArgs.builder()
.role("OWNER")
.userByEmail(bqowner.email())
.build(),
DatasetAccessArgs.builder()
.role("READER")
.domain("hashicorp.com")
.build())
.build());
var dataset = new Dataset("dataset", DatasetArgs.builder()
.datasetId("private")
.friendlyName("test")
.description("This dataset is private")
.location("EU")
.defaultTableExpirationMs(3600000)
.labels(Map.of("env", "default"))
.accesses(
DatasetAccessArgs.builder()
.role("OWNER")
.userByEmail(bqowner.email())
.build(),
DatasetAccessArgs.builder()
.role("READER")
.domain("hashicorp.com")
.build(),
DatasetAccessArgs.builder()
.dataset(DatasetAccessDatasetArgs.builder()
.dataset(DatasetAccessDatasetDatasetArgs.builder()
.projectId(public_.project())
.datasetId(public_.datasetId())
.build())
.targetTypes("VIEWS")
.build())
.build())
.build());
}
}Bigquery Dataset Authorized Routine
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
import com.pulumi.gcp.bigquery.Routine;
import com.pulumi.gcp.bigquery.RoutineArgs;
import com.pulumi.gcp.bigquery.inputs.RoutineArgumentArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessArgs;
import com.pulumi.gcp.bigquery.inputs.DatasetAccessRoutineArgs;
import static com.pulumi.codegen.internal.Serialization.*;
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 publicDataset = new Dataset("publicDataset", DatasetArgs.builder()
.datasetId("public_dataset")
.description("This dataset is public")
.build());
var publicRoutine = new Routine("publicRoutine", RoutineArgs.builder()
.datasetId(publicDataset.datasetId())
.routineId("public_routine")
.routineType("TABLE_VALUED_FUNCTION")
.language("SQL")
.definitionBody("""
SELECT 1 + value AS value
""")
.arguments(RoutineArgumentArgs.builder()
.name("value")
.argumentKind("FIXED_TYPE")
.dataType(serializeJson(
jsonObject(
jsonProperty("typeKind", "INT64")
)))
.build())
.returnTableType(serializeJson(
jsonObject(
jsonProperty("columns", jsonArray(jsonObject(
jsonProperty("name", "value"),
jsonProperty("type", jsonObject(
jsonProperty("typeKind", "INT64")
))
)))
)))
.build());
var private_ = new Dataset("private", DatasetArgs.builder()
.datasetId("private_dataset")
.description("This dataset is private")
.accesses(
DatasetAccessArgs.builder()
.role("OWNER")
.userByEmail("my@service-account.com")
.build(),
DatasetAccessArgs.builder()
.routine(DatasetAccessRoutineArgs.builder()
.projectId(publicRoutine.project())
.datasetId(publicRoutine.datasetId())
.routineId(publicRoutine.routineId())
.build())
.build())
.build());
}
}Import
Dataset can be imported using any of these accepted formats
$ pulumi import gcp:bigquery/dataset:Dataset default projects/{{project}}/datasets/{{dataset_id}}$ pulumi import gcp:bigquery/dataset:Dataset default {{project}}/{{dataset_id}}$ pulumi import gcp:bigquery/dataset:Dataset default {{dataset_id}}Properties
An array of objects that define dataset access for one or more entities. Structure is documented below.
The time when this dataset was created, in milliseconds since the epoch.
Defines the default collation specification of future tables created in the dataset. If a table is created in this dataset without table-level default collation, then the table inherits the dataset default collation, which is applied to the string fields that do not have explicit collation specified. A change to this field affects only tables created afterwards, and does not alter the existing tables. The following values are supported:
The default encryption key for all tables in the dataset. Once this property is set, all newly-created partitioned tables in the dataset will have encryption key set to this value, unless table creation request (or query) overrides the key. Structure is documented below.
The default partition expiration for all partitioned tables in the dataset, in milliseconds. Once this property is set, all newly-created partitioned tables in the dataset will have an expirationMs property in the timePartitioning settings set to this value, and changing the value will only affect new tables, not existing ones. The storage in a partition will have an expiration time of its partition time plus this value. Setting this property overrides the use of defaultTableExpirationMs for partitioned tables: only one of defaultTableExpirationMs and defaultPartitionExpirationMs will be used for any new partitioned table. If you provide an explicit timePartitioning.expirationMs when creating or updating a partitioned table, that value takes precedence over the default partition expiration time indicated by this property.
The default lifetime of all tables in the dataset, in milliseconds. The minimum value is 3600000 milliseconds (one hour). Once this property is set, all newly-created tables in the dataset will have an expirationTime property set to the creation time plus the value in this property, and changing the value will only affect new tables, not existing ones. When the expirationTime for a given table is reached, that table will be deleted automatically. If a table's expirationTime is modified or removed before the table expires, or if you provide an explicit expirationTime when creating a table, that value takes precedence over the default expiration time indicated by this property.
If set to true, delete all the tables in the dataset when destroying the resource; otherwise, destroying the resource will fail if tables are present.
A user-friendly description of the dataset
A descriptive name for the dataset
TRUE if the dataset and its table names are case-insensitive, otherwise FALSE. By default, this is FALSE, which means the dataset and its table names are case-sensitive. This field does not affect routine references.
The date when this dataset or any of its tables was last modified, in milliseconds since the epoch.
The geographic location where the dataset should reside. See official docs. There are two types of locations, regional or multi-regional. A regional location is a specific geographic place, such as Tokyo, and a multi-regional location is a large geographic area, such as the United States, that contains at least two geographic places. The default value is multi-regional location US. Changing this forces a new resource to be created.
Defines the time travel window in hours. The value can be from 48 to 168 hours (2 to 7 days).
Specifies the storage billing model for the dataset. Set this flag value to LOGICAL to use logical bytes for storage billing, or to PHYSICAL to use physical bytes instead. LOGICAL is the default if this flag isn't specified.