ktx/packages/cli/test/context/ingest/sqlite-local-ingest-store.test.ts

157 lines
4.4 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
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';
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 { SqliteLocalIngestStore } from '../../../src/context/ingest/sqlite-local-ingest-store.js';
import type { LocalIngestRunRecord } from '../../../src/context/ingest/local-stage-ingest.js';
2026-05-10 23:12:26 +02:00
function runRecord(overrides: Partial<LocalIngestRunRecord> = {}): LocalIngestRunRecord {
return {
runId: 'local-run-1',
jobId: 'local-run-1',
status: 'done',
adapter: 'fake',
connectionId: 'warehouse',
sourceDir: '/tmp/source',
syncId: '2026-04-27-120000-local-run-1',
startedAt: '2026-04-27T12:00:00.000Z',
completedAt: '2026-04-27T12:00:01.000Z',
progress: 1,
done: true,
previousRunId: null,
diffSummary: {
added: 1,
modified: 0,
deleted: 0,
unchanged: 0,
},
diffPaths: {
added: ['orders/orders.json'],
modified: [],
deleted: [],
unchanged: [],
},
workUnitCount: 1,
rawFileCount: 1,
workUnits: [
{
unitKey: 'fake-orders',
rawFiles: ['orders/orders.json'],
peerFileIndex: [],
dependencyPaths: [],
},
],
evictionDeletedRawPaths: [],
errors: [],
...overrides,
};
}
describe('SqliteLocalIngestStore', () => {
let tempDir: string;
let dbPath: string;
beforeEach(async () => {
2026-05-10 23:51:24 +02:00
tempDir = await mkdtemp(join(tmpdir(), 'ktx-sqlite-local-ingest-'));
dbPath = join(tempDir, '.ktx', 'db.sqlite');
2026-05-10 23:12:26 +02:00
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('persists and reads a local ingest run by id', () => {
const store = new SqliteLocalIngestStore({ dbPath });
const record = runRecord();
store.saveCompletedRun({
record,
rawContentHashes: {
'orders/orders.json': 'hash-1',
},
});
expect(store.findRunById('local-run-1')).toEqual(record);
expect(store.findRunById('missing-run')).toBeNull();
});
it('returns the latest completed report for the same connection and adapter', () => {
const store = new SqliteLocalIngestStore({ dbPath });
const first = runRecord({
runId: 'local-run-1',
jobId: 'local-run-1',
completedAt: '2026-04-27T12:00:00.000Z',
});
const second = runRecord({
runId: 'local-run-2',
jobId: 'local-run-2',
syncId: '2026-04-27-120500-local-run-2',
completedAt: '2026-04-27T12:05:00.000Z',
previousRunId: 'local-run-1',
});
const otherAdapter = runRecord({
runId: 'metabase-run-1',
jobId: 'metabase-run-1',
adapter: 'metabase',
syncId: '2026-04-27-121000-metabase-run-1',
completedAt: '2026-04-27T12:10:00.000Z',
});
store.saveCompletedRun({
record: first,
rawContentHashes: {
'orders/orders.json': 'hash-1',
},
});
store.saveCompletedRun({
record: second,
rawContentHashes: {
'orders/orders.json': 'hash-2',
'orders/payments.json': 'hash-3',
},
});
store.saveCompletedRun({
record: otherAdapter,
rawContentHashes: {
'cards/revenue.json': 'hash-4',
},
});
expect(store.findLatestCompletedReport('warehouse', 'fake')).toMatchObject({
runId: 'local-run-2',
previousRunId: 'local-run-1',
rawContentHashes: {
'orders/orders.json': 'hash-2',
'orders/payments.json': 'hash-3',
},
});
expect(store.findLatestCompletedReport('warehouse', 'fake', { excludeRunId: 'local-run-2' })).toMatchObject({
runId: 'local-run-1',
rawContentHashes: {
'orders/orders.json': 'hash-1',
},
});
expect(store.findLatestCompletedReport('warehouse', 'fake', { excludeRunId: 'local-run-1' })).toMatchObject({
runId: 'local-run-2',
rawContentHashes: {
'orders/orders.json': 'hash-2',
'orders/payments.json': 'hash-3',
},
});
expect(store.findLatestCompletedReport('warehouse', 'metabase')).toMatchObject({
runId: 'metabase-run-1',
rawContentHashes: {
'cards/revenue.json': 'hash-4',
},
});
expect(store.findLatestCompletedReport('missing', 'fake')).toBeNull();
});
it('ignores malformed run ids when reading status', () => {
const store = new SqliteLocalIngestStore({ dbPath });
expect(store.findRunById('../escape')).toBeNull();
expect(store.findRunById('')).toBeNull();
});
});