Scrivere dati utilizzando Cloud Dataflow

Scrivere dati in Cloud Bigtable con Apache Beam.

Per saperne di più

Per la documentazione dettagliata che include questo esempio di codice, consulta quanto segue:

Esempio di codice

Java

Per scoprire come installare e utilizzare la libreria client per Bigtable, consulta Librerie client di Bigtable.

Per eseguire l'autenticazione su Bigtable, configura le credenziali predefinite dell'applicazione. Per ulteriori informazioni, vedi Configura l'autenticazione per un ambiente di sviluppo locale.


import com.google.cloud.bigtable.beam.CloudBigtableIO;
import com.google.cloud.bigtable.beam.CloudBigtableTableConfiguration;
import com.google.cloud.bigtable.hbase.BigtableOptionsFactory;
import org.apache.beam.runners.dataflow.options.DataflowPipelineOptions;
import org.apache.beam.sdk.Pipeline;
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.Create;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.util.Bytes;

public class HelloWorldWrite {

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

    CloudBigtableTableConfiguration bigtableTableConfig =
        new CloudBigtableTableConfiguration.Builder()
            .withProjectId(options.getBigtableProjectId())
            .withInstanceId(options.getBigtableInstanceId())
            .withTableId(options.getBigtableTableId())
            .build();

    p.apply(Create.of("phone#4c410523#20190501", "phone#4c410523#20190502"))
        .apply(
            ParDo.of(
                new DoFn<String, Mutation>() {
                  @ProcessElement
                  public void processElement(@Element String rowkey, OutputReceiver<Mutation> out) {
                    long timestamp = System.currentTimeMillis();
                    Put row = new Put(Bytes.toBytes(rowkey));

                    row.addColumn(
                        Bytes.toBytes("stats_summary"),
                        Bytes.toBytes("os_build"),
                        timestamp,
                        Bytes.toBytes("android"));
                    out.output(row);
                  }
                }))
        .apply(CloudBigtableIO.writeToTable(bigtableTableConfig));

    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);
  }

  public static CloudBigtableTableConfiguration batchWriteFlowControlExample(
      BigtableOptions options) {
    CloudBigtableTableConfiguration bigtableTableConfig =
        new CloudBigtableTableConfiguration.Builder()
            .withProjectId(options.getBigtableProjectId())
            .withInstanceId(options.getBigtableInstanceId())
            .withTableId(options.getBigtableTableId())
            .withConfiguration(BigtableOptionsFactory.BIGTABLE_ENABLE_BULK_MUTATION_FLOW_CONTROL,
                "true")
            .build();
    return bigtableTableConfig;
  }
}

Passaggi successivi

Per cercare e filtrare esempi di codice per altri prodotti Google Cloud, consulta Browser di esempio Google Cloud.