Read data

Read data from Cloud Bigtable with Apache Beam.

Explore further

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

Code sample

Java

To learn how to install and use the client library for Bigtable, see Bigtable client libraries.

To authenticate to Bigtable, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.cloud.bigtable.beam.CloudBigtableIO;
import com.google.cloud.bigtable.beam.CloudBigtableScanConfiguration;
import org.apache.beam.runners.dataflow.options.DataflowPipelineOptions;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.io.Read;
import org.apache.beam.sdk.options.Default;
import org.apache.beam.sdk.options.Description;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.filter.FirstKeyOnlyFilter;
import org.apache.hadoop.hbase.util.Bytes;

public class HelloWorldRead {
  public static void main(String[] args) {
    BigtableOptions options =
        PipelineOptionsFactory.fromArgs(args).withValidation().as(BigtableOptions.class);
    Pipeline p = Pipeline.create(options);

    Scan scan = new Scan();
    scan.setCacheBlocks(false);
    scan.setFilter(new FirstKeyOnlyFilter());

    CloudBigtableScanConfiguration config =
        new CloudBigtableScanConfiguration.Builder()
            .withProjectId(options.getBigtableProjectId())
            .withInstanceId(options.getBigtableInstanceId())
            .withTableId(options.getBigtableTableId())
            .withScan(scan)
            .build();

    p.apply(Read.from(CloudBigtableIO.read(config)))
        .apply(
            ParDo.of(
                new DoFn<Result, Void>() {
                  @ProcessElement
                  public void processElement(@Element Result row, OutputReceiver<Void> out) {
                    System.out.println(Bytes.toString(row.getRow()));
                  }
                }));

    p.run().waitUntilFinish();
  }

  public interface BigtableOptions extends DataflowPipelineOptions {
    @Description("The Bigtable project ID, this can be different than your Dataflow project")
    @Default.String("bigtable-project")
    String getBigtableProjectId();

    void setBigtableProjectId(String bigtableProjectId);

    @Description("The Bigtable instance ID")
    @Default.String("bigtable-instance")
    String getBigtableInstanceId();

    void setBigtableInstanceId(String bigtableInstanceId);

    @Description("The Bigtable table ID in the instance.")
    @Default.String("mobile-time-series")
    String getBigtableTableId();

    void setBigtableTableId(String bigtableTableId);
  }
}

What's next

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