feat(duckdb-driver): Add support for installing and loading DuckDB Community Extensions (#9169)

* feat(duckdb-driver): Add support for installing and loading DuckDB Community Extensions

* remarks on PR

---------

Co-authored-by: Konstantin Burkalev <[email protected]>

Author: benyaminsalimi

docs/pages/product/configuration/data-sources/duckdb.mdx

@@ -73,6 +73,7 @@ deployment][ref-demo-deployment] in Cube Cloud.
 | `CUBEJS_DB_DUCKDB_S3_URL_STYLE`         | To choose the S3 URL style(vhost or path)                                                                             | 'vhost' or 'path'                                             |    ❌    |                                    ❌                                     |
 | `CUBEJS_DB_DUCKDB_S3_SESSION_TOKEN`     | The token for the S3 session                                                                                          | A valid Session Token                                         |    ❌    |                                    ✅                                     |
 | `CUBEJS_DB_DUCKDB_EXTENSIONS`           | A comma-separated list of DuckDB extensions	to install and load                                                       | A comma-separated list of DuckDB extensions                   |    ❌    |                                    ✅                                     |
+| `CUBEJS_DB_DUCKDB_COMMUNITY_EXTENSIONS` | A comma-separated list of DuckDB community extensions	to install and load                                             | A comma-separated list of DuckDB community extensions         |    ❌    |                                    ✅                                     |
 | `CUBEJS_CONCURRENCY` | The number of [concurrent queries][ref-data-source-concurrency] to the data source | A valid number |    ❌    |
 
 [ref-data-source-concurrency]: /product/configuration/concurrency#data-source-concurrency
@@ -133,4 +134,4 @@ connections are made over HTTPS.
   /product/caching/using-pre-aggregations#pre-aggregation-build-strategies
 [ref-schema-ref-types-formats-countdistinctapprox]: /reference/data-model/types-and-formats#count_distinct_approx
 [self-preaggs-batching]: #batching
-[ref-demo-deployment]: /product/deployment/cloud/deployments#demo-deployments
+[ref-demo-deployment]: /product/deployment/cloud/deployments#demo-deployments

docs/pages/reference/configuration/environment-variables.mdx

@@ -372,6 +372,14 @@ A comma-separated list of DuckDB extensions	to install and load.
 | ------------------------------------------- | ---------------------- | --------------------- |
 | A comma-separated list of DuckDB extensions | N/A                    | N/A                   |
 
+## `CUBEJS_DB_DUCKDB_COMMUNITY_EXTENSIONS`
+
+A comma-separated list of DuckDB community extensions	to install and load.
+
+| Possible Values                                       | Default in Development | Default in Production |
+| ----------------------------------------------------- | ---------------------- | --------------------- |
+| A comma-separated list of DuckDB community extensions | N/A                    | N/A                   |
+
 ## `CUBEJS_DB_ELASTIC_APIKEY_ID`
 
 The [ID of the API key from elastic.co][elastic-docs-api-keys]. Required when

packages/cubejs-backend-shared/src/env.ts

@@ -1773,6 +1773,19 @@ const variables: Record<string, (...args: any) => any> = {
     }
     return [];
   },
+  duckdbCommunityExtensions: ({
+    dataSource
+  }: {
+    dataSource: string,
+  }) => {
+    const extensions = process.env[
+      keyByDataSource('CUBEJS_DB_DUCKDB_COMMUNITY_EXTENSIONS', dataSource)
+    ];
+    if (extensions) {
+      return extensions.split(',').map(e => e.trim());
+    }
+    return [];
+  },
   /** ***************************************************************
    * Presto Driver                                                  *
    **************************************************************** */

packages/cubejs-duckdb-driver/src/DuckDBDriver.ts

@@ -57,10 +57,38 @@ export class DuckDBDriver extends BaseDriver implements DriverInterface {
     return super.toGenericType(columnType.toLowerCase());
   }
 
+  private async installExtensions(extensions: string[], execAsync: (sql: string, ...params: any[]) => Promise<void>, repository: string = ''): Promise<void> {
+    repository = repository ? ` FROM ${repository}` : '';
+    for (const extension of extensions) {
+      try {
+        await execAsync(`INSTALL ${extension}${repository}`);
+      } catch (e) {
+        if (this.logger) {
+          console.error(`DuckDB - error on installing ${extension}`, { e });
+        }
+        // DuckDB will lose connection_ref on connection on error, this will lead to broken connection object
+        throw e;
+      }
+    }
+  }
+
+  private async loadExtensions(extensions: string[], execAsync: (sql: string, ...params: any[]) => Promise<void>): Promise<void> {
+    for (const extension of extensions) {
+      try {
+        await execAsync(`LOAD ${extension}`);
+      } catch (e) {
+        if (this.logger) {
+          console.error(`DuckDB - error on loading ${extension}`, { e });
+        }
+        // DuckDB will lose connection_ref on connection on error, this will lead to broken connection object
+        throw e;
+      }
+    }
+  }
+
   protected async init(): Promise<InitPromise> {
     const token = this.config.motherDuckToken || getEnv('duckdbMotherDuckToken', this.config);
     const dbPath = this.config.databasePath || getEnv('duckdbDatabasePath', this.config);
-    
     // Determine the database URL based on the provided db_path or token
     let dbUrl: string;
     if (dbPath) {
@@ -121,7 +149,7 @@ export class DuckDBDriver extends BaseDriver implements DriverInterface {
         value: getEnv('duckdbS3SessionToken', this.config),
       }
     ];
-    
+
     for (const { key, value } of configuration) {
       if (value) {
         try {
@@ -137,34 +165,13 @@ export class DuckDBDriver extends BaseDriver implements DriverInterface {
     }
 
     // Install & load extensions if configured in env variable.
-    const extensions = getEnv('duckdbExtensions', this.config);
-    for (const extension of extensions) {
-      try {
-        await execAsync(`INSTALL ${extension}`);
-      } catch (e) {
-        if (this.logger) {
-          console.error(`DuckDB - error on installing ${extension}`, {
-            e
-          });
-        }
-
-        // DuckDB will lose connection_ref on connection on error, this will lead to broken connection object
-        throw e;
-      }
-
-      try {
-        await execAsync(`LOAD ${extension}`);
-      } catch (e) {
-        if (this.logger) {
-          console.error(`DuckDB - error on loading ${extension}`, {
-            e
-          });
-        }
-
-        // DuckDB will lose connection_ref on connection on error, this will lead to broken connection object
-        throw e;
-      }
-    }
+    const officialExtensions = getEnv('duckdbExtensions', this.config);
+    await this.installExtensions(officialExtensions, execAsync);
+    await this.loadExtensions(officialExtensions, execAsync);
+    const communityExtensions = getEnv('duckdbCommunityExtensions', this.config);
+    // @see https://duckdb.org/community_extensions/
+    await this.installExtensions(communityExtensions, execAsync, 'community');
+    await this.loadExtensions(communityExtensions, execAsync);
 
     if (this.config.initSql) {
       try {
@@ -177,7 +184,7 @@ export class DuckDBDriver extends BaseDriver implements DriverInterface {
         }
       }
     }
-    
+
     return {
       defaultConnection,
       db