Schedule a backfill run

Initiate a data backfill to load historical data into BigQuery. For information about how much data is available for backfill, see the documentation for your data source.

Explore further

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

• Manage transfers
• Scheduling queries

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.DataTransferServiceClient;
import com.google.cloud.bigquery.datatransfer.v1.ScheduleTransferRunsRequest;
import com.google.cloud.bigquery.datatransfer.v1.ScheduleTransferRunsResponse;
import com.google.protobuf.Timestamp;
import java.io.IOException;
import org.threeten.bp.Clock;
import org.threeten.bp.Instant;
import org.threeten.bp.temporal.ChronoUnit;

// Sample to run schedule back fill for transfer config
public class ScheduleBackFill {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String configId = "MY_CONFIG_ID";
    Clock clock = Clock.systemDefaultZone();
    Instant instant = clock.instant();
    Timestamp startTime =
        Timestamp.newBuilder()
            .setSeconds(instant.minus(5, ChronoUnit.DAYS).getEpochSecond())
            .setNanos(instant.minus(5, ChronoUnit.DAYS).getNano())
            .build();
    Timestamp endTime =
        Timestamp.newBuilder()
            .setSeconds(instant.minus(2, ChronoUnit.DAYS).getEpochSecond())
            .setNanos(instant.minus(2, ChronoUnit.DAYS).getNano())
            .build();
    scheduleBackFill(configId, startTime, endTime);
  }

  public static void scheduleBackFill(String configId, Timestamp startTime, Timestamp endTime)
      throws IOException {
    try (DataTransferServiceClient client = DataTransferServiceClient.create()) {
      ScheduleTransferRunsRequest request =
          ScheduleTransferRunsRequest.newBuilder()
              .setParent(configId)
              .setStartTime(startTime)
              .setEndTime(endTime)
              .build();
      ScheduleTransferRunsResponse response = client.scheduleTransferRuns(request);
      System.out.println("Schedule backfill run successfully :" + response.getRunsCount());
    } catch (ApiException ex) {
      System.out.print("Schedule backfill was not run." + 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.

import datetime

from google.cloud.bigquery_datatransfer_v1 import (
    DataTransferServiceClient,
    StartManualTransferRunsRequest,
)

# Create a client object
client = DataTransferServiceClient()

# Replace with your transfer configuration name
transfer_config_name = "projects/1234/locations/us/transferConfigs/abcd"
now = datetime.datetime.now(datetime.timezone.utc)
start_time = now - datetime.timedelta(days=5)
end_time = now - datetime.timedelta(days=2)

# Some data sources, such as scheduled_query only support daily run.
# Truncate start_time and end_time to midnight time (00:00AM UTC).
start_time = datetime.datetime(
    start_time.year, start_time.month, start_time.day, tzinfo=datetime.timezone.utc
)
end_time = datetime.datetime(
    end_time.year, end_time.month, end_time.day, tzinfo=datetime.timezone.utc
)

requested_time_range = StartManualTransferRunsRequest.TimeRange(
    start_time=start_time,
    end_time=end_time,
)

# Initialize request argument(s)
request = StartManualTransferRunsRequest(
    parent=transfer_config_name,
    requested_time_range=requested_time_range,
)

# Make the request
response = client.start_manual_transfer_runs(request=request)

# Handle the response
print("Started manual transfer runs:")
for run in response.runs:
    print(f"backfill: {run.run_time} run: {run.name}")

What's next

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