mirror of
https://github.com/Kaelio/ktx.git
synced 2026-06-10 08:05:14 +02:00
56985b7e09
* 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
81 lines
3.2 KiB
TypeScript
81 lines
3.2 KiB
TypeScript
import { describe, expect, it } from 'vitest';
|
|
import {
|
|
normalizeKtxRelationshipName,
|
|
pluralizeKtxRelationshipToken,
|
|
singularizeKtxRelationshipToken,
|
|
tokenSimilarity,
|
|
tokenizeKtxRelationshipName,
|
|
} from '../../../src/context/scan/relationship-name-similarity.js';
|
|
|
|
describe('relationship name similarity', () => {
|
|
it('tokenizes common warehouse naming styles', () => {
|
|
expect(normalizeKtxRelationshipName('AlbumId')).toMatchObject({
|
|
normalized: 'album_id',
|
|
singular: 'album_id',
|
|
plural: 'album_ids',
|
|
tokens: ['album', 'id'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('artistID')).toMatchObject({
|
|
normalized: 'artist_id',
|
|
tokens: ['artist', 'id'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('SalesLT.CustomerID')).toMatchObject({
|
|
normalized: 'sales_lt_customer_id',
|
|
singular: 'sales_lt_customer_id',
|
|
tokens: ['sales', 'lt', 'customer', 'id'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('SCREAMING_CUSTOMER_UUID')).toMatchObject({
|
|
normalized: 'screaming_customer_uuid',
|
|
tokens: ['screaming', 'customer', 'uuid'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('billing-account-key')).toMatchObject({
|
|
normalized: 'billing_account_key',
|
|
tokens: ['billing', 'account', 'key'],
|
|
});
|
|
});
|
|
|
|
it('removes only leading warehouse layer prefixes', () => {
|
|
expect(normalizeKtxRelationshipName('mart__Sales_Accounts')).toMatchObject({
|
|
normalized: 'sales_accounts',
|
|
singular: 'sales_account',
|
|
plural: 'sales_accounts',
|
|
tokens: ['sales', 'accounts'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('dim_users')).toMatchObject({
|
|
normalized: 'users',
|
|
singular: 'user',
|
|
plural: 'users',
|
|
tokens: ['users'],
|
|
});
|
|
expect(normalizeKtxRelationshipName('customer_dim_id')).toMatchObject({
|
|
normalized: 'customer_dim_id',
|
|
tokens: ['customer', 'dim', 'id'],
|
|
});
|
|
});
|
|
|
|
it('folds accents and preserves non-suffix trailing s words', () => {
|
|
expect(normalizeKtxRelationshipName('KundénID')).toMatchObject({
|
|
normalized: 'kunden_id',
|
|
tokens: ['kunden', 'id'],
|
|
});
|
|
expect(singularizeKtxRelationshipToken('address')).toBe('address');
|
|
expect(singularizeKtxRelationshipToken('addresses')).toBe('address');
|
|
expect(singularizeKtxRelationshipToken('status')).toBe('status');
|
|
expect(pluralizeKtxRelationshipToken('address')).toBe('addresses');
|
|
expect(pluralizeKtxRelationshipToken('company')).toBe('companies');
|
|
});
|
|
|
|
it('returns deterministic tokens for direct tokenization calls', () => {
|
|
expect(tokenizeKtxRelationshipName('HTTPResponseCode')).toEqual(['http', 'response', 'code']);
|
|
expect(tokenizeKtxRelationshipName('customer2AddressID')).toEqual(['customer', '2', 'address', 'id']);
|
|
});
|
|
|
|
it('scores token overlap and ordered suffix similarity', () => {
|
|
expect(tokenSimilarity('artist_id', 'artist_id')).toBe(1);
|
|
expect(tokenSimilarity('Album.ArtistId', 'ArtistID')).toBeGreaterThanOrEqual(0.74);
|
|
expect(tokenSimilarity('customer_account_id', 'account_id')).toBeGreaterThan(
|
|
tokenSimilarity('customer_account_id', 'invoice_id'),
|
|
);
|
|
expect(tokenSimilarity('', 'artist')).toBe(0);
|
|
});
|
|
});
|