Load: Parquet, replace

Load Parquet file from Google Cloud Storage, replacing a table.

Documentation pages that include this code sample

Code Sample

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.

import (
	"context"
	"fmt"

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

// importParquetTruncate demonstrates loading Apache Parquet data from Cloud Storage into a table
// and overwriting/truncating existing data in the table.
func importParquetTruncate(projectID, datasetID, tableID 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()

	gcsRef := bigquery.NewGCSReference("gs://cloud-samples-data/bigquery/us-states/us-states.parquet")
	gcsRef.SourceFormat = bigquery.Parquet
	gcsRef.AutoDetect = true
	loader := client.Dataset(datasetID).Table(tableID).LoaderFrom(gcsRef)
	loader.WriteDisposition = bigquery.WriteTruncate

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

	if status.Err() != nil {
		return fmt.Errorf("job completed with error: %v", status.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.


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.JobInfo;
import com.google.cloud.bigquery.JobInfo.WriteDisposition;
import com.google.cloud.bigquery.LoadJobConfiguration;
import com.google.cloud.bigquery.TableId;
import java.math.BigInteger;

public class LoadParquetReplaceTable {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String datasetName = "MY_DATASET_NAME";
    String sourceUri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet";
    String tableName = "us_states";
    loadParquetReplaceTable(datasetName, tableName, sourceUri);
  }

  public static void loadParquetReplaceTable(
      String datasetName, String tableName, String sourceUri) {
    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();

      // Imports a GCS file into a table and overwrites table data if table already exists.
      // This sample loads CSV file at:
      // https://storage.googleapis.com/cloud-samples-data/bigquery/us-states/us-states.csv
      TableId tableId = TableId.of(datasetName, tableName);

      // For more information on LoadJobConfiguration see:
      // https://googleapis.dev/java/google-cloud-clients/latest/com/google/cloud/bigquery/LoadJobConfiguration.Builder.html
      LoadJobConfiguration configuration =
          LoadJobConfiguration.builder(tableId, sourceUri)
              .setFormatOptions(FormatOptions.parquet())
              // Set the write disposition to overwrite existing table data.
              .setWriteDisposition(WriteDisposition.WRITE_TRUNCATE)
              .build();

      // For more information on Job see:
      // https://googleapis.dev/java/google-cloud-clients/latest/index.html?com/google/cloud/bigquery/package-summary.html
      // Load the table
      Job job = bigquery.create(JobInfo.of(configuration));

      // Load data from a GCS parquet file into the table
      // Blocks until this load table job completes its execution, either failing or succeeding.
      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 into the table due to an error: \n"
                + job.getStatus().getError());
        return;
      }

      // Check number of rows loaded into the table
      BigInteger numRows = bigquery.getTable(tableId).getNumRows();
      System.out.printf("Loaded %d rows. \n", numRows);

      System.out.println("GCS parquet overwrote existing table successfully.");
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Table extraction job was interrupted. \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.

// Import the Google Cloud client libraries
const {BigQuery} = require('@google-cloud/bigquery');
const {Storage} = require('@google-cloud/storage');

// Instantiate clients
const bigquery = new BigQuery();
const storage = new Storage();

/**
 * This sample loads the CSV file at
 * https://storage.googleapis.com/cloud-samples-data/bigquery/us-states/us-states.csv
 *
 * TODO(developer): Replace the following lines with the path to your file.
 */
const bucketName = 'cloud-samples-data';
const filename = 'bigquery/us-states/us-states.parquet';

async function loadParquetFromGCSTruncate() {
  /**
   * Imports a GCS file into a table and overwrites
   * table data if table already exists.
   */

  /**
   * TODO(developer): Uncomment the following lines before running the sample.
   */
  // const datasetId = "my_dataset";
  // const tableId = "my_table";

  // Configure the load job. For full list of options, see:
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad
  const metadata = {
    sourceFormat: 'PARQUET',
    // Set the write disposition to overwrite existing table data.
    writeDisposition: 'WRITE_TRUNCATE',
    location: 'US',
  };

  // Load data from a Google Cloud Storage file into the table
  const [job] = await bigquery
    .dataset(datasetId)
    .table(tableId)
    .load(storage.bucket(bucketName).file(filename), metadata);
  // load() waits for the job to finish
  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.

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';

// instantiate the bigquery table service
$bigQuery = new BigQueryClient([
    'projectId' => $projectId,
]);
$table = $bigQuery->dataset($datasetId)->table($tableId);

// create the import job
$gcsUri = 'gs://cloud-samples-data/bigquery/us-states/us-states.parquet';
$loadConfig = $table->loadFromStorage($gcsUri)->sourceFormat('PARQUET')->writeDisposition('WRITE_TRUNCATE');
$job = $table->runJob($loadConfig);

// poll the job until it is complete
$backoff = new ExponentialBackoff(10);
$backoff->execute(function () use ($job) {
    print('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.

import six

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(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
)

body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_id, job_config=job_config).result()
previous_rows = client.get_table(table_id).num_rows
assert previous_rows > 0

job_config = bigquery.LoadJobConfig(
    write_disposition=bigquery.WriteDisposition.WRITE_TRUNCATE,
    source_format=bigquery.SourceFormat.PARQUET,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

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

destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))