Files
skillhub/apps/web/app/api/stats/route.test.ts
airano caca09fbe7 feat(curation): data quality pipeline — Phases 1-3
Add comprehensive data curation system to clean up the 197K skill
dataset and show only quality browse-ready skills to users.

Phase 1 — Database exploration:
- Explore scripts (explore.ts, explore.mjs, explore.sql) for analysis
- Discovered: 69% duplicates, 77% aggregator/fork noise

Phase 2 — Data cleanup and classification:
- Schema: 6 new curation columns + 4 indexes
- curate.mjs: 8-step pipeline (classify, dedup, fork detection, etc.)
- Result: 197K → 60K unique → 16K browse-ready skills
- Bug fix: securityStatus was computed but never stored during crawl

Phase 3 — UI browse-ready filters:
- browseReadyFilter applied to 17+ query functions
- Homepage stats show accurate browse-ready counts
- Stats API filtered (previously had no WHERE clause)
- Category counts recalculated (e.g. 45K → 3.1K)
- Featured skills exclude duplicates and aggregators

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 14:31:25 +03:30

101 lines
3.2 KiB
TypeScript

import { describe, it, expect, vi, beforeEach } from 'vitest';
import { NextRequest } from 'next/server';
// Mock rate limiting - must be before route import
vi.mock('@/lib/rate-limit', () => ({
withRateLimit: vi.fn().mockResolvedValue({ allowed: true, remaining: 100, limit: 120, resetAt: Date.now() + 60000 }),
createRateLimitResponse: vi.fn(),
createRateLimitHeaders: vi.fn().mockReturnValue({}),
}));
// Mock cache - must be before route import
vi.mock('@/lib/cache', () => ({
getCached: vi.fn().mockResolvedValue(null),
setCache: vi.fn().mockResolvedValue(undefined),
cacheKeys: { stats: () => 'stats' },
cacheTTL: { stats: 3600 },
}));
// Mock the db module - must be before imports that use it
vi.mock('@skillhub/db', () => {
const mockStatsRow = [{ totalSkills: 100, totalDownloads: 5000, totalContributors: 50 }];
const mockCategoryRow = [{ count: 8 }];
return {
createDb: vi.fn(() => ({
select: vi.fn().mockReturnValue({
from: vi.fn((table: unknown) => {
// categories table query returns count directly (no .where())
if (table === 'categories-table') {
return Promise.resolve(mockCategoryRow);
}
// skills table query has .where() chained
return {
where: vi.fn().mockResolvedValue(mockStatsRow),
};
}),
}),
})),
skills: { downloadCount: 'download_count', githubOwner: 'github_owner', isDuplicate: 'is_duplicate', skillType: 'skill_type' },
categories: 'categories-table',
sql: vi.fn((..._args: unknown[]) => 'mock-sql'),
};
});
import { GET } from './route';
// Helper to create mock request
function createMockRequest(url = 'http://localhost:3000/api/stats') {
return new NextRequest(url);
}
describe('GET /api/stats', () => {
beforeEach(() => {
vi.clearAllMocks();
});
it('should return totalSkills count', async () => {
const request = createMockRequest();
const response = await GET(request);
const data = await response.json();
expect(response.status).toBe(200);
expect(data.totalSkills).toBeDefined();
expect(typeof data.totalSkills).toBe('number');
});
it('should return totalDownloads sum', async () => {
const request = createMockRequest();
const response = await GET(request);
const data = await response.json();
expect(data.totalDownloads).toBeDefined();
expect(typeof data.totalDownloads).toBe('number');
});
it('should return totalCategories count', async () => {
const request = createMockRequest();
const response = await GET(request);
const data = await response.json();
expect(data.totalCategories).toBeDefined();
expect(typeof data.totalCategories).toBe('number');
});
it('should return totalContributors count', async () => {
const request = createMockRequest();
const response = await GET(request);
const data = await response.json();
expect(data.totalContributors).toBeDefined();
expect(typeof data.totalContributors).toBe('number');
});
it('should return platforms count', async () => {
const request = createMockRequest();
const response = await GET(request);
const data = await response.json();
expect(data.platforms).toBe(5);
});
});