批量加载数据

using Google.Cloud.BigQuery.V2;
using System;
using System.IO;

public class BigQueryLoadFromFile
{
    public void LoadFromFile(
        string projectId = "your-project-id",
        string datasetId = "your_dataset_id",
        string tableId = "your_table_id",
        string filePath = "path/to/file.csv"
    )
    {
        BigQueryClient client = BigQueryClient.Create(projectId);
        // Create job configuration
        var uploadCsvOptions = new UploadCsvOptions()
        {
            SkipLeadingRows = 1,  // Skips the file headers
            Autodetect = true
        };
        using (FileStream stream = File.Open(filePath, FileMode.Open))
        {
            // Create and run job
            // Note that there are methods available for formats other than CSV
            BigQueryJob job = client.UploadCsv(
                datasetId, tableId, null, stream, uploadCsvOptions);
            job = job.PollUntilCompleted().ThrowOnAnyError();  // Waits for the job to complete.

            // Display the number of rows uploaded
            BigQueryTable table = client.GetTable(datasetId, tableId);
            Console.WriteLine(
                $"Loaded {table.Resource.NumRows} rows to {table.FullyQualifiedId}");
        }
    }
}

import (
	"context"
	"fmt"
	"os"

	"cloud.google.com/go/bigquery"
)

// importCSVFromFile demonstrates loading data into a BigQuery table using a file on the local filesystem.
func importCSVFromFile(projectID, datasetID, tableID, filename string) error {
	// projectID := "my-project-id"
	// datasetID := "mydataset"
	// tableID := "mytable"
	ctx := context.Background()
	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		return fmt.Errorf("bigquery.NewClient: %v", err)
	}
	defer client.Close()

	f, err := os.Open(filename)
	if err != nil {
		return err
	}
	source := bigquery.NewReaderSource(f)
	source.AutoDetect = true   // Allow BigQuery to determine schema.
	source.SkipLeadingRows = 1 // CSV has a single header line.

	loader := client.Dataset(datasetID).Table(tableID).LoaderFrom(source)

	job, err := loader.Run(ctx)
	if err != nil {
		return err
	}
	status, err := job.Wait(ctx)
	if err != nil {
		return err
	}
	if err := status.Err(); err != nil {
		return err
	}
	return nil
}

TableId tableId = TableId.of(datasetName, tableName);
WriteChannelConfiguration writeChannelConfiguration =
    WriteChannelConfiguration.newBuilder(tableId).setFormatOptions(FormatOptions.csv()).build();
// The location must be specified; other fields can be auto-detected.
JobId jobId = JobId.newBuilder().setLocation(location).build();
TableDataWriteChannel writer = bigquery.writer(jobId, writeChannelConfiguration);
// Write data to writer
try (OutputStream stream = Channels.newOutputStream(writer)) {
  Files.copy(csvPath, stream);
}
// Get load job
Job job = writer.getJob();
job = job.waitFor();
LoadStatistics stats = job.getStatistics();
return stats.getOutputRows();

// Imports the Google Cloud client library
const {BigQuery} = require('@google-cloud/bigquery');
const bigquery = new BigQuery();

async function loadLocalFile() {
  // Imports a local file into a table.

  /**
   * TODO(developer): Uncomment the following lines before running the sample.
   */
  // const filename = '/path/to/file.csv';
  // const datasetId = 'my_dataset';
  // const tableId = 'my_table';

  // Load data from a local file into the table
  const [job] = await bigquery
    .dataset(datasetId)
    .table(tableId)
    .load(filename);

  console.log(`Job ${job.id} completed.`);

  // Check the job's status for errors
  const errors = job.status.errors;
  if (errors && errors.length > 0) {
    throw errors;
  }
}

use Google\Cloud\BigQuery\BigQueryClient;
use Google\Cloud\Core\ExponentialBackoff;

/** Uncomment and populate these variables in your code */
// $projectId  = 'The Google project ID';
// $datasetId  = 'The BigQuery dataset ID';
// $tableId    = 'The BigQuery table ID';
// $source     = 'The path to the CSV source file to import';

// instantiate the bigquery table service
$bigQuery = new BigQueryClient([
    'projectId' => $projectId,
]);
$dataset = $bigQuery->dataset($datasetId);
$table = $dataset->table($tableId);
// create the import job
$loadConfig = $table->load(fopen($source, 'r'))->sourceFormat('CSV');

$job = $table->runJob($loadConfig);
// poll the job until it is complete
$backoff = new ExponentialBackoff(10);
$backoff->execute(function () use ($job) {
    printf('Waiting for job to complete' . PHP_EOL);
    $job->reload();
    if (!$job->isComplete()) {
        throw new Exception('Job has not yet completed', 500);
    }
});
// check if the job has errors
if (isset($job->info()['status']['errorResult'])) {
    $error = $job->info()['status']['errorResult']['message'];
    printf('Error running job: %s' . PHP_EOL, $error);
} else {
    print('Data imported successfully' . PHP_EOL);
}

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(
    source_format=bigquery.SourceFormat.CSV, skip_leading_rows=1, autodetect=True,
)

with open(file_path, "rb") as source_file:
    job = client.load_table_from_file(source_file, table_id, job_config=job_config)

job.result()  # Waits for the job to complete.

table = client.get_table(table_id)  # Make an API request.
print(
    "Loaded {} rows and {} columns to {}".format(
        table.num_rows, len(table.schema), table_id
    )
)

require "google/cloud/bigquery"

def load_from_file dataset_id = "your_dataset_id",
                   file_path  = "path/to/file.csv"
  bigquery = Google::Cloud::Bigquery.new
  dataset  = bigquery.dataset dataset_id
  table_id = "new_table_id"

  # Infer the config.location based on the location of the referenced dataset.
  load_job = dataset.load_job table_id, file_path do |config|
    config.skip_leading = 1
    config.autodetect   = true
  end
  load_job.wait_until_done! # Waits for table load to complete.

  table = dataset.table table_id
  puts "Loaded #{table.rows_count} rows into #{table.id}"
end