透過 Lakehouse for Apache Iceberg REST 目錄從 Apache Iceberg 讀取 CDC 資料

如要使用 Lakehouse for Apache Iceberg REST 目錄，從 Apache Iceberg 讀取變更資料擷取 (CDC) 事件，請使用 Apache Beam 受管理 I/O 連接器。

代管 I/O 支援 Apache Iceberg 的下列功能：

目錄
讀取功能 批次讀取
寫入功能

如果是 Apache Iceberg 專用 BigQuery 資料表，請搭配使用 BigQueryIO 連接器和 BigQuery Storage API。資料表必須已存在，不支援動態建立資料表。

限制

  1. 只有透過 Managed API，才能使用 Apache Iceberg CDC。受管理轉換服務功能尚未啟用。預期會出現影響回溯相容性的變更
  2. CDC Managed API 只會讀取僅限附加的快照。完整 CDC 尚未推出。

必要條件

  1. 設定 Lakehouse for Apache Iceberg。按照「使用 Iceberg REST 目錄搭配 Lakehouse 執行階段目錄」一文的說明，為專案設定必要權限。 Google Cloud 請務必瞭解該頁面說明的 Apache Iceberg 專用 Lakehouse Iceberg REST 目錄限制。
  2. 建立來源 Iceberg 資料表。這個範例假設您有 Apache Iceberg 資料表。如要建立管道，請參閱「使用 Lakehouse for Apache Iceberg REST 目錄將串流寫入 Apache Iceberg」一文。

依附元件

將下列依附元件新增至專案：

Java 

<dependency>
  <groupId>org.apache.beam</groupId>
  <artifactId>beam-sdks-java-managed</artifactId>
  <version>${beam.version}</version>
</dependency>

<dependency>
  <groupId>org.apache.beam</groupId>
  <artifactId>beam-sdks-java-io-iceberg</artifactId>
  <version>${beam.version}</version>
</dependency>

<dependency>
  <groupId>org.apache.iceberg</groupId>
  <artifactId>iceberg-gcp</artifactId>
  <version>${iceberg.version}</version>
</dependency>

範例

以下範例展示串流管道，可從 Apache Iceberg 資料表讀取 CDC 事件、匯總使用者點擊次數，並將結果寫入另一個 Apache Iceberg 資料表。

Java

如要向 Dataflow 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

import com.google.auth.oauth2.GoogleCredentials;
import com.google.common.collect.ImmutableMap;
import java.io.IOException;
import java.util.Map;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.coders.RowCoder;
import org.apache.beam.sdk.extensions.gcp.options.GcpOptions;
import org.apache.beam.sdk.managed.Managed;
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.options.Validation;
import org.apache.beam.sdk.schemas.Schema;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.Sum;
import org.apache.beam.sdk.transforms.windowing.FixedWindows;
import org.apache.beam.sdk.transforms.windowing.Window;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.Row;
import org.apache.beam.sdk.values.TypeDescriptors;
import org.joda.time.Duration;

/**
 * A streaming pipeline that reads CDC events from an Iceberg table, aggregates user clicks, and
 * writes the results to another Iceberg table. For more information on BigLake, 
 * see the documentation at https://cloud.google.com/bigquery/docs/blms-rest-catalog.
 *
 * <p>This pipeline can be used to process the output of {@link
 * ApacheIcebergRestCatalogStreamingWrite}.
 */
public class ApacheIcebergCdcRead {

  // Schema for the source table containing click events.
  public static final Schema SOURCE_SCHEMA =
      Schema.builder().addStringField("user_id").addInt64Field("click_count").build();

  // Schema for the destination table containing aggregated click counts.
  public static final Schema DESTINATION_SCHEMA =
      Schema.builder().addStringField("user_id").addInt64Field("total_clicks").build();

  /** Pipeline options for this example. */
  public interface Options extends GcpOptions {
    @Description("The source Iceberg table to read CDC events from")
    @Validation.Required
    String getSourceTable();

    void setSourceTable(String sourceTable);

    @Description("The destination Iceberg table to write aggregated results to")
    @Validation.Required
    String getDestinationTable();

    void setDestinationTable(String destinationTable);

    @Description("Warehouse location for the Iceberg catalog")
    @Validation.Required
    String getWarehouse();

    void setWarehouse(String warehouse);

    @Description("The URI for the REST catalog")
    @Default.String("https://biglake.googleapis.com/iceberg/v1beta/restcatalog")
    String getCatalogUri();

    void setCatalogUri(String value);

    @Description("The name of the Iceberg catalog")
    @Validation.Required
    String getCatalogName();

    void setCatalogName(String catalogName);
  }

  public static void main(String[] args) throws IOException {
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);

    // Note: The token expires in 1 hour. Users may need to re-run the pipeline.
    // Future updates to Iceberg and the BigLake Metastore will support token refreshing.
    Map<String, String> catalogProps =
        ImmutableMap.<String, String>builder()
            .put("type", "rest")
            .put("uri", options.getCatalogUri())
            .put("warehouse", options.getWarehouse())
            .put("header.x-goog-user-project", options.getProject())
            .put(
                "header.Authorization",
                "Bearer "
                    + GoogleCredentials.getApplicationDefault()
                        .createScoped("https://www.googleapis.com/auth/cloud-platform")
                        .refreshAccessToken()
                        .getTokenValue())
            .put("rest-metrics-reporting-enabled", "false")
            .build();

    Pipeline p = Pipeline.create(options);

    // Configure the Iceberg CDC read
    Map<String, Object> icebergReadConfig =
        ImmutableMap.<String, Object>builder()
            .put("table", options.getSourceTable())
            .put("catalog_name", options.getCatalogName())
            .put("catalog_properties", catalogProps)
            .put("streaming", Boolean.TRUE)
            .put("poll_interval_seconds", 20)
            .build();

    PCollection<Row> cdcEvents =
        p.apply("ReadFromIceberg", Managed.read(Managed.ICEBERG_CDC).withConfig(icebergReadConfig))
            .getSinglePCollection()
            .setRowSchema(SOURCE_SCHEMA);

    PCollection<Row> aggregatedRows =
        cdcEvents
            .apply("ApplyWindow", Window.into(FixedWindows.of(Duration.standardSeconds(30))))
            .apply(
                "ExtractUserAndCount",
                MapElements.into(
                        TypeDescriptors.kvs(TypeDescriptors.strings(), TypeDescriptors.longs()))
                    .via(
                        row -> {
                          String userId = row.getString("user_id");
                          Long clickCount = row.getInt64("click_count");
                          return KV.of(userId, clickCount == null ? 0L : clickCount);
                        }))
            .apply("SumClicksPerUser", Sum.longsPerKey())
            .apply(
                "FormatToRow",
                MapElements.into(TypeDescriptors.rows())
                    .via(
                        kv ->
                            Row.withSchema(DESTINATION_SCHEMA)
                                .withFieldValue("user_id", kv.getKey())
                                .withFieldValue("total_clicks", kv.getValue())
                                .build()))
            .setCoder(RowCoder.of(DESTINATION_SCHEMA));

    // Configure the Iceberg write
    Map<String, Object> icebergWriteConfig =
        ImmutableMap.<String, Object>builder()
            .put("table", options.getDestinationTable())
            .put("catalog_properties", catalogProps)
            .put("catalog_name", options.getCatalogName())
            .put("triggering_frequency_seconds", 30)
            .build();

    aggregatedRows.apply(
        "WriteToIceberg", Managed.write(Managed.ICEBERG).withConfig(icebergWriteConfig));

    p.run();
  }
}

後續步驟