Interroger Cloud Storage avec une table permanente

Interrogez les données d'un fichier sur Cloud Storage en créant une table permanente.

En savoir plus

Pour obtenir une documentation détaillée incluant cet exemple de code, consultez les articles suivants :

Créer des tables externes Cloud Storage

Exemple de code

Java

Avant d'essayer cet exemple, suivez les instructions de configuration pour Java du guide de démarrage rapide de BigQuery : Utiliser les bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Java.

Pour vous authentifier auprès de BigQuery, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez la page Configurer l'authentification pour les bibliothèques clientes.

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.CsvOptions;
import com.google.cloud.bigquery.ExternalTableDefinition;
import com.google.cloud.bigquery.Field;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.Schema;
import com.google.cloud.bigquery.StandardSQLTypeName;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TableInfo;
import com.google.cloud.bigquery.TableResult;

// 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";
    Schema schema =
        Schema.of(
            Field.of("name", StandardSQLTypeName.STRING),
            Field.of("post_abbr", StandardSQLTypeName.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, Schema 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.
      BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();

      // Skip header row in the file.
      CsvOptions csvOptions = CsvOptions.newBuilder().setSkipLeadingRows(1).build();

      TableId tableId = TableId.of(datasetName, tableName);
      // Create a permanent table linked to the GCS file
      ExternalTableDefinition externalTable =
          ExternalTableDefinition.newBuilder(sourceUri, csvOptions).setSchema(schema).build();
      bigquery.create(TableInfo.of(tableId, externalTable));

      // Example query to find states starting with 'W'
      TableResult results = bigquery.query(QueryJobConfiguration.of(query));

      results
          .iterateAll()
          .forEach(row -> row.forEach(val -> System.out.printf("%s,", val.toString())));

      System.out.println("Query on external permanent table performed successfully.");
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Query not performed \n" + e.toString());
    }
  }
}

Node.js

Avant d'essayer cet exemple, suivez les instructions de configuration pour Node.js du guide de démarrage rapide de BigQuery : Utiliser les bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Node.js.

// Import the Google Cloud client library and create a client
const {BigQuery} = require('@google-cloud/bigquery');
const bigquery = new BigQuery();

async function queryExternalGCSPerm() {
  // Queries an external data source using a permanent table

  /**
   * TODO(developer): Uncomment the following lines before running the sample.
   */
  // const datasetId = "my_dataset";
  // const tableId = "my_table";

  // Configure the external data source
  const dataConfig = {
    sourceFormat: 'CSV',
    sourceUris: ['gs://cloud-samples-data/bigquery/us-states/us-states.csv'],
    // Optionally skip header row
    csvOptions: {skipLeadingRows: 1},
  };

  // For all options, see https://cloud.google.com/bigquery/docs/reference/v2/tables#resource
  const options = {
    schema: schema,
    externalDataConfiguration: dataConfig,
  };

  // Create an external table linked to the GCS file
  const [table] = await bigquery
    .dataset(datasetId)
    .createTable(tableId, options);

  console.log(`Table ${table.id} created.`);

  // Example query to find states starting with 'W'
  const query = `SELECT post_abbr
  FROM \`${datasetId}.${tableId}\`
  WHERE name LIKE 'W%'`;

  // Run the query as a job
  const [job] = await bigquery.createQueryJob(query);
  console.log(`Job ${job.id} started.`);

  // Wait for the query to finish
  const [rows] = await job.getQueryResults();

  // Print the results
  console.log('Rows:');
  console.log(rows);
}

Python

Avant d'essayer cet exemple, suivez les instructions de configuration pour Python du guide de démarrage rapide de BigQuery : Utiliser les bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Python.

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"

# 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 = bigquery.ExternalConfig(external_source_format)
# Set source_uris that point to your data in Google Cloud
external_config.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"

external_config.reference_file_schema_uri = reference_file_schema_uri

table = bigquery.Table(table_id)
# Set the external data configuration of the table
table.external_data_configuration = external_config
table = client.create_table(table)  # Make an API request.

print(
    f"Created table with external source format {table.external_data_configuration.source_format}"
)

Étapes suivantes

Pour rechercher et filtrer des exemples de code pour d'autres produits Google Cloud, consultez l'explorateur d'exemples Google Cloud.