读取数据

使用 Apache Beam 从 Cloud Bigtable 中读取数据。

深入探索

如需查看包含此代码示例的详细文档，请参阅以下内容：

• Bigtable HBase Beam 连接器

代码示例

Java

如需了解如何安装和使用 Bigtable 的客户端库，请参阅 Bigtable 客户端库。

如需向 Bigtable 进行身份验证，请设置应用默认凭据。 如需了解详情，请参阅为本地开发环境设置身份验证。

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);
  }
}

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅Google Cloud 示例浏览器。