|
| 1 | +import { describe, expect, it } from 'vitest' |
| 2 | +import { defaultClusterProbeCap } from '../src/constants.js' |
| 3 | +import { selectClusterRowRanges } from '../src/search/ranges.js' |
| 4 | + |
| 5 | +/** |
| 6 | + * Build synthetic cluster metadata with `nClusters` clusters of one row each, |
| 7 | + * so the total rows covered by the returned ranges equals the number of |
| 8 | + * clusters probed (independent of how ranges merge). |
| 9 | + * @param {number} nClusters |
| 10 | + * @returns {import('../src/types.js').HypVectorMetadata} |
| 11 | + */ |
| 12 | +function makeMeta(nClusters) { |
| 13 | + /** @type {Uint8Array[]} */ |
| 14 | + const centroids = [] |
| 15 | + for (let c = 0; c < nClusters; c += 1) { |
| 16 | + // Distinct 16-bit patterns so cluster ranking by Hamming is well-defined. |
| 17 | + centroids.push(Uint8Array.from([c & 0xff, c >> 8 & 0xff])) |
| 18 | + } |
| 19 | + const clusterCounts = new Uint32Array(nClusters).fill(1) |
| 20 | + return { |
| 21 | + version: 0, dimension: 16, metric: 'cosine', normalized: true, |
| 22 | + hasBinary: true, count: nClusters, clusters: nClusters, centroids, clusterCounts, |
| 23 | + } |
| 24 | +} |
| 25 | + |
| 26 | +/** |
| 27 | + * Sum of rows covered by a list of row ranges. |
| 28 | + * @param {{ rowStart: number, rowEnd: number }[]} ranges |
| 29 | + * @returns {number} |
| 30 | + */ |
| 31 | +function rowsCovered(ranges) { |
| 32 | + let sum = 0 |
| 33 | + for (const r of ranges) sum += r.rowEnd - r.rowStart |
| 34 | + return sum |
| 35 | +} |
| 36 | + |
| 37 | +describe('selectClusterRowRanges probe cap', () => { |
| 38 | + const query = Uint8Array.from([0, 0]) |
| 39 | + |
| 40 | + it('caps the default fraction at the absolute ceiling for large nlist', () => { |
| 41 | + // 0.25 * 500 = 125 clusters, but the default cap (96) should bind. |
| 42 | + const ranges = selectClusterRowRanges(makeMeta(500), query, undefined) |
| 43 | + expect(rowsCovered(ranges)).toBe(defaultClusterProbeCap) |
| 44 | + }) |
| 45 | + |
| 46 | + it('does not cap when the default fraction is below the ceiling', () => { |
| 47 | + // 0.25 * 100 = 25 clusters, well under the cap — unchanged behavior. |
| 48 | + const ranges = selectClusterRowRanges(makeMeta(100), query, undefined) |
| 49 | + expect(rowsCovered(ranges)).toBe(25) |
| 50 | + }) |
| 51 | + |
| 52 | + it('honors an explicit fraction literally (no cap)', () => { |
| 53 | + // Explicit 0.25 on 500 clusters → 125, NOT capped. |
| 54 | + const ranges = selectClusterRowRanges(makeMeta(500), query, 0.25) |
| 55 | + expect(rowsCovered(ranges)).toBe(125) |
| 56 | + }) |
| 57 | + |
| 58 | + it('honors an explicit absolute count above the cap', () => { |
| 59 | + const ranges = selectClusterRowRanges(makeMeta(500), query, 200) |
| 60 | + expect(rowsCovered(ranges)).toBe(200) |
| 61 | + }) |
| 62 | + |
| 63 | + it('never probes more clusters than exist', () => { |
| 64 | + const ranges = selectClusterRowRanges(makeMeta(40), query, undefined) |
| 65 | + expect(rowsCovered(ranges)).toBe(10) // ceil(0.25 * 40) |
| 66 | + }) |
| 67 | +}) |
0 commit comments