ktx/packages/cli/test/context/ingest/clustering/kmeans.test.ts

68 lines
1.9 KiB
TypeScript
Raw Permalink Normal View History

2026-05-10 23:12:26 +02:00
import { describe, expect, test } 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 { kmeans, pickK } from '../../../../src/context/ingest/clustering/kmeans.js';
2026-05-10 23:12:26 +02:00
describe('pickK', () => {
test('uses ceil(N/8) heuristic clamped to [1, 10]', () => {
expect(pickK(0)).toBe(0);
expect(pickK(1)).toBe(1);
expect(pickK(8)).toBe(1);
expect(pickK(9)).toBe(2);
expect(pickK(24)).toBe(3);
expect(pickK(81)).toBe(10);
expect(pickK(1000)).toBe(10);
});
});
describe('kmeans', () => {
test('separates two well-spaced gaussians', () => {
const points = [
[0, 0],
[0.1, 0.1],
[-0.1, 0.05],
[10, 10],
[10.1, 9.9],
[9.95, 10.05],
];
const { assignments } = kmeans(points, 2, { seed: 42 });
expect(assignments[0]).toBe(assignments[1]);
expect(assignments[0]).toBe(assignments[2]);
expect(assignments[3]).toBe(assignments[4]);
expect(assignments[3]).toBe(assignments[5]);
expect(assignments[0]).not.toBe(assignments[3]);
});
test('is deterministic with same seed', () => {
const points = Array.from({ length: 30 }, (_, i) => [Math.sin(i), Math.cos(i)]);
const a = kmeans(points, 4, { seed: 7 }).assignments;
const b = kmeans(points, 4, { seed: 7 }).assignments;
expect(a).toEqual(b);
});
test('k=1 puts everything in one cluster', () => {
const points = [
[1, 0],
[0, 1],
[-1, 0],
[0, -1],
];
const { assignments } = kmeans(points, 1, { seed: 1 });
expect(new Set(assignments).size).toBe(1);
});
test('k>=N produces N singleton clusters', () => {
const points = [
[1, 0],
[0, 1],
[-1, 0],
];
const { assignments } = kmeans(points, 3, { seed: 1 });
expect(new Set(assignments).size).toBe(3);
});
test('handles empty input', () => {
const { assignments, centroids } = kmeans([], 3, { seed: 1 });
expect(assignments).toEqual([]);
expect(centroids).toEqual([]);
});
});