Query data from a file on Cloud Storage by creating a permanent table.

## Explore further


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

- [Create Cloud Storage external tables](https://docs.cloud.google.com/bigquery/docs/external-data-cloud-storage)

## Code sample

### 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.CsvOptions.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.ExternalTableDefinition.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.QueryJobConfiguration.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableId.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableInfo.html;
    import com.google.cloud.bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableResult.html;

    // Sample to queries an external data source using a permanent table
    public class QueryExternalGcsPerm {

      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.csv";
        https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html schema =
            https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html.of(
                https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html.of("name", https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html.STRING),
                https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Field.html.of("post_abbr", https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.StandardSQLTypeName.html.STRING));
        String query =
            String.format("SELECT * FROM %s.%s WHERE name LIKE 'W%%'", datasetName, tableName);
        queryExternalGcsPerm(datasetName, tableName, sourceUri, schema, query);
      }

      public static void queryExternalGcsPerm(
          String datasetName, String tableName, String sourceUri, https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.Schema.html schema, String query) {
        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();

          // Skip header row in the file.
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.CsvOptions.html csvOptions = https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.CsvOptions.html.newBuilder().setSkipLeadingRows(1).build();

          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);
          // Create a permanent table linked to the GCS file
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.ExternalTableDefinition.html externalTable =
              https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.ExternalTableDefinition.html.newBuilder(sourceUri, csvOptions).setSchema(schema).build();
          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____(TableInfo.of(tableId, externalTable));

          // Example query to find states starting with 'W'
          https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableResult.html results = bigquery.https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQuery.html#com_google_cloud_bigquery_BigQuery_query_com_google_cloud_bigquery_QueryJobConfiguration_com_google_cloud_bigquery_BigQuery_JobOption____(https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.QueryJobConfiguration.html.of(query));

          results
              .https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.TableResult.html#com_google_cloud_bigquery_TableResult_iterateAll__()
              .forEach(row -> row.forEach(val -> System.out.printf("%s,", val.toString())));

          System.out.println("Query on external permanent table performed successfully.");
        } catch (https://docs.cloud.google.com/java/docs/reference/google-cloud-bigquery/latest/com.google.cloud.bigquery.BigQueryException.html | InterruptedException e) {
          System.out.println("Query not performed \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).

    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"

    # TODO(developer): Set the external source format of your table.
    # Note that the set of allowed values for external data sources is
    # different than the set used for loading data (see :class:`~google.cloud.bigquery.job.SourceFormat`).
    external_source_format = "AVRO"

    # TODO(developer): Set the source_uris to point to your data in Google Cloud
    source_uris = [
        "gs://cloud-samples-data/bigquery/federated-formats-reference-file-schema/a-twitter.avro",
        "gs://cloud-samples-data/bigquery/federated-formats-reference-file-schema/b-twitter.avro",
        "gs://cloud-samples-data/bigquery/federated-formats-reference-file-schema/c-twitter.avro",
    ]

    # Create ExternalConfig object with external source format
    external_config = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.external_config.ExternalConfig.html(external_source_format)
    # Set source_uris that point to your data in Google Cloud
    https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.external_config.html.source_uris = source_uris

    # TODO(developer) You have the option to set a reference_file_schema_uri, which points to
    # a reference file for the table schema
    reference_file_schema_uri = "gs://cloud-samples-data/bigquery/federated-formats-reference-file-schema/b-twitter.avro"

    https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.external_config.html.reference_file_schema_uri = reference_file_schema_uri

    table = https://docs.cloud.google.com/python/docs/reference/bigquery/latest.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html(table_id)
    # Set the external data configuration of the table
    table.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html#google_cloud_bigquery_table_Table_external_data_configuration = external_config
    table = client.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.client.Client.html#google_cloud_bigquery_client_Client_create_table(table)  # Make an API request.

    print(
        f"Created table with external source format {table.https://docs.cloud.google.com/python/docs/reference/bigquery/latest/google.cloud.bigquery.table.Table.html#google_cloud_bigquery_table_Table_external_data_configuration.source_format}"
    )

## 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).