ktx/packages/cli/test/context/ingest/diff-set.service.test.ts
Andrey Avtomonov 56985b7e09
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

163 lines
5.3 KiB
TypeScript

import { beforeEach, describe, expect, it, vi } from 'vitest';
import { computeDiffSetFromHashes, DiffSetService } from '../../../src/context/ingest/diff-set.service.js';
function makeRepo(latest: Map<string, string>) {
return {
findLatestHashesForCompletedSyncs: () => Promise.resolve(latest),
};
}
describe('DiffSetService', () => {
let service: DiffSetService;
const provenanceRepo = { findLatestHashesForCompletedSyncs: vi.fn() };
beforeEach(() => {
vi.clearAllMocks();
service = new DiffSetService(provenanceRepo as any);
});
it('first run — no prior completed run — everything is added', async () => {
provenanceRepo.findLatestHashesForCompletedSyncs.mockResolvedValue(new Map());
const diff = await service.compute(
'c1',
'fake',
new Map([
['a.yml', 'h1'],
['b.yml', 'h2'],
]),
);
expect(diff.added.sort()).toEqual(['a.yml', 'b.yml']);
expect(diff.modified).toEqual([]);
expect(diff.deleted).toEqual([]);
expect(diff.unchanged).toEqual([]);
});
it('classifies added / modified / deleted / unchanged against the latest-hash baseline', async () => {
provenanceRepo.findLatestHashesForCompletedSyncs.mockResolvedValue(
new Map([
['a.yml', 'h1'],
['b.yml', 'h_old'],
['c.yml', 'hc'],
]),
);
const now = new Map([
['a.yml', 'h1'],
['b.yml', 'h_new'],
['d.yml', 'hd'],
]);
const diff = await service.compute('c1', 'fake', now);
expect(diff.unchanged).toEqual(['a.yml']);
expect(diff.modified).toEqual(['b.yml']);
expect(diff.deleted).toEqual(['c.yml']);
expect(diff.added).toEqual(['d.yml']);
});
it('computes a pure diff from current and prior hash maps', () => {
const diff = computeDiffSetFromHashes(
new Map([
['a.yml', 'h1'],
['b.yml', 'h2-new'],
['d.yml', 'h4'],
]),
new Map([
['a.yml', 'h1'],
['b.yml', 'h2-old'],
['c.yml', 'h3'],
]),
);
expect(diff).toEqual({
added: ['d.yml'],
modified: ['b.yml'],
deleted: ['c.yml'],
unchanged: ['a.yml'],
});
});
it('returns sorted arrays for deterministic hashing', async () => {
provenanceRepo.findLatestHashesForCompletedSyncs.mockResolvedValue(new Map());
const diff = await service.compute(
'c1',
'fake',
new Map([
['z.yml', 'hz'],
['a.yml', 'ha'],
]),
);
expect(diff.added).toEqual(['a.yml', 'z.yml']);
});
it('with isPathInScope predicate, out-of-scope prior entries are not reported as deleted', async () => {
const prior = new Map([
['cards/1.json', 'hashA'],
['cards/2.json', 'hashB'],
['cards/3.json', 'hashC'],
]);
const current = new Map([
['cards/1.json', 'hashA'],
['cards/2.json', 'hashB'],
]);
const inScope = new Set(['cards/1.json', 'cards/2.json']);
const svc = new DiffSetService(makeRepo(prior) as any);
const diff = await svc.compute('conn', 'metabase', current, (p) => inScope.has(p));
expect(diff.deleted).toEqual([]);
expect(diff.unchanged).toEqual(['cards/1.json', 'cards/2.json']);
});
it('with isPathInScope predicate, in-scope deletions are still reported', async () => {
const prior = new Map([
['cards/1.json', 'hashA'],
['cards/2.json', 'hashB'],
]);
const current = new Map([['cards/1.json', 'hashA']]);
const inScope = new Set(['cards/1.json', 'cards/2.json']);
const svc = new DiffSetService(makeRepo(prior) as any);
const diff = await svc.compute('conn', 'metabase', current, (p) => inScope.has(p));
expect(diff.deleted).toEqual(['cards/2.json']);
});
it('holds unchanged baseline across multiple incremental re-syncs (regression for skipped-row sync_id drift)', async () => {
// After sync 1 wrote (a.yml, h1, sync=S1, skipped) and sync 2 computed a no-op,
// sync 3 must still see a.yml as unchanged — the baseline comes from S1, not from
// the most recent sync_id alone.
provenanceRepo.findLatestHashesForCompletedSyncs.mockResolvedValue(
new Map([
['a.yml', 'h1'],
['b.yml', 'h2'],
]),
);
const diff = await service.compute(
'c1',
'fake',
new Map([
['a.yml', 'h1'],
['b.yml', 'h2'],
]),
);
expect(diff.added).toEqual([]);
expect(diff.unchanged).toEqual(['a.yml', 'b.yml']);
});
});
describe('DiffSetService — scope-narrowing scenario', () => {
it('scope from [1,2,3] → [1,2] leaves no spurious deletions', async () => {
const prior = new Map([
['cards/1.json', 'hashA'],
['cards/2.json', 'hashB'],
['cards/3.json', 'hashC'],
['sync-config.json', 'hashCfg'],
]);
const current = new Map([
['cards/1.json', 'hashA'],
['cards/2.json', 'hashB'],
['sync-config.json', 'hashCfg2'],
]);
const inScope = new Set(['cards/1.json', 'cards/2.json', 'sync-config.json']);
const svc = new DiffSetService(makeRepo(prior) as any);
const diff = await svc.compute('conn', 'metabase', current, (p) => inScope.has(p));
expect(diff.deleted).toEqual([]);
expect(diff.modified).toEqual(['sync-config.json']);
expect(diff.unchanged).toEqual(['cards/1.json', 'cards/2.json']);
expect(diff.added).toEqual([]);
});
});