Load data from Amazon S3

Schedule recurring load jobs from Amazon S3 into BigQuery.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Java

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 amazon s3 transfer config.
public class CreateAmazonS3Transfer {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    final String projectId = "MY_PROJECT_ID";
    String datasetId = "MY_DATASET_ID";
    String tableId = "MY_TABLE_ID";
    // Amazon S3 Bucket Uri with read role permission
    String sourceUri = "s3://your-bucket-name/*";
    String awsAccessKeyId = "MY_AWS_ACCESS_KEY_ID";
    String awsSecretAccessId = "AWS_SECRET_ACCESS_ID";
    String sourceFormat = "CSV";
    String fieldDelimiter = ",";
    String skipLeadingRows = "1";
    Map<String, Value> params = new HashMap<>();
    params.put(
        "destination_table_name_template", Value.newBuilder().setStringValue(tableId).build());
    params.put("data_path", Value.newBuilder().setStringValue(sourceUri).build());
    params.put("access_key_id", Value.newBuilder().setStringValue(awsAccessKeyId).build());
    params.put("secret_access_key", Value.newBuilder().setStringValue(awsSecretAccessId).build());
    params.put("source_format", Value.newBuilder().setStringValue(sourceFormat).build());
    params.put("field_delimiter", Value.newBuilder().setStringValue(fieldDelimiter).build());
    params.put("skip_leading_rows", Value.newBuilder().setStringValue(skipLeadingRows).build());
    TransferConfig transferConfig =
        TransferConfig.newBuilder()
            .setDestinationDatasetId(datasetId)
            .setDisplayName("Your Aws S3 Config Name")
            .setDataSourceId("amazon_s3")
            .setParams(Struct.newBuilder().putAllFields(params).build())
            .setSchedule("every 24 hours")
            .build();
    createAmazonS3Transfer(projectId, transferConfig);
  }

  public static void createAmazonS3Transfer(String projectId, TransferConfig transferConfig)
      throws IOException {
    try (DataTransferServiceClient client = DataTransferServiceClient.create()) {
      ProjectName parent = ProjectName.of(projectId);
      CreateTransferConfigRequest request =
          CreateTransferConfigRequest.newBuilder()
              .setParent(parent.toString())
              .setTransferConfig(transferConfig)
              .build();
      TransferConfig config = client.createTransferConfig(request);
      System.out.println("Amazon s3 transfer created successfully :" + config.getName());
    } catch (ApiException ex) {
      System.out.print("Amazon s3 transfer was not created." + ex.toString());
    }
  }
}

What's next

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