Load a Parquet to replace a table

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: %w", 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: %w", status.Err())
	}
	return nil
}

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());
    }
  }
}

use Google\Cloud\BigQuery\BigQueryClient;

/**
 * Import data from storage parquet with write truncate option.
 *
 * @param string $projectId The project Id of your Google Cloud Project.
 * @param string $datasetId The BigQuery dataset ID.
 * @param string $tableId The BigQuery table ID.
 */
function import_from_storage_parquet_truncate(
    string $projectId,
    string $datasetId,
    string $tableId
): void {
    // 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);

    // check if the job is complete
    $job->reload();
    if (!$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);
    }
}