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

## Explore further


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

- [Load Avro data from Cloud Storage](https://docs.cloud.google.com/bigquery/docs/loading-data-cloud-storage-avro)

## Code sample

### Go


Before trying this sample, follow the Go setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Go API
reference documentation](https://godoc.org/cloud.google.com/go/bigquery).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    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.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_GCSReference_NewGCSReference("gs://cloud-samples-data/bigquery/us-states/us-states.avro")
    	gcsRef.SourceFormat = bigquery.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_CSV_Avro_JSON_DatastoreBackup_GoogleSheets_Bigtable_Parquet_ORC_TFSavedModel_XGBoostBooster_Iceberg
    	loader := client.Dataset(datasetID).Table(tableID).https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_Table_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.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_WriteAppend_WriteTruncate_WriteTruncateData_WriteEmpty

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

    	if status.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_JobStatus_Err() != nil {
    		return fmt.Errorf("job completed with error: %w", status.https://docs.cloud.google.com/go/docs/reference/cloud.google.com/go/bigquery/latest/index.html#cloud_google_com_go_bigquery_JobStatus_Err())
    	}
    	return nil
    }

### Java


Before trying this sample, follow the Java setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Java API
reference documentation](https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/overview).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryException.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryOptions.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.JobInfo.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html;

    // 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.
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html bigquery = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryOptions.html.getDefaultInstance().getService();

          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html tableId = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html.of(datasetName, tableName);
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html loadConfig =
              https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.LoadJobConfiguration.html.newBuilder(tableId, sourceUri)
                  .setFormatOptions(https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.FormatOptions.html#com_google_cloud_bigquery_FormatOptions_avro__())
                  // Set the write disposition to overwrite existing table data
                  .setWriteDisposition(https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.JobInfo.html.WriteDisposition.WRITE_TRUNCATE)
                  .build();

          // Load data from a GCS Avro file into the table
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html job = bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html#com_google_cloud_bigquery_BigQuery_create_com_google_cloud_bigquery_DatasetInfo_com_google_cloud_bigquery_BigQuery_DatasetOption____(JobInfo.of(loadConfig));
          // Blocks until this load table job completes its execution, either failing or succeeding.
          job = job.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html#com_google_cloud_bigquery_Job_waitFor_com_google_cloud_bigquery_BigQueryRetryConfig_com_google_cloud_RetryOption____();
          if (job.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Job.html#com_google_cloud_bigquery_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 (https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryException.html | InterruptedException e) {
          System.out.println("Column not added during load append \n" + e.toString());
        }
      }
    }

### Python


Before trying this sample, follow the Python setup instructions in the
[BigQuery quickstart using
client libraries](https://docs.cloud.google.com/bigquery/docs/quickstarts/quickstart-client-libraries).


For more information, see the
[BigQuery Python API
reference documentation](https://docs.cloud.google.com/python/docs/reference/bigquery/latest).


To authenticate to BigQuery, set up Application Default Credentials.
For more information, see

[Set up authentication for client libraries](https://docs.cloud.google.com/bigquery/docs/authentication#client-libs).

    import io

    from google.cloud import https://docs.cloud.google.com/python/docs/reference/bigquery/latest

    # Construct a BigQuery client object.
    client = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html()

    # TODO(developer): Set table_id to the ID of the table to create.
    # table_id = "your-project.your_dataset.your_table_name

    job_config = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.LoadJobConfig.html(
        schema=[
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("name", "STRING"),
            https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.schema.SchemaField.html("post_abbr", "STRING"),
        ],
    )

    body = io.BytesIO(b"Washington,WA")
    client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_load_table_from_file(body, table_id, job_config=job_config).result()
    previous_rows = client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_get_table(table_id).https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html#google_cloud_bigquery_table_Table_num_rows
    assert previous_rows > 0

    job_config = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.job.LoadJobConfig.html(
        write_disposition=https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.WriteDisposition.html.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.WriteDisposition.html#google_cloud_bigquery_enums_WriteDisposition_WRITE_TRUNCATE,
        source_format=https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.enums.SourceFormat.html.AVRO,
    )

    uri = "gs://cloud-samples-data/bigquery/us-states/us-states.avro"
    load_job = client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_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.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_get_table(table_id)
    print("Loaded {} rows.".format(destination_table.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html#google_cloud_bigquery_table_Table_num_rows))

## What's next


To search and filter code samples for other Google Cloud products, see the
[Google Cloud sample browser](https://docs.cloud.google.com/docs/samples?product=bigquery).