Load: ORC, replace table

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

Documentation pages that include this code sample

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.


using Google.Apis.Bigquery.v2.Data;
using Google.Cloud.BigQuery.V2;
using System;

public class BigQueryLoadTableGcsOrcTruncate
{
    public void LoadTableGcsOrcTruncate(
        string projectId = "your-project-id",
        string datasetId = "your_dataset_id",
        string tableId = "your_table_id"
    )
    {
        BigQueryClient client = BigQueryClient.Create(projectId);
        var gcsURI = "gs://cloud-samples-data/bigquery/us-states/us-states.orc";
        var dataset = client.GetDataset(datasetId);
        TableReference destinationTableRef = dataset.GetTableReference(
            tableId: "us_states");
        // Create job configuration
        var jobOptions = new CreateLoadJobOptions()
        {
            SourceFormat = FileFormat.Orc,
            WriteDisposition = WriteDisposition.WriteTruncate
        };
        // Create and run job
        var loadJob = client.CreateLoadJob(
            sourceUri: gcsURI,
            destination: destinationTableRef,
            // Pass null as the schema because the schema is inferred when
            // loading Orc data
            schema: null, options: jobOptions);
        loadJob = loadJob.PollUntilCompleted().ThrowOnAnyError();  // Waits for the job to complete.
        // Display the number of rows uploaded
        BigQueryTable table = client.GetTable(destinationTableRef);
        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.

import (
	"context"
	"fmt"

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

// importORCTruncate demonstrates loading Apache ORC data from Cloud Storage into a table
// and overwriting/truncating existing data in the table.
func importORCTruncate(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.orc")
	gcsRef.SourceFormat = bigquery.ORC
	loader := client.Dataset(datasetID).Table(tableID).LoaderFrom(gcsRef)
	// Default for import jobs is to append data to a table.  WriteTruncate
	// specifies that existing data should instead be replaced/overwritten.
	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.LoadJobConfiguration;
import com.google.cloud.bigquery.TableId;

// Sample to overwrite the BigQuery table data by loading a ORC file from GCS
public class LoadOrcFromGcsTruncate {

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

  public static void loadOrcFromGcsTruncate(
      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();

      TableId tableId = TableId.of(datasetName, tableName);
      LoadJobConfiguration loadConfig =
          LoadJobConfiguration.newBuilder(tableId, sourceUri)
              .setFormatOptions(FormatOptions.orc())
              // Set the write disposition to overwrite existing table data
              .setWriteDisposition(JobInfo.WriteDisposition.WRITE_TRUNCATE)
              .build();

      // Load data from a GCS ORC file into the table
      Job job = bigquery.create(JobInfo.of(loadConfig));
      // Blocks until this load table job completes its execution, either failing or succeeding.
      job = job.waitFor();
      if (job.isDone() && job.getStatus().getError() == null) {
        System.out.println("Table is successfully overwritten by ORC file loaded from GCS");
      } else {
        System.out.println(
            "BigQuery was unable to load into the table due to an error:"
                + job.getStatus().getError());
      }
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Column not added during load append \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 the 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.orc';

async function loadORCFromGCSTruncate() {
  /**
   * 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: 'ORC',
    // 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.orc';
$loadConfig = $table->loadFromStorage($gcsUri)->sourceFormat('ORC')->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.ORC,
)

uri = "gs://cloud-samples-data/bigquery/us-states/us-states.orc"
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))