ktx/packages/cli/test/context/ingest/adapters/metabase/fetch-scope.test.ts

141 lines
4.7 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { 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 { computeFetchScope, type FetchScope, hashScope, isPathInMetabaseScope } from '../../../../../src/context/ingest/adapters/metabase/fetch-scope.js';
import type { StagedSyncConfig } from '../../../../../src/context/ingest/adapters/metabase/types.js';
2026-05-10 23:12:26 +02:00
const BASE_CONFIG = {
metabaseConnectionId: 'a1b2c3d4-e5f6-4789-9abc-def012345678',
metabaseDatabaseId: 42,
defaultTagNames: [] as string[],
mapping: {
metabaseDatabaseId: 42,
metabaseDatabaseName: 'Analytics',
metabaseEngine: 'postgres',
targetConnectionId: 'b2c3d4e5-f6a7-4890-abcd-ef0123456789',
},
} satisfies Omit<StagedSyncConfig, 'syncMode' | 'selections'>;
describe('computeFetchScope', () => {
it('returns { kind: "all" } for syncMode ALL', () => {
const scope = computeFetchScope({
...BASE_CONFIG,
syncMode: 'ALL',
selections: [{ selectionType: 'item', metabaseObjectId: 5 }],
});
expect(scope).toEqual({ kind: 'all' });
});
it('returns { kind: "all-except", ... } for syncMode EXCEPT', () => {
const scope = computeFetchScope({
...BASE_CONFIG,
syncMode: 'EXCEPT',
selections: [
{ selectionType: 'item', metabaseObjectId: 5 },
{ selectionType: 'collection', metabaseObjectId: 7 },
],
});
expect(scope).toEqual({
kind: 'all-except',
excludeCardIds: new Set([5]),
excludeCollectionIds: new Set([7]),
});
});
it('returns { kind: "explicit", ... } for syncMode ONLY', () => {
const scope = computeFetchScope({
...BASE_CONFIG,
syncMode: 'ONLY',
selections: [
{ selectionType: 'item', metabaseObjectId: 5 },
{ selectionType: 'item', metabaseObjectId: 11 },
{ selectionType: 'collection', metabaseObjectId: 7 },
],
});
expect(scope).toEqual({
kind: 'explicit',
includeCardIds: new Set([5, 11]),
includeCollectionIds: new Set([7]),
});
});
2026-05-10 23:13:17 -07:00
it('treats generated ONLY with no selections as all', () => {
2026-05-10 23:12:26 +02:00
const scope = computeFetchScope({ ...BASE_CONFIG, syncMode: 'ONLY', selections: [] });
2026-05-10 23:13:17 -07:00
expect(scope).toEqual({ kind: 'all' });
2026-05-10 23:12:26 +02:00
});
});
describe('hashScope', () => {
it('produces the same hash for identical inputs', () => {
const a = hashScope({
kind: 'explicit',
includeCardIds: new Set([1, 2, 3]),
includeCollectionIds: new Set([7]),
});
const b = hashScope({
kind: 'explicit',
includeCardIds: new Set([3, 2, 1]),
includeCollectionIds: new Set([7]),
});
expect(a).toBe(b);
});
it('produces different hashes for different scopes', () => {
const a = hashScope({ kind: 'all' });
const b = hashScope({
kind: 'explicit',
includeCardIds: new Set([1]),
includeCollectionIds: new Set(),
});
expect(a).not.toBe(b);
});
it('produces a 64-char hex string', () => {
const fp = hashScope({ kind: 'all' });
expect(fp).toMatch(/^[0-9a-f]{64}$/);
});
});
describe('isPathInMetabaseScope', () => {
const allScope: FetchScope = { kind: 'all' };
const exceptScope: FetchScope = {
kind: 'all-except',
excludeCardIds: new Set([100]),
excludeCollectionIds: new Set([5]),
};
const explicitScope: FetchScope = {
kind: 'explicit',
includeCardIds: new Set([1, 2]),
includeCollectionIds: new Set([7]),
};
it('always includes sync-config.json', () => {
expect(isPathInMetabaseScope('sync-config.json', allScope)).toBe(true);
expect(isPathInMetabaseScope('sync-config.json', exceptScope)).toBe(true);
expect(isPathInMetabaseScope('sync-config.json', explicitScope)).toBe(true);
});
it('always includes collections/* and databases/*', () => {
expect(isPathInMetabaseScope('collections/5.json', explicitScope)).toBe(true);
expect(isPathInMetabaseScope('databases/42.json', explicitScope)).toBe(true);
});
it('for `all` scope, every cards/<id>.json is in scope', () => {
expect(isPathInMetabaseScope('cards/1.json', allScope)).toBe(true);
expect(isPathInMetabaseScope('cards/999.json', allScope)).toBe(true);
});
it('for `all-except` scope, excluded card ids are out of scope', () => {
expect(isPathInMetabaseScope('cards/100.json', exceptScope)).toBe(false);
expect(isPathInMetabaseScope('cards/101.json', exceptScope)).toBe(true);
});
it('for `explicit` scope, only include-set card ids are in scope', () => {
expect(isPathInMetabaseScope('cards/1.json', explicitScope)).toBe(true);
expect(isPathInMetabaseScope('cards/2.json', explicitScope)).toBe(true);
expect(isPathInMetabaseScope('cards/3.json', explicitScope)).toBe(false);
});
it('unknown path shapes default to in-scope (conservative)', () => {
expect(isPathInMetabaseScope('some-new-dir/whatever.json', explicitScope)).toBe(true);
});
});