ktx/packages/cli/test/context/scan/relationship-formal-metadata.test.ts

135 lines
4 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 type { KtxEnrichedRelationship, KtxEnrichedSchema } from '../../../src/context/scan/enrichment-types.js';
import { collectKtxFormalMetadataRelationships } from '../../../src/context/scan/relationship-formal-metadata.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
function schema(relationships: KtxEnrichedRelationship[]): KtxEnrichedSchema {
2026-05-10 23:12:26 +02:00
return {
connectionId: 'warehouse',
tables: [
{
id: 'accounts',
ref: { catalog: null, db: null, name: 'accounts' },
enabled: true,
descriptions: {},
columns: [
{
id: 'accounts.id',
tableId: 'accounts',
tableRef: { catalog: null, db: null, name: 'accounts' },
name: 'id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: true,
parentColumnId: null,
descriptions: {},
embedding: null,
sampleValues: null,
cardinality: null,
},
],
},
{
id: 'orders',
ref: { catalog: null, db: null, name: 'orders' },
enabled: true,
descriptions: {},
columns: [
{
id: 'orders.account_id',
tableId: 'orders',
tableRef: { catalog: null, db: null, name: 'orders' },
name: 'account_id',
nativeType: 'INTEGER',
normalizedType: 'integer',
dimensionType: 'number',
nullable: false,
primaryKey: false,
parentColumnId: null,
descriptions: {},
embedding: null,
sampleValues: null,
cardinality: null,
},
],
},
],
relationships,
};
}
2026-05-10 23:51:24 +02:00
function formalRelationship(overrides: Partial<KtxEnrichedRelationship> = {}): KtxEnrichedRelationship {
2026-05-10 23:12:26 +02:00
return {
id: 'orders:orders.account_id->accounts:accounts.id',
source: 'formal',
from: {
tableId: 'orders',
columnIds: ['orders.account_id'],
table: { catalog: null, db: null, name: 'orders' },
columns: ['account_id'],
},
to: {
tableId: 'accounts',
columnIds: ['accounts.id'],
table: { catalog: null, db: null, name: 'accounts' },
columns: ['id'],
},
relationshipType: 'many_to_one',
confidence: 0.6,
isPrimaryKeyReference: false,
...overrides,
};
}
describe('formal metadata relationship collection', () => {
it('accepts valid formal relationships with ground-truth confidence', () => {
2026-05-10 23:51:24 +02:00
const result = collectKtxFormalMetadataRelationships(schema([formalRelationship()]));
2026-05-10 23:12:26 +02:00
expect(result.accepted).toEqual([
expect.objectContaining({
id: 'orders:orders.account_id->accounts:accounts.id',
source: 'formal',
confidence: 1,
isPrimaryKeyReference: true,
}),
]);
expect(result.skipped).toEqual([]);
expect(result.acceptedIds).toEqual(new Set(['orders:orders.account_id->accounts:accounts.id']));
});
it('skips duplicate and invalid formal relationships with reasons', () => {
2026-05-10 23:51:24 +02:00
const result = collectKtxFormalMetadataRelationships(
2026-05-10 23:12:26 +02:00
schema([
formalRelationship(),
formalRelationship(),
formalRelationship({
id: 'orders:orders.missing_account_id->accounts:accounts.id',
from: {
tableId: 'orders',
columnIds: ['orders.missing_account_id'],
table: { catalog: null, db: null, name: 'orders' },
columns: ['missing_account_id'],
},
}),
formalRelationship({
id: 'manual-edge',
source: 'manual',
}),
]),
);
expect(result.accepted).toHaveLength(1);
expect(result.skipped).toEqual([
{
relationshipId: 'orders:orders.account_id->accounts:accounts.id',
reason: 'formal_metadata_duplicate',
},
{
relationshipId: 'orders:orders.missing_account_id->accounts:accounts.id',
reason: 'formal_metadata_endpoint_not_found',
},
]);
});
});