mirror of
https://github.com/Kaelio/ktx.git
synced 2026-07-04 10:52:13 +02:00
* feat(connector): add Amazon Athena connector via Glue Data Catalog * fix(athena): address reviewer feedback * fix(athena): wire scope discovery, fix normalizeDriver, tighten types and tests * fix(athena): honor databases scope, wire sql-analysis dialect, harden config resolution - introspect() limits to the configured `databases` scope instead of scanning every Glue database in the account (docs promised this; connector ignored it) - add athena -> athena to sql-analysis SQLGLOT_DIALECTS so `ktx sql` and MCP read-only validation parse Athena SQL under the Trino grammar, not postgres - stringConfigValue coerces a resolved-empty `env:` reference to undefined so optional fields fall back to their defaults (workgroup 'primary', catalog 'AwsDataCatalog') instead of '' - drop trailing whitespace in dialect.test.ts * fix(athena): integrate with main's SQL/non-SQL dialect split and add dialect notes Rebase onto main, which introduced the KtxDialect (core) vs KtxSqlDialect (SQL-only) split for MongoDB: - KtxAthenaDialect implements KtxSqlDialect; the connector resolves it via getSqlDialectForDriver so SQL-generation methods stay in scope - add authored athena.md SQL notes for the sql_dialect_notes MCP tool, required now that athena resolves to the athena sqlglot dialect (dialect-notes coverage is derived from the warehouse-driver registry) --------- Co-authored-by: Andrey Avtomonov <andreybavt@gmail.com>
157 lines
5 KiB
TypeScript
157 lines
5 KiB
TypeScript
import { mkdtemp, rm } from 'node:fs/promises';
|
|
import { tmpdir } from 'node:os';
|
|
import { join } from 'node:path';
|
|
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
|
|
import {
|
|
driverRegistrations,
|
|
getDriverRegistration,
|
|
listSupportedDrivers,
|
|
} from '../../../src/context/connections/drivers.js';
|
|
import type {
|
|
KtxDriverConnectorModule,
|
|
KtxScopeConfigKey,
|
|
} from '../../../src/context/connections/drivers.js';
|
|
import type { KtxConnectionDriver } from '../../../src/context/scan/types.js';
|
|
|
|
type FixtureFactory = (projectDir: string) => Record<string, unknown>;
|
|
|
|
const connectionFixtures: Record<KtxConnectionDriver, FixtureFactory> = {
|
|
postgres: () => ({
|
|
driver: 'postgres',
|
|
url: 'postgresql://reader:secret@localhost:5432/analytics', // pragma: allowlist secret
|
|
schemas: ['public'],
|
|
}),
|
|
sqlite: () => ({ driver: 'sqlite', path: 'warehouse.db' }),
|
|
duckdb: (projectDir) => ({ driver: 'duckdb', path: join(projectDir, 'warehouse.duckdb') }),
|
|
mongodb: () => ({
|
|
driver: 'mongodb',
|
|
url: 'mongodb://localhost:27017/app',
|
|
databases: ['app'],
|
|
}),
|
|
mysql: () => ({
|
|
driver: 'mysql',
|
|
host: 'localhost',
|
|
database: 'analytics',
|
|
username: 'reader',
|
|
password: 'secret', // pragma: allowlist secret
|
|
schemas: ['analytics'],
|
|
}),
|
|
clickhouse: () => ({
|
|
driver: 'clickhouse',
|
|
url: 'http://localhost:8123',
|
|
database: 'analytics',
|
|
username: 'reader',
|
|
password: 'secret', // pragma: allowlist secret
|
|
}),
|
|
sqlserver: () => ({
|
|
driver: 'sqlserver',
|
|
host: 'localhost',
|
|
database: 'analytics',
|
|
username: 'reader',
|
|
password: 'secret', // pragma: allowlist secret
|
|
schemas: ['dbo'],
|
|
}),
|
|
bigquery: () => ({
|
|
driver: 'bigquery',
|
|
dataset_id: 'analytics',
|
|
credentials_json: JSON.stringify({
|
|
project_id: 'project-1',
|
|
client_email: 'reader@example.test',
|
|
private_key: '-----BEGIN PRIVATE KEY-----\nsecret\n-----END PRIVATE KEY-----\n', // pragma: allowlist secret
|
|
}),
|
|
location: 'US',
|
|
}),
|
|
snowflake: () => ({
|
|
driver: 'snowflake',
|
|
account: 'example-account',
|
|
username: 'reader',
|
|
password: 'secret', // pragma: allowlist secret
|
|
warehouse: 'COMPUTE_WH',
|
|
database: 'ANALYTICS',
|
|
schema: 'PUBLIC',
|
|
}),
|
|
athena: () => ({
|
|
driver: 'athena',
|
|
region: 'us-east-1',
|
|
s3_staging_dir: 's3://my-bucket/athena-results/',
|
|
}),
|
|
};
|
|
|
|
const allowedScopeKeys = new Set(['dataset_ids', 'databases', 'schemas', 'schema_names']);
|
|
const historicSqlReaderDrivers = new Set<KtxConnectionDriver>(['postgres', 'bigquery', 'snowflake']);
|
|
|
|
function assertExportedRegistryBoundaryTypes(input: {
|
|
scopeConfigKey: KtxScopeConfigKey;
|
|
connectorModule: KtxDriverConnectorModule;
|
|
}): {
|
|
scopeConfigKey: KtxScopeConfigKey;
|
|
connectorModule: KtxDriverConnectorModule;
|
|
} {
|
|
return input;
|
|
}
|
|
|
|
describe('driverRegistrations', () => {
|
|
let projectDir: string;
|
|
|
|
beforeEach(async () => {
|
|
projectDir = await mkdtemp(join(tmpdir(), 'ktx-driver-registry-'));
|
|
});
|
|
|
|
afterEach(async () => {
|
|
await rm(projectDir, { recursive: true, force: true });
|
|
});
|
|
|
|
it('lists every supported warehouse driver', () => {
|
|
const registryDrivers = Object.keys(driverRegistrations).sort();
|
|
expect(listSupportedDrivers()).toEqual(registryDrivers);
|
|
expect(listSupportedDrivers()).toEqual([
|
|
'athena',
|
|
'bigquery',
|
|
'clickhouse',
|
|
'duckdb',
|
|
'mongodb',
|
|
'mysql',
|
|
'postgres',
|
|
'snowflake',
|
|
'sqlite',
|
|
'sqlserver',
|
|
]);
|
|
});
|
|
|
|
it('resolves registered drivers case-insensitively', () => {
|
|
expect(getDriverRegistration(' Postgres ')?.driver).toBe('postgres');
|
|
expect(getDriverRegistration('unknown')).toBeUndefined();
|
|
});
|
|
|
|
it.each(Object.values(driverRegistrations))('adapts $driver connector exports', async (registration) => {
|
|
const connectorModule = await registration.load();
|
|
const connection = connectionFixtures[registration.driver](projectDir);
|
|
const exportedBoundary = assertExportedRegistryBoundaryTypes({
|
|
scopeConfigKey: registration.scopeConfigKey ?? 'schemas',
|
|
connectorModule,
|
|
});
|
|
expect(exportedBoundary.connectorModule.createScanConnector).toEqual(expect.any(Function));
|
|
|
|
expect(connectorModule.isConnectionConfig(connection)).toBe(true);
|
|
expect(connectorModule.isConnectionConfig({})).toBe(false);
|
|
|
|
const connector = connectorModule.createScanConnector({
|
|
connectionId: 'warehouse',
|
|
connection,
|
|
projectDir,
|
|
});
|
|
|
|
expect(connector.driver).toBe(registration.driver);
|
|
expect(connector.listSchemas).toEqual(expect.any(Function));
|
|
expect(connector.listTables).toEqual(expect.any(Function));
|
|
await connector.cleanup?.();
|
|
|
|
if (registration.driver === 'sqlite' || registration.driver === 'duckdb') {
|
|
expect(registration.scopeConfigKey).toBeNull();
|
|
} else {
|
|
expect(registration.scopeConfigKey).not.toBeNull();
|
|
expect(allowedScopeKeys.has(registration.scopeConfigKey ?? '')).toBe(true);
|
|
}
|
|
expect(registration.hasHistoricSqlReader).toBe(historicSqlReaderDrivers.has(registration.driver));
|
|
});
|
|
});
|