Load an Avro file to replace a table

Load an Avro file from Cloud Storage, replacing existing table data.

Explore further

For detailed documentation that includes this code sample, see the following:

• Loading Avro data from Cloud Storage

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.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

import (
	"context"
	"fmt"

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

// importAvroTruncate demonstrates loading Apache Avro data from Cloud Storage into a table
// and overwriting/truncating existing data in the table.
func importAvroTruncate(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.avro")
	gcsRef.SourceFormat = bigquery.Avro
	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: %w", 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.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

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 AVRO file from GCS
public class LoadAvroFromGcsTruncate {

  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.avro";
    loadAvroFromGcsTruncate(datasetName, tableName, sourceUri);
  }

  public static void loadAvroFromGcsTruncate(
      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.avro())
              // Set the write disposition to overwrite existing table data
              .setWriteDisposition(JobInfo.WriteDisposition.WRITE_TRUNCATE)
              .build();

      // Load data from a GCS Avro 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()) {
        System.out.println("Table is successfully overwritten by AVRO 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.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

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

async function loadTableGCSAvroTruncate() {
  /**
   * 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 = 'us_states';

  // Configure the load job. For full list of options, see:
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad
  const jobConfigurationLoad = {
    sourceFormat: 'AVRO',
    writeDisposition: 'WRITE_TRUNCATE',
  };

  // 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), jobConfigurationLoad);

  // load() waits for the job to finish
  console.log(`Job ${job.id} completed.`);
  console.log(
    `Write disposition used: ${job.configuration.load.writeDisposition}.`
  );
}

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.

To authenticate to BigQuery, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

import io

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 = io.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.AVRO,
)

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

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.