Apache Iceberg에 쓰기

Dataflow 관리형 I/O 변환을 사용하여 Apache Iceberg에 쓰기

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

• Dataflow에서 Apache Iceberg로 쓰기

코드 샘플

Java

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

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("catalog_name", options.getCatalogName())
        .put("warehouse_location", options.getWarehouseLocation())
        .put("catalog_type", CATALOG_TYPE)
        .build();

    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("table", options.getTableName())
        .put("catalog_config", 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();
  }
}

다음 단계

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