从 Dataflow 写入 Apache Iceberg

如需将数据从 Dataflow 写入 Apache Iceberg,请使用托管式 I/O 连接器

依赖项

将以下依赖项添加到项目中:

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>

配置

对于 Apache Iceberg,托管式 I/O 使用以下配置参数:

名称 数据类型 说明
table 字符串 Apache Iceberg 表的标识符。示例: "db.table1"
catalog_name 字符串 目录的名称。示例:"local"
catalog_properties 地图 Apache Iceberg 目录的配置属性映射。所需的属性取决于清单。如需了解详情,请参阅 Apache Iceberg 文档中的 CatalogUtil
config_properties 地图 一组可选的 Hadoop 配置属性。如需了解详情,请参阅 Apache Iceberg 文档中的 CatalogUtil
triggering_frequency_seconds 整数 对于流式写入流水线,表示缓冲区尝试生成快照的频率,以秒为单位。

示例

以下示例会将内存中的 JSON 数据写入 Apache Iceberg 表。

Java

如需向 Dataflow 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.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();
  }
}