ktx/packages/cli/test/context/scan/local-structural-artifacts.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

278 lines
8.4 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 { initKtxProject, type KtxLocalProject } from '../../../src/context/project/project.js';
import { readLocalScanStructuralSnapshot } from '../../../src/context/scan/local-structural-artifacts.js';
describe('readLocalScanStructuralSnapshot', () => {
let tempDir: string;
let project: KtxLocalProject;
beforeEach(async () => {
tempDir = await mkdtemp(join(tmpdir(), 'ktx-local-structural-artifacts-'));
project = await initKtxProject({
projectDir: join(tempDir, 'project'),
});
});
afterEach(async () => {
await rm(tempDir, { recursive: true, force: true });
});
it('rebuilds a canonical snapshot from persisted live-database raw files', async () => {
const rawRoot = 'raw-sources/warehouse/live-database/sync-1';
await project.fileStore.writeFile(
`${rawRoot}/connection.json`,
`${JSON.stringify(
{
connectionId: 'warehouse',
extractedAt: '2026-04-29T12:00:00.000Z',
metadata: { source: 'sqlite-smoke' },
tableCount: 2,
},
null,
2,
)}\n`,
'ktx',
'ktx@example.com',
'Seed connection artifact',
);
await project.fileStore.writeFile(
`${rawRoot}/tables/customers.json`,
`${JSON.stringify(
{
name: 'customers',
catalog: null,
db: 'public',
kind: 'table',
comment: 'Customer table',
estimatedRows: 12,
columns: [
{
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'Customer id',
},
],
foreignKeys: [],
},
null,
2,
)}\n`,
'ktx',
'ktx@example.com',
'Seed customers artifact',
);
await project.fileStore.writeFile(
`${rawRoot}/tables/orders.json`,
`${JSON.stringify(
{
name: 'orders',
catalog: null,
db: 'public',
kind: 'table',
comment: null,
estimatedRows: 20,
columns: [
{
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: null,
},
{
name: 'customer_id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: false,
comment: null,
},
],
foreignKeys: [
{
fromColumn: 'customer_id',
toCatalog: null,
toDb: 'public',
toTable: 'customers',
toColumn: 'id',
constraintName: null,
},
],
},
null,
2,
)}\n`,
'ktx',
'ktx@example.com',
'Seed orders artifact',
);
const snapshot = await readLocalScanStructuralSnapshot({
project,
connectionId: 'warehouse',
driver: 'sqlite',
rawSourcesDir: rawRoot,
extractedAtFallback: '2026-04-29T13:00:00.000Z',
});
expect(snapshot).toMatchObject({
connectionId: 'warehouse',
driver: 'sqlite',
extractedAt: '2026-04-29T12:00:00.000Z',
metadata: { source: 'sqlite-smoke' },
tables: [
{
db: 'public',
name: 'customers',
comment: 'Customer table',
columns: [
{
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: true,
comment: 'Customer id',
},
],
},
{
db: 'public',
name: 'orders',
foreignKeys: [
{
fromColumn: 'customer_id',
toCatalog: null,
toDb: 'public',
toTable: 'customers',
toColumn: 'id',
constraintName: null,
},
],
},
],
});
});
it('rebuilds scan warnings from persisted live-database warning files', async () => {
const rawRoot = 'raw-sources/warehouse/live-database/sync-warnings';
await project.fileStore.writeFile(
`${rawRoot}/connection.json`,
'{"connectionId":"warehouse","metadata":{}}\n',
'ktx',
'ktx@example.com',
'Seed connection artifact',
);
await project.fileStore.writeFile(
`${rawRoot}/warnings.json`,
`${JSON.stringify(
{
warnings: [
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped foreign-key discovery in public (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'public', kind: 'foreign_key' },
},
],
},
null,
2,
)}\n`,
'ktx',
'ktx@example.com',
'Seed warning artifact',
);
await project.fileStore.writeFile(
`${rawRoot}/tables/orders.json`,
'{"name":"orders","catalog":null,"db":"public","kind":"table","comment":null,"estimatedRows":null,"columns":[{"name":"id","nativeType":"integer","normalizedType":"integer","dimensionType":"number","nullable":false,"primaryKey":false,"comment":null}],"foreignKeys":[]}\n',
'ktx',
'ktx@example.com',
'Seed orders artifact',
);
const snapshot = await readLocalScanStructuralSnapshot({
project,
connectionId: 'warehouse',
driver: 'postgres',
rawSourcesDir: rawRoot,
extractedAtFallback: '2026-04-29T13:00:00.000Z',
});
expect(snapshot.warnings).toEqual([
{
code: 'constraint_discovery_unauthorized',
message: 'Skipped foreign-key discovery in public (insufficient grants on system catalogs)',
recoverable: true,
metadata: { schema: 'public', kind: 'foreign_key' },
},
]);
});
it('uses the scan report timestamp when connection.json omits extractedAt', async () => {
const rawRoot = 'raw-sources/warehouse/live-database/sync-2';
await project.fileStore.writeFile(
`${rawRoot}/connection.json`,
'{"connectionId":"warehouse","metadata":{}}\n',
'ktx',
'ktx@example.com',
'Seed connection artifact without extractedAt',
);
await project.fileStore.writeFile(
`${rawRoot}/tables/orders.json`,
'{"name":"orders","catalog":null,"db":null,"kind":"table","comment":null,"estimatedRows":null,"columns":[{"name":"id","nativeType":"integer","normalizedType":"integer","dimensionType":"number","nullable":false,"primaryKey":true,"comment":null}],"foreignKeys":[]}\n',
'ktx',
'ktx@example.com',
'Seed orders artifact',
);
const snapshot = await readLocalScanStructuralSnapshot({
project,
connectionId: 'warehouse',
driver: 'postgres',
rawSourcesDir: rawRoot,
extractedAtFallback: '2026-04-29T13:00:00.000Z',
});
expect(snapshot.extractedAt).toBe('2026-04-29T13:00:00.000Z');
});
it('tolerates older live-database staged directories without warnings.json', async () => {
const rawRoot = 'raw-sources/warehouse/live-database/sync-no-warnings';
await project.fileStore.writeFile(
`${rawRoot}/connection.json`,
'{"connectionId":"warehouse","metadata":{}}\n',
'ktx',
'ktx@example.com',
'Seed connection artifact',
);
await project.fileStore.writeFile(
`${rawRoot}/tables/orders.json`,
'{"name":"orders","catalog":null,"db":null,"kind":"table","comment":null,"estimatedRows":null,"columns":[{"name":"id","nativeType":"integer","normalizedType":"integer","dimensionType":"number","nullable":false,"primaryKey":true,"comment":null}],"foreignKeys":[]}\n',
'ktx',
'ktx@example.com',
'Seed orders artifact',
);
const snapshot = await readLocalScanStructuralSnapshot({
project,
connectionId: 'warehouse',
driver: 'postgres',
rawSourcesDir: rawRoot,
extractedAtFallback: '2026-04-29T13:00:00.000Z',
});
expect(snapshot.warnings).toEqual([]);
});
});