使用資料表結構定義寫入 BigQuery

提供資料表結構定義，從 Dataflow 寫入新的或現有的 BigQuery 資料表

深入探索

如需包含這個程式碼範例的詳細說明文件，請參閱下列內容：

程式碼範例

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.api.services.bigquery.model.TableFieldSchema;
import com.google.api.services.bigquery.model.TableRow;
import com.google.api.services.bigquery.model.TableSchema;
import java.util.Arrays;
import java.util.List;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.coders.DefaultCoder;
import org.apache.beam.sdk.extensions.avro.coders.AvroCoder;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.Write;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.Write.CreateDisposition;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.Create;

public class BigQueryWriteWithSchema {
  // A custom datatype for the source data.
  @DefaultCoder(AvroCoder.class)
  public static class MyData {
    public String name;
    public Long age;

    public MyData() {}

    public MyData(String name, Long age) {
      this.name = name;
      this.age = age;
    }
  }

  public static void main(String[] args) {
    // Example source data.
    final List<MyData> data = Arrays.asList(
        new MyData("Alice", 40L),
        new MyData("Bob", 30L),
        new MyData("Charlie", 20L)
    );

    // Define a table schema. A schema is required for write disposition CREATE_IF_NEEDED.
    TableSchema schema = new TableSchema()
        .setFields(
            Arrays.asList(
                new TableFieldSchema()
                    .setName("user_name")
                    .setType("STRING")
                    .setMode("REQUIRED"),
                new TableFieldSchema()
                    .setName("age")
                    .setType("INT64") // Defaults to NULLABLE
            )
        );

    // Parse the pipeline options passed into the application. Example:
    //   --projectId=$PROJECT_ID --datasetName=$DATASET_NAME --tableName=$TABLE_NAME
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptionsFactory.register(ExamplePipelineOptions.class);
    ExamplePipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation()
        .as(ExamplePipelineOptions.class);

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        // Create an in-memory PCollection of MyData objects.
        .apply(Create.of(data))
        // Write the data to a new or existing BigQuery table.
        .apply(BigQueryIO.<MyData>write()
            .to(String.format("%s:%s.%s",
                options.getProjectId(),
                options.getDatasetName(),
                options.getTableName()))
            .withFormatFunction(
                (MyData x) -> new TableRow().set("user_name", x.name).set("age", x.age))
            .withCreateDisposition(CreateDisposition.CREATE_IF_NEEDED)
            .withSchema(schema)
            .withMethod(Write.Method.STORAGE_WRITE_API)
        );
    pipeline.run().waitUntilFinish();
  }
}

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 範例瀏覽器。