Write from Dataflow to Apache Iceberg

To write from Dataflow to Apache Iceberg, use the managed I/O connector.

Dependencies

Add the following dependencies to your project:

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>2.56.0</version>
</dependency>

Configuration

The Apache Iceberg connector uses the following configuration parameters:

• table (string). The name of the Apache Iceberg. Example: "db.table1".
• catalog_config (map). The catalog configuration. Contains the following fields:
  • catalog_name (string). The name of the catalog. Example: "local".
  • catalog_type (string). The type of catalog. Supported values: "hadoop", "hive", "rest".
  • warehouse_location (string). The warehouse location. Example: file://path/to/warehouse.

Example

The following example writes in-memory JSON data to an Apache Iceberg table.

Java

To authenticate to Dataflow, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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.
    var input = pipeline
        .apply(Create.of(TABLE_ROWS))
        .apply(JsonToRow.withSchema(SCHEMA));

    PCollectionRowTuple.of("input", input).apply(
        Managed.write(Managed.ICEBERG)
            .withConfig(config)
    );

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