Protobuf 列としてデータをエクスポートする

// package Main queries Google BigQuery.
package main

import (
	"context"
	"fmt"
	"io"
	"log"
	"os"

	"cloud.google.com/go/bigquery"
	"google.golang.org/api/iterator"
	"google.golang.org/Protobuf/proto"

	pb "path/to/proto/file_proto"
)

const (
	projectID = "your-project-id"
)

// Row contains returned row data from bigquery.
type Row struct {
	RowKey string `bigquery:"RowKey"`
	Proto  []byte `bigquery:"ProtoResult"`
}

func main() {
	ctx := context.Background()

	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		log.Fatalf("bigquery.NewClient: %v", err)
	}
	defer client.Close()

	rows, err := query(ctx, client)
	if err != nil {
		log.Fatal(err)
	}
	if err := printResults(os.Stdout, rows); err != nil {
		log.Fatal(err)
	}
}

// query returns a row iterator suitable for reading query results.
func query(ctx context.Context, client *bigquery.Client) (*bigquery.RowIterator, error) {

	query := client.Query(
		`SELECT 
  concat(word, ":", corpus) as RowKey, 
  <dataset-id>.toMyProtoMessage(
    STRUCT(
      word, 
      CAST(word_count AS BIGNUMERIC)
    )
  ) AS ProtoResult 
FROM 
  ` + "` bigquery - public - data.samples.shakespeare `" + ` 
LIMIT 
  100;
`)
	return query.Read(ctx)
}

// printResults prints results from a query.
func printResults(w io.Writer, iter *bigquery.RowIterator) error {
	for {
		var row Row
		err := iter.Next(&row)
		if err == iterator.Done {
			return nil
		}
		if err != nil {
			return fmt.Errorf("error iterating through results: %w", err)
		}
		message := &pb.TestMessage{}
		if err = proto.Unmarshal(row.Proto, message); err != nil {
			return err
		}
		fmt.Fprintf(w, "rowKey: %s, message: %v\n", row.RowKey, message)
	}
}

package proto;

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.FieldValueList;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobId;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.TableResult;
import path.to.proto.TestMessage;
import java.util.UUID;

/** Queries Google BigQuery */
public final class Main {
  public static void main(String[] args) throws Exception {
    String projectId = "your-project-id";
    BigQuery bigquery = BigQueryOptions.newBuilder().setProjectId(projectId).build().getService();

    QueryJobConfiguration queryConfig =
        QueryJobConfiguration.newBuilder(
                " SELECT "
                    + "concat(word , \":\",corpus) as RowKey,"
                    + "<dataset-id>.toMyProtoMessage(STRUCT(word, "
                    + "CAST(word_count AS BIGNUMERIC))) AS ProtoResult "
                    + "FROM "
                    + "`bigquery-public-data.samples.shakespeare` "
                    + "ORDER BY word_count DESC "
                    + "LIMIT 20")
            .setUseLegacySql(false)
            .build();

    // Create a job ID so that we can safely retry.
    JobId jobId = JobId.of(UUID.randomUUID().toString());
    Job queryJob = bigquery.create(JobInfo.newBuilder(queryConfig).setJobId(jobId).build());

    // Wait for the query to complete.
    queryJob = queryJob.waitFor();

    // Check for errors
    if (queryJob == null) {
      throw new RuntimeException("Job no longer exists");
    } else if (queryJob.getStatus().getError() != null) {
      // You can also look at queryJob.getStatus().getExecutionErrors() for all
      // errors, not just the latest one.
      throw new RuntimeException(queryJob.getStatus().getError().toString());
    }

    // Get the results.
    TableResult result = queryJob.getQueryResults();

    // Print all pages of the results.
    for (FieldValueList row : result.iterateAll()) {
      String key = row.get("RowKey").getStringValue();
      byte[] message = row.get("ProtoResult").getBytesValue();
      TestMessage testMessage = TestMessage.parseFrom(message);
      System.out.printf("rowKey: %s, message: %s\n", key, testMessage);
    }
  }
}

"""Queries Google BigQuery."""

from google.cloud import bigquery
from path.to.proto import awesome_pb2


def main():
  project_id = "your-project-id"
  client = bigquery.Client(project=project_id)
  query_job = client.query(query="""
               SELECT
			concat(word , ":",corpus) as RowKey,
			<dataset-id>.toMyProtoMessage(
			    STRUCT(
			      word, 
			      CAST(word_count AS BIGNUMERIC)
			    )
			  ) AS ProtoResult 
		FROM
				  `bigquery-public-data.samples.shakespeare`
		ORDER BY word_count DESC
		LIMIT 20
    """)
  rows = query_job.result()
  for row in rows:
    message = awesome_pb2.TestMessage()
    message.ParseFromString(row.get("ProtoResult"))
    print(
        "rowKey: {}, message: {}".format(row.get("RowKey"), message)
    )