ktx/packages/cli/test/context/ingest/adapters/dbt/fetch.test.ts

39 lines
1.5 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { mkdir, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
import { fetchDbtRepo } from '../../../../../src/context/ingest/adapters/dbt/fetch.js';
2026-05-10 23:12:26 +02:00
describe('fetchDbtRepo', () => {
let tempDir: string;
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-dbt-fetch-'));
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('copies dbt yaml files from a fetched repo subpath into staged dir', async () => {
const cacheDir = join(tempDir, 'cache');
const stagedDir = join(tempDir, 'staged');
await mkdir(join(cacheDir, 'analytics', 'models'), { recursive: true });
await writeFile(join(cacheDir, 'analytics', 'dbt_project.yml'), 'name: analytics\n', 'utf-8');
await writeFile(join(cacheDir, 'analytics', 'models', 'orders.yml'), 'models: []\n', 'utf-8');
const cloneOrPull = vi.fn(async () => ({ commitHash: 'abc123' }));
await expect(
fetchDbtRepo({
config: { repoUrl: 'https://github.com/acme/dbt.git', path: 'analytics' },
cacheDir,
stagedDir,
deps: { cloneOrPull },
}),
).resolves.toEqual({ commitHash: 'abc123', filesCopied: 2 });
await expect(readFile(join(stagedDir, 'dbt_project.yml'), 'utf-8')).resolves.toContain('analytics');
await expect(readFile(join(stagedDir, 'models', 'orders.yml'), 'utf-8')).resolves.toContain('models');
});
});