Cloud Dataflow를 사용하여 데이터 쓰기

Apache Beam을 사용해 Cloud Bigtable에 데이터를 씁니다.

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

• Bigtable HBase Beam 커넥터

코드 샘플

Java

Bigtable용 클라이언트 라이브러리를 설치하고 사용하는 방법은 Bigtable 클라이언트 라이브러리를 참조하세요.

Bigtable에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

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;
  }
}

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저를 참조하세요.