從 Dataflow 寫入 Apache Iceberg

如要從 Dataflow 寫入 Apache Iceberg,請使用受管理 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 BigQuery Storage API 使用 BigQueryIO 連接器。資料表必須已存在,不支援動態建立資料表。

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>

設定

受管理 I/O 會使用下列 Apache Iceberg 設定參數:

讀取及寫入設定 資料類型 說明
table 字串 Apache Iceberg 資料表的 ID。示例: "db.table1"
catalog_name 字串 目錄的名稱。範例:"local"
catalog_properties 地圖 Apache Iceberg 目錄的設定屬性對應。必要屬性取決於目錄。詳情請參閱 Apache Iceberg 說明文件中的 CatalogUtil
config_properties 地圖 一組選用的 Hadoop 設定屬性。詳情請參閱 Apache Iceberg 說明文件中的 CatalogUtil
撰寫設定 資料類型 說明
triggering_frequency_seconds 整數 對於串流寫入管道,接收器嘗試產生快照的頻率 (以秒為單位)。

動態目的地

Apache Iceberg 的受管理 I/O 支援動態目的地。連接器可以根據傳入記錄中的欄位值,動態選取目的地資料表,而不是寫入單一固定資料表。

如要使用動態目的地,請為 table 設定參數提供範本。詳情請參閱動態目的地

範例

下列範例說明如何使用 Managed I/O 寫入 Apache Iceberg。

寫入 Apache Iceberg 資料表

以下範例會將記憶體內 JSON 資料寫入 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」。

import com.google.common.collect.ImmutableMap;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.managed.Managed;
import org.apache.beam.sdk.options.Description;
import org.apache.beam.sdk.options.PipelineOptions;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.schemas.Schema;
import org.apache.beam.sdk.transforms.Create;
import org.apache.beam.sdk.transforms.JsonToRow;
import org.apache.beam.sdk.values.PCollectionRowTuple;

public class ApacheIcebergWrite {
  static final List<String> TABLE_ROWS = Arrays.asList(
      "{\"id\":0, \"name\":\"Alice\"}",
      "{\"id\":1, \"name\":\"Bob\"}",
      "{\"id\":2, \"name\":\"Charles\"}"
  );

  static final String CATALOG_TYPE = "hadoop";

  // The schema for the table rows.
  public static final Schema SCHEMA = new Schema.Builder()
      .addStringField("name")
      .addInt64Field("id")
      .build();

  public interface Options extends PipelineOptions {
    @Description("The URI of the Apache Iceberg warehouse location")
    String getWarehouseLocation();

    void setWarehouseLocation(String value);

    @Description("The name of the Apache Iceberg catalog")
    String getCatalogName();

    void setCatalogName(String value);

    @Description("The name of the table to write to")
    String getTableName();

    void setTableName(String value);
  }

  public static void main(String[] args) {

    // Parse the pipeline options passed into the application. Example:
    //   --runner=DirectRunner --warehouseLocation=$LOCATION --catalogName=$CATALOG \
    //   --tableName= $TABLE_NAME
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    Pipeline pipeline = Pipeline.create(options);

    // Configure the Iceberg source I/O
    Map catalogConfig = ImmutableMap.<String, Object>builder()
        .put("warehouse", options.getWarehouseLocation())
        .put("type", CATALOG_TYPE)
        .build();

    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("table", options.getTableName())
        .put("catalog_name", options.getCatalogName())
        .put("catalog_properties", catalogConfig)
        .build();

    // Build the pipeline.
    pipeline.apply(Create.of(TABLE_ROWS))
        .apply(JsonToRow.withSchema(SCHEMA))
        .apply(Managed.write(Managed.ICEBERG).withConfig(config));

    pipeline.run().waitUntilFinish();
  }
}

使用動態目的地寫入

以下範例會根據輸入資料中的欄位,寫入不同的 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」。

import com.google.common.collect.ImmutableMap;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.PipelineResult;
import org.apache.beam.sdk.managed.Managed;
import org.apache.beam.sdk.options.Description;
import org.apache.beam.sdk.options.PipelineOptions;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.schemas.Schema;
import org.apache.beam.sdk.transforms.Create;
import org.apache.beam.sdk.transforms.JsonToRow;

public class ApacheIcebergDynamicDestinations {

  // The schema for the table rows.
  public static final Schema SCHEMA = new Schema.Builder()
      .addInt64Field("id")
      .addStringField("name")
      .addStringField("airport")
      .build();

  // The data to write to table, formatted as JSON strings.
  static final List<String> TABLE_ROWS = List.of(
      "{\"id\":0, \"name\":\"Alice\", \"airport\": \"ORD\" }",
      "{\"id\":1, \"name\":\"Bob\", \"airport\": \"SYD\" }",
      "{\"id\":2, \"name\":\"Charles\", \"airport\": \"ORD\" }"
  );

  public interface Options extends PipelineOptions {
    @Description("The URI of the Apache Iceberg warehouse location")
    String getWarehouseLocation();

    void setWarehouseLocation(String value);

    @Description("The name of the Apache Iceberg catalog")
    String getCatalogName();

    void setCatalogName(String value);
  }

  // Write JSON data to Apache Iceberg, using dynamic destinations to determine the Iceberg table
  // where Dataflow writes each record. The JSON data contains a field named "airport". The
  // Dataflow pipeline writes to Iceberg tables with the naming pattern "flights-{airport}".
  public static void main(String[] args) {
    // Parse the pipeline options passed into the application. Example:
    //   --runner=DirectRunner --warehouseLocation=$LOCATION --catalogName=$CATALOG \
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    Pipeline pipeline = Pipeline.create(options);

    // Configure the Iceberg source I/O
    Map catalogConfig = ImmutableMap.<String, Object>builder()
        .put("warehouse", options.getWarehouseLocation())
        .put("type", "hadoop")
        .build();

    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("catalog_name", options.getCatalogName())
        .put("catalog_properties", catalogConfig)
        // Route the incoming records based on the value of the "airport" field.
        .put("table", "flights-{airport}")
        // Specify which fields to keep from the input data.
        .put("keep", Arrays.asList("name", "id"))
        .build();

    // Build the pipeline.
    pipeline
        // Read in-memory JSON data.
        .apply(Create.of(TABLE_ROWS))
        // Convert the JSON records to Row objects.
        .apply(JsonToRow.withSchema(SCHEMA))
        // Write each Row to Apache Iceberg.
        .apply(Managed.write(Managed.ICEBERG).withConfig(config));

    // Run the pipeline.
    pipeline.run().waitUntilFinish();
  }
}

後續步驟