Import a local file

Import a local file into a table.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

• Batch loading data

Code Sample

C#

Before trying this sample, follow the C# setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery C# API reference documentation.

View on GitHub Feedback

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}");
        }
    }
}

Go

Before trying this sample, follow the Go setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Go API reference documentation.

View on GitHub Feedback

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
}

Java

Before trying this sample, follow the Java setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Java API reference documentation.

View on GitHub Feedback

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.FormatOptions;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobId;
import com.google.cloud.bigquery.JobStatistics.LoadStatistics;
import com.google.cloud.bigquery.TableDataWriteChannel;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.WriteChannelConfiguration;
import java.io.IOException;
import java.io.OutputStream;
import java.nio.channels.Channels;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.UUID;

public class LoadLocalFile {

  public static void main(String[] args) throws IOException, InterruptedException {
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    Path csvPath = FileSystems.getDefault().getPath(".", "my-data.csv");
    loadLocalFile(datasetName, tableName, csvPath, FormatOptions.csv());
  }

  public static void loadLocalFile(
      String datasetName, String tableName, Path csvPath, FormatOptions formatOptions)
      throws IOException, InterruptedException {
    try {
      // Initialize client that will be used to send requests. This client only needs to be created
      // once, and can be reused for multiple requests.
      BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
      TableId tableId = TableId.of(datasetName, tableName);

      WriteChannelConfiguration writeChannelConfiguration =
          WriteChannelConfiguration.newBuilder(tableId).setFormatOptions(formatOptions).build();

      // The location and JobName must be specified; other fields can be auto-detected.
      String jobName = "jobId_" + UUID.randomUUID().toString();
      JobId jobId = JobId.newBuilder().setLocation("us").setJob(jobName).build();

      // Imports a local file into a table.
      try (TableDataWriteChannel writer = bigquery.writer(jobId, writeChannelConfiguration);
          OutputStream stream = Channels.newOutputStream(writer)) {
        Files.copy(csvPath, stream);
      }

      // Get the Job created by the TableDataWriteChannel and wait for it to complete.
      Job job = bigquery.getJob(jobId);
      Job completedJob = job.waitFor();
      if (completedJob == null) {
        System.out.println("Job not executed since it no longer exists.");
        return;
      } else if (completedJob.getStatus().getError() != null) {
        System.out.println(
            "BigQuery was unable to load local file to the table due to an error: \n"
                + job.getStatus().getError());
        return;
      }

      // Get output status
      LoadStatistics stats = job.getStatistics();
      System.out.printf("Successfully loaded %d rows. \n", stats.getOutputRows());
    } catch (BigQueryException e) {
      System.out.println("Local file not loaded. \n" + e.toString());
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Node.js API reference documentation.

View on GitHub Feedback

// 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;
  }
}

PHP

Before trying this sample, follow the PHP setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery PHP API reference documentation.

View on GitHub Feedback

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);
}

Python

Before trying this sample, follow the Python setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Python API reference documentation.

View on GitHub Feedback

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
    )
)

Ruby

Before trying this sample, follow the Ruby setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Ruby API reference documentation.

View on GitHub Feedback

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