|
| 1 | +// Copyright (c) 2026 ObjectStack. Licensed under the Apache-2.0 license. |
| 2 | + |
| 3 | +/** |
| 4 | + * #16179 — `dateRange: 'today'` counted the first instant of TOMORROW. |
| 5 | + * |
| 6 | + * ## The defect, in one sentence |
| 7 | + * |
| 8 | + * `parseDateRangeString('today')` returns the day's start instant and the NEXT |
| 9 | + * day's start instant; the call site compared that upper bound with `$lte` |
| 10 | + * (`nextUtcCalendarDay` widens only a bare `YYYY-MM-DD` and returns `null` for |
| 11 | + * an instant, so the half-open branch was never taken). `'today'` was therefore |
| 12 | + * one day PLUS ONE INSTANT long, two adjacent day windows overlapped at |
| 13 | + * midnight, and a row stamped exactly there was counted in BOTH — silently, no |
| 14 | + * error, no warning. |
| 15 | + * |
| 16 | + * ## ⭐ The control is the point of this file |
| 17 | + * |
| 18 | + * The card offered two routes and the second was taken: fix what the RELATIVE |
| 19 | + * TOKENS emit, and ⛔ leave an explicit `dateRange: [a, b]` alone — `$lte` on a |
| 20 | + * caller-written timestamp end is a PUBLISHED reading (`@objectstack/driver-memory` |
| 21 | + * is a released package) and narrowing it is a decision nobody made. So every |
| 22 | + * case below asks the SAME rows through BOTH arms of `AnalyticsDateRangeSchema` |
| 23 | + * and asserts the difference between the two answers is EXACTLY the boundary |
| 24 | + * instant — the token dropped it, the explicit array still keeps it. A repair |
| 25 | + * that drifted into route 1 goes red here, on the explicit-array leg, not on |
| 26 | + * the token leg. |
| 27 | + * |
| 28 | + * ## Why the assertions are about ROWS, and why both storage forms |
| 29 | + * |
| 30 | + * The window is internal; what a caller sees is which rows the answer counted, |
| 31 | + * so every case drives the real public entry `MemoryAnalyticsService.query()` |
| 32 | + * through `AnalyticsQuerySchema.parse`. And the call site builds TWO bounds |
| 33 | + * joined by `$or` — one for `Date`-valued rows, one for ISO-string rows, the |
| 34 | + * two forms an in-memory table really holds — so each case runs on both. A |
| 35 | + * repair applied to one leg only passes half of this file. |
| 36 | + * |
| 37 | + * ## What this file deliberately does NOT pin |
| 38 | + * |
| 39 | + * - The `last N …` leg and the unresolved-preset fallback. The declared |
| 40 | + * vocabulary spells its presets `last_7_days` while the parser matches |
| 41 | + * `startsWith('last ')`, so every preset but `'today'` currently takes the |
| 42 | + * `[range, range]` fallback — that mismatch is #16322 and the fallback's |
| 43 | + * match-everything behaviour is #16041. ⛔ Neither is pinned here; pinning |
| 44 | + * either would freeze a defect as a contract. |
| 45 | + * - Which calendar the window is anchored to (#16042) and where a day BEGINS |
| 46 | + * (#15825). Both are pinned by their own files. This file's cells carry a |
| 47 | + * non-UTC zone only to prove the repair also holds where the upper bound is a |
| 48 | + * ZONE's midnight instant rather than UTC's. |
| 49 | + */ |
| 50 | + |
| 51 | +import { describe, it, expect, vi } from 'vitest'; |
| 52 | +import { InMemoryDriver } from './memory-driver.js'; |
| 53 | +import { MemoryAnalyticsService } from './memory-analytics.js'; |
| 54 | +import { AnalyticsQuerySchema } from '@objectstack/spec/data'; |
| 55 | +import type { AnalyticsDateRange, AnalyticsQuery, Cube } from '@objectstack/spec/data'; |
| 56 | + |
| 57 | +const REAL_TZ = process.env.TZ; |
| 58 | + |
| 59 | +/** Run `fn` with the PROCESS on `zone` and the clock frozen at `instant`. */ |
| 60 | +async function at<T>(zone: string, instant: string, fn: () => Promise<T>): Promise<T> { |
| 61 | + process.env.TZ = zone; |
| 62 | + vi.useFakeTimers({ toFake: ['Date'] }); |
| 63 | + vi.setSystemTime(new Date(instant)); |
| 64 | + try { |
| 65 | + return await fn(); |
| 66 | + } finally { |
| 67 | + vi.useRealTimers(); |
| 68 | + if (REAL_TZ === undefined) delete process.env.TZ; |
| 69 | + else process.env.TZ = REAL_TZ; |
| 70 | + } |
| 71 | +} |
| 72 | + |
| 73 | +const CUBE: Cube = { |
| 74 | + name: 'events', |
| 75 | + title: 'Events', |
| 76 | + sql: 'events', |
| 77 | + measures: { |
| 78 | + count: { name: 'count', label: 'Count', type: 'count', sql: 'id' }, |
| 79 | + }, |
| 80 | + dimensions: { |
| 81 | + probe: { name: 'probe', label: 'Probe', type: 'string', sql: 'probe' }, |
| 82 | + createdAt: { |
| 83 | + name: 'created_at', |
| 84 | + label: 'Created At', |
| 85 | + type: 'time', |
| 86 | + sql: 'created_at', |
| 87 | + granularities: ['day'], |
| 88 | + }, |
| 89 | + }, |
| 90 | + public: true, |
| 91 | +}; |
| 92 | + |
| 93 | +const asQuery = (input: AnalyticsQuery): AnalyticsQuery => AnalyticsQuerySchema.parse(input); |
| 94 | + |
| 95 | +/** |
| 96 | + * The two shapes an in-memory table really holds for a datetime — the `Date` |
| 97 | + * a direct JS caller writes and the ISO string the driver's own `created_at` |
| 98 | + * default and every REST/JSON write produce. The call site builds one bound |
| 99 | + * for each and `$or`s them, so every case runs on both. |
| 100 | + */ |
| 101 | +const STORAGE = ['Date', 'ISO string'] as const; |
| 102 | +type Storage = (typeof STORAGE)[number]; |
| 103 | + |
| 104 | +/** Ask `range` over rows planted at `instants`; answer which probes came back. */ |
| 105 | +async function probesSelected( |
| 106 | + instants: string[], |
| 107 | + opts: { range: AnalyticsDateRange; timezone?: string; storage: Storage }, |
| 108 | +): Promise<string[]> { |
| 109 | + const driver = new InMemoryDriver({ |
| 110 | + initialData: { |
| 111 | + events: instants.map((iso, i) => ({ |
| 112 | + id: i + 1, |
| 113 | + probe: iso, |
| 114 | + created_at: opts.storage === 'Date' ? new Date(iso) : iso, |
| 115 | + })), |
| 116 | + }, |
| 117 | + }); |
| 118 | + await driver.connect(); |
| 119 | + const service = new MemoryAnalyticsService({ driver, cubes: [CUBE] }); |
| 120 | + const query: AnalyticsQuery = { |
| 121 | + cube: 'events', |
| 122 | + measures: ['events.count'], |
| 123 | + dimensions: ['events.probe'], |
| 124 | + timeDimensions: [{ dimension: 'events.createdAt', dateRange: opts.range }], |
| 125 | + }; |
| 126 | + if (opts.timezone !== undefined) query.timezone = opts.timezone; |
| 127 | + const result = await service.query(asQuery(query)); |
| 128 | + return result.rows.map((row) => String(row['events.probe'])).sort(); |
| 129 | +} |
| 130 | + |
| 131 | +const ms = (iso: string) => Date.parse(iso); |
| 132 | +const iso = (t: number) => new Date(t).toISOString(); |
| 133 | + |
| 134 | +/** |
| 135 | + * What `zone`'s local clock reads at `instant`, from the platform tz database |
| 136 | + * ALONE — ⛔ never from the primitives the repair uses. This is what makes the |
| 137 | + * window literals below data rather than a second implementation: each one is |
| 138 | + * asserted to be a local midnight by this function. |
| 139 | + */ |
| 140 | +function localClock(instant: string, zone: string): string { |
| 141 | + return new Intl.DateTimeFormat('en-CA', { |
| 142 | + timeZone: zone, |
| 143 | + hourCycle: 'h23', |
| 144 | + year: 'numeric', month: '2-digit', day: '2-digit', |
| 145 | + hour: '2-digit', minute: '2-digit', second: '2-digit', |
| 146 | + fractionalSecondDigits: 3, |
| 147 | + }).format(new Date(instant)); |
| 148 | +} |
| 149 | + |
| 150 | +interface Cell { |
| 151 | + zone: string; |
| 152 | + /** Frozen clock, always written in UTC. */ |
| 153 | + instant: string; |
| 154 | + /** `'today'` on `zone`'s calendar — the half-open `[start, end)` it MUST be. */ |
| 155 | + window: [string, string]; |
| 156 | +} |
| 157 | + |
| 158 | +/** |
| 159 | + * UTC (where the bound is UTC midnight), a zone AHEAD of UTC whose day boundary |
| 160 | + * is a plain non-UTC instant, one BEHIND, and one whose offset is not a whole |
| 161 | + * number of hours — so a repair that quietly re-derived the bound as a UTC day |
| 162 | + * cannot pass. Every `window` literal is checked against `Intl` below. |
| 163 | + */ |
| 164 | +const CELLS: Cell[] = [ |
| 165 | + { zone: 'UTC', instant: '2026-09-06T12:00:00Z', window: ['2026-09-06T00:00:00.000Z', '2026-09-07T00:00:00.000Z'] }, |
| 166 | + { zone: 'Asia/Shanghai', instant: '2026-09-06T20:00:00Z', window: ['2026-09-06T16:00:00.000Z', '2026-09-07T16:00:00.000Z'] }, |
| 167 | + { zone: 'America/Denver', instant: '2026-09-06T12:00:00Z', window: ['2026-09-06T06:00:00.000Z', '2026-09-07T06:00:00.000Z'] }, |
| 168 | + { zone: 'Asia/Kolkata', instant: '2026-09-06T12:00:00Z', window: ['2026-09-05T18:30:00.000Z', '2026-09-06T18:30:00.000Z'] }, |
| 169 | +]; |
| 170 | + |
| 171 | +const label = (c: Cell) => `${c.zone} @ ${c.instant}`; |
| 172 | + |
| 173 | +/** |
| 174 | + * Probes around the window's UPPER bound, which is the only place this card |
| 175 | + * lives: the last instant inside, the boundary instant itself, the first |
| 176 | + * instant after — plus an unambiguous midday anchor and the window's own start, |
| 177 | + * so a repair that broke the LOWER bound cannot pass either. |
| 178 | + */ |
| 179 | +function probesFor(c: Cell): string[] { |
| 180 | + const [start, end] = c.window.map(ms); |
| 181 | + return [...new Set([ |
| 182 | + start, |
| 183 | + start + Math.floor((end - start) / 2), |
| 184 | + end - 1, |
| 185 | + end, // ⭐ THE instant this card is about |
| 186 | + end + 1, |
| 187 | + ])].map(iso); |
| 188 | +} |
| 189 | + |
| 190 | +/** The rows a half-open `[start, end)` window contains. */ |
| 191 | +const halfOpen = (probes: string[], w: [string, string]) => |
| 192 | + probes.filter((p) => ms(p) >= ms(w[0]) && ms(p) < ms(w[1])).sort(); |
| 193 | + |
| 194 | +/** The rows a closed `[start, end]` window contains — today's explicit-array reading. */ |
| 195 | +const closed = (probes: string[], w: [string, string]) => |
| 196 | + probes.filter((p) => ms(p) >= ms(w[0]) && ms(p) <= ms(w[1])).sort(); |
| 197 | + |
| 198 | +describe("#16179 — 'today' stops BEFORE tomorrow's first instant", () => { |
| 199 | + for (const c of CELLS) { |
| 200 | + for (const storage of STORAGE) { |
| 201 | + it(`${label(c)} · ${storage}: the row at the next day's 00:00:00.000 is NOT counted`, async () => { |
| 202 | + const probes = probesFor(c); |
| 203 | + const boundary = c.window[1]; |
| 204 | + |
| 205 | + // CONTROL FIRST — a probe set that never touches the boundary |
| 206 | + // would pass while asserting nothing about this card. |
| 207 | + expect(probes, `${label(c)}: the boundary instant must be planted`).toContain(boundary); |
| 208 | + |
| 209 | + const expected = halfOpen(probes, c.window); |
| 210 | + expect(expected, 'the boundary instant must be OUTSIDE the expected set').not.toContain(boundary); |
| 211 | + |
| 212 | + await at(c.zone, c.instant, async () => { |
| 213 | + await expect( |
| 214 | + probesSelected(probes, { range: 'today', timezone: c.zone, storage }), |
| 215 | + ).resolves.toEqual(expected); |
| 216 | + }); |
| 217 | + }); |
| 218 | + |
| 219 | + it(`${label(c)} · ${storage}: ⭐ an explicit [a, b] over the SAME window still counts b`, async () => { |
| 220 | + const probes = probesFor(c); |
| 221 | + const explicit: AnalyticsDateRange = [c.window[0], c.window[1]]; |
| 222 | + |
| 223 | + // The published reading, unchanged: a caller-written timestamp |
| 224 | + // end is INCLUSIVE. ⛔ This is route 1's tripwire — a repair |
| 225 | + // that made `$lt` unconditional reddens HERE. |
| 226 | + const expected = closed(probes, c.window); |
| 227 | + expect(expected, 'the control must include the boundary instant').toContain(c.window[1]); |
| 228 | + |
| 229 | + await at(c.zone, c.instant, async () => { |
| 230 | + await expect( |
| 231 | + probesSelected(probes, { range: explicit, timezone: c.zone, storage }), |
| 232 | + ).resolves.toEqual(expected); |
| 233 | + }); |
| 234 | + }); |
| 235 | + |
| 236 | + it(`${label(c)} · ${storage}: the two arms differ by EXACTLY the boundary instant`, async () => { |
| 237 | + const probes = probesFor(c); |
| 238 | + const explicit: AnalyticsDateRange = [c.window[0], c.window[1]]; |
| 239 | + |
| 240 | + await at(c.zone, c.instant, async () => { |
| 241 | + const token = await probesSelected(probes, { range: 'today', timezone: c.zone, storage }); |
| 242 | + const array = await probesSelected(probes, { range: explicit, timezone: c.zone, storage }); |
| 243 | + |
| 244 | + // Stated as data: the repair removed one instant from the |
| 245 | + // token's answer and nothing at all from the array's. |
| 246 | + expect(array.filter((p) => !token.includes(p))).toEqual([c.window[1]]); |
| 247 | + expect(token.filter((p) => !array.includes(p))).toEqual([]); |
| 248 | + }); |
| 249 | + }); |
| 250 | + } |
| 251 | + } |
| 252 | + |
| 253 | + it('every window literal is a local midnight in its own zone — checked against `Intl`, not against the code under test', () => { |
| 254 | + for (const c of CELLS) { |
| 255 | + for (const bound of c.window) { |
| 256 | + expect( |
| 257 | + localClock(bound, c.zone), |
| 258 | + `${label(c)}: ${bound} is not midnight in ${c.zone}`, |
| 259 | + ).toMatch(/ 00:00:00\.000$/); |
| 260 | + } |
| 261 | + } |
| 262 | + }); |
| 263 | + |
| 264 | + it('every window is exactly one calendar day apart and the cells are not all UTC', () => { |
| 265 | + for (const c of CELLS) { |
| 266 | + const [start, end] = c.window.map(ms); |
| 267 | + expect(end - start, `${label(c)}: window is not 24h`).toBe(86_400_000); |
| 268 | + } |
| 269 | + const nonUtcBoundaries = CELLS.filter((c) => !c.window[1].endsWith('T00:00:00.000Z')); |
| 270 | + expect( |
| 271 | + nonUtcBoundaries.length, |
| 272 | + 'every cell ends at UTC midnight, so a repair that re-derived the bound as a UTC day would pass', |
| 273 | + ).toBeGreaterThan(0); |
| 274 | + }); |
| 275 | +}); |
| 276 | + |
| 277 | +describe('#16179 — two adjacent day windows PARTITION the midnight instant', () => { |
| 278 | + // The double-count, driven end to end: the same row, the same table, asked |
| 279 | + // on two consecutive days. Before the repair it answered `2` — counted by |
| 280 | + // the day it ends and by the day it begins. |
| 281 | + const ZONE = 'Asia/Shanghai'; |
| 282 | + const MIDNIGHT = '2026-09-06T16:00:00.000Z'; // where 2026-09-07 begins in Shanghai |
| 283 | + |
| 284 | + for (const storage of STORAGE) { |
| 285 | + it(`${storage}: the row at midnight is counted by exactly one of the two days`, async () => { |
| 286 | + const probes = [MIDNIGHT]; |
| 287 | + let hits = 0; |
| 288 | + |
| 289 | + // The day that ENDS at MIDNIGHT. |
| 290 | + await at(ZONE, '2026-09-06T12:00:00Z', async () => { |
| 291 | + const got = await probesSelected(probes, { range: 'today', timezone: ZONE, storage }); |
| 292 | + hits += got.length; |
| 293 | + }); |
| 294 | + // The day that BEGINS at MIDNIGHT. |
| 295 | + await at(ZONE, '2026-09-07T02:00:00Z', async () => { |
| 296 | + const got = await probesSelected(probes, { range: 'today', timezone: ZONE, storage }); |
| 297 | + hits += got.length; |
| 298 | + }); |
| 299 | + |
| 300 | + expect(hits, 'a row must belong to exactly one day — 2 is the double-count this card is about').toBe(1); |
| 301 | + }); |
| 302 | + } |
| 303 | +}); |
| 304 | + |
| 305 | +describe('#16179 — a bare `YYYY-MM-DD` end still means the WHOLE day (#4042 / #3777)', () => { |
| 306 | + // The other exclusive-end route, which this card must not disturb: a bare |
| 307 | + // day the CALLER wrote is still widened to `< nextUtcCalendarDay(day)`. |
| 308 | + for (const storage of STORAGE) { |
| 309 | + it(`${storage}: ['2026-09-06', '2026-09-06'] selects all of 2026-09-06 and nothing of the 7th`, async () => { |
| 310 | + const probes = [ |
| 311 | + '2026-09-05T23:59:59.999Z', |
| 312 | + '2026-09-06T00:00:00.000Z', |
| 313 | + '2026-09-06T12:00:00.000Z', |
| 314 | + '2026-09-06T23:59:59.999Z', |
| 315 | + '2026-09-07T00:00:00.000Z', |
| 316 | + ]; |
| 317 | + await expect( |
| 318 | + probesSelected(probes, { range: ['2026-09-06', '2026-09-06'], storage }), |
| 319 | + ).resolves.toEqual([ |
| 320 | + '2026-09-06T00:00:00.000Z', |
| 321 | + '2026-09-06T12:00:00.000Z', |
| 322 | + '2026-09-06T23:59:59.999Z', |
| 323 | + ]); |
| 324 | + }); |
| 325 | + } |
| 326 | +}); |
0 commit comments