Create a scheduled query with a service account

Schedule a query to run every 24 hours with a destination table identifier based on the run date. The query is executed as a service account user.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Java

Before trying this sample, follow the Java setup instructions in the BigQuery quickstart using client libraries. For more information, see the BigQuery Java API reference documentation.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.bigquery.datatransfer.v1.CreateTransferConfigRequest;
import com.google.cloud.bigquery.datatransfer.v1.DataTransferServiceClient;
import com.google.cloud.bigquery.datatransfer.v1.ProjectName;
import com.google.cloud.bigquery.datatransfer.v1.TransferConfig;
import com.google.protobuf.Struct;
import com.google.protobuf.Value;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

// Sample to create a scheduled query with service account
public class CreateScheduledQueryWithServiceAccount {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    final String projectId = "MY_PROJECT_ID";
    final String datasetId = "MY_DATASET_ID";
    final String serviceAccount = "MY_SERVICE_ACCOUNT";
    final String query =
        "SELECT CURRENT_TIMESTAMP() as current_time, @run_time as intended_run_time, "
            + "@run_date as intended_run_date, 17 as some_integer";
    Map<String, Value> params = new HashMap<>();
    params.put("query", Value.newBuilder().setStringValue(query).build());
    params.put(
        "destination_table_name_template",
        Value.newBuilder().setStringValue("my_destination_table_{run_date}").build());
    params.put("write_disposition", Value.newBuilder().setStringValue("WRITE_TRUNCATE").build());
    params.put("partitioning_field", Value.newBuilder().build());
    TransferConfig transferConfig =
        TransferConfig.newBuilder()
            .setDestinationDatasetId(datasetId)
            .setDisplayName("Your Scheduled Query Name")
            .setDataSourceId("scheduled_query")
            .setParams(Struct.newBuilder().putAllFields(params).build())
            .setSchedule("every 24 hours")
            .build();
    createScheduledQueryWithServiceAccount(projectId, transferConfig, serviceAccount);
  }

  public static void createScheduledQueryWithServiceAccount(
      String projectId, TransferConfig transferConfig, String serviceAccount) throws IOException {
    try (DataTransferServiceClient dataTransferServiceClient = DataTransferServiceClient.create()) {
      ProjectName parent = ProjectName.of(projectId);
      CreateTransferConfigRequest request =
          CreateTransferConfigRequest.newBuilder()
              .setParent(parent.toString())
              .setTransferConfig(transferConfig)
              .setServiceAccountName(serviceAccount)
              .build();
      TransferConfig config = dataTransferServiceClient.createTransferConfig(request);
      System.out.println(
          "\nScheduled query with service account created successfully :" + config.getName());
    } catch (ApiException ex) {
      System.out.print("\nScheduled query with service account was not created." + ex.toString());
    }
  }
}

Python

Before trying this sample, follow the Python setup instructions in the BigQuery quickstart using client libraries. For more information, see the BigQuery Python API reference documentation.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

from google.cloud import bigquery_datatransfer

transfer_client = bigquery_datatransfer.DataTransferServiceClient()

# The project where the query job runs is the same as the project
# containing the destination dataset.
project_id = "your-project-id"
dataset_id = "your_dataset_id"

# This service account will be used to execute the scheduled queries. Omit
# this request parameter to run the query as the user with the credentials
# associated with this client.
service_account_name = "abcdef-test-sa@abcdef-test.iam.gserviceaccount.com"

# Use standard SQL syntax for the query.
query_string = """
SELECT
  CURRENT_TIMESTAMP() as current_time,
  @run_time as intended_run_time,
  @run_date as intended_run_date,
  17 as some_integer
"""

parent = transfer_client.common_project_path(project_id)

transfer_config = bigquery_datatransfer.TransferConfig(
    destination_dataset_id=dataset_id,
    display_name="Your Scheduled Query Name",
    data_source_id="scheduled_query",
    params={
        "query": query_string,
        "destination_table_name_template": "your_table_{run_date}",
        "write_disposition": "WRITE_TRUNCATE",
        "partitioning_field": "",
    },
    schedule="every 24 hours",
)

transfer_config = transfer_client.create_transfer_config(
    bigquery_datatransfer.CreateTransferConfigRequest(
        parent=parent,
        transfer_config=transfer_config,
        service_account_name=service_account_name,
    )
)

print("Created scheduled query '{}'".format(transfer_config.name))

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.