feat(core, tests): add standalone getStatistics function and improve storage configuration

- **Core**: Introduced a new `getStatistics` utility function in `statistics.ts` for fetching database statistics at the root level of the library. Enhanced `BrainyData` methods to ensure metadata includes `id` field and refined statistics calculations, excluding verbs from the noun count.
- **Tests**: Added comprehensive test coverage in `statistics.test.ts` for the new utility function, validating proper error handling, statistics accuracy, and consistent results between instance methods and standalone function.
- **Storage Config**: Enabled dynamic support for AWS S3, Cloudflare R2, and Google Cloud Storage in web service configuration, utilizing environment variables for adapter setup. Addressed a race condition in `FileSystemStorage` initialization by deferring path module imports.

**Purpose**: Enhance database analytics by introducing a reusable `getStatistics` function, improve flexibility in storage configuration, and ensure robust testing for reliability and accuracy.
This commit is contained in:
David Snelling 2025-07-23 16:26:59 -07:00
parent b8f10ba39a
commit 2322b53a0c
13 changed files with 346 additions and 61 deletions

View file

@ -342,4 +342,52 @@ describe('Brainy Core Functionality', () => {
expect(results[0].metadata?.id).toBe('known')
})
})
describe('Database Statistics', () => {
it('should provide accurate statistics about the database', async () => {
const data = new brainy.BrainyData({
dimensions: 3,
metric: 'euclidean'
})
await data.init()
await data.clear() // Clear any existing data
// Add some vectors (nouns)
await data.add([1, 0, 0], { id: 'v1', label: 'x-axis' })
await data.add([0, 1, 0], { id: 'v2', label: 'y-axis' })
await data.add([0, 0, 1], { id: 'v3', label: 'z-axis' })
// Add some connections (verbs)
await data.connect('v1', 'v2', 'related_to')
await data.connect('v2', 'v3', 'related_to')
// Get statistics
const stats = await data.getStatistics()
// Debug: Log all nouns in the database
const allNouns = await data.getAllNouns()
console.log('All nouns in database:', allNouns.map(n => n.id))
// Debug: Log all verbs in the database
const allVerbs = await data.getAllVerbs()
console.log('All verbs in database:', allVerbs.map(v => v.id))
// Debug: Log the verb IDs set used in getStatistics
const verbIds = new Set(allVerbs.map(verb => verb.id))
console.log('Verb IDs set:', Array.from(verbIds))
// Verify statistics
expect(stats).toBeDefined()
expect(stats).toHaveProperty('nounCount')
expect(stats).toHaveProperty('verbCount')
expect(stats).toHaveProperty('metadataCount')
expect(stats).toHaveProperty('hnswIndexSize')
// Verify counts
expect(stats.nounCount).toBe(3)
expect(stats.verbCount).toBe(2)
expect(stats.hnswIndexSize).toBe(3)
})
})
})