c8cd75cf6c
接管另一路会话的 Phase 5 在飞件收口(5A/5C 主体由那一路落码,本笔补齐 P1-B7 与两处台账并整量验证)。 - 5A/B60:撞款 console 的行窗口在服务端真分页(响应 dup 行数 ≤ pageSize,total_dup 仍是未分页 总数)、dupGroup 判据收归服务端单一出处(前端 dupWithinGroup 删掉,两套同名规则不再分叉)、 排序先于切窗;后管矩阵改预聚合+列窗 40。读数(200 列 × 50 行):每行 3 店 8.4 → 5.3 → 0.7ms (12.4×),每行 40 店 83.7 → 18.4 → 1.8ms(45.3×)。服务端不设列窗是判断不是漏做:shops 每行 只有 5 个标量,而矩阵的列来自已分页的行——给 shops 再加分页会把"全局指标读全集"和"列窗读本页" 两套语义搅在一起。浏览器首屏/交互耗时本机拿不到,登记为 Phase 6 现网复量。 - P1-B6:claim 循环的父任务终态判定折成一次批量 IN(TaskFileJobBatchQueries+Mapper XML, 铁律 1 收口在 Mapper),逐行 CAS 认领一字不动。 - P1-B5:V187 只建 idx_biz_file_task_resume_of;审计给的候选集索引**有意不建**(V184 前缀已覆盖, OR/IS-NULL 与 COALESCE 不可索引),判据把这条负判定钉住。真库 EXPLAIN 本机无 MySQL,顺延现网。 - P1-B8:结果载荷的对象存储删除移到 afterCommit,事务里不再做 120s 超时的网络调用。 - P1-B7:结果集读取按窗提交+收割(窗口=线程池队列容量的一半)。审计把它记成"无 limit",但截断 是正确性错误不是性能取舍,真能收的是"整份结果集被读两遍"——一次性提交时每支 Future 把解好的 载荷扣在自己身上直到全部收割完,峰值=结果集+另一份整副本;分窗后副本只驻留一窗。流式组装 契约要改 4 个模块的调用方,本 Phase 未做,别读成 P1-B7 已闭环。 - SourceScanTest 台账随之登记:裸名 25 → 26、调用方 18 → 19(P1-B7 的窗口判据只能打在源码上—— 线程池只有 8 个线程,"同时开始读几行"改前改后读数相同,差异只体现在堆上,mock 数不出来)。
184 lines
8.2 KiB
TypeScript
184 lines
8.2 KiB
TypeScript
import test from 'node:test'
|
||
import assert from 'node:assert/strict'
|
||
import { buildMatrixCells, matrixCellOf, storeColumnsOf } from '../src/pages/tasks/duplicate-console-logic.ts'
|
||
import type { DuplicateItem, DuplicateOccurrence } from '../src/pages/tasks/duplicate-model.ts'
|
||
|
||
/**
|
||
* B60 撞款矩阵:预聚合的等价性与前后读数。
|
||
*
|
||
* 审计指的那件事是「每格多次全量 filter」——模板一格要付 cellCount ×2 + cellTitle(内部再
|
||
* cellCount + cellCountryDots + 每站点一次 cellCountryCount),每次都是把该行 occurrences 整份
|
||
* filter 一遍,而且**每格都新建一条文案字符串**。下面 `legacyCell` 就是页面原来那几行函数的
|
||
* 原样搬运,当"前";与新一次算完的 `buildMatrixCells`(空格按列共用一份视图)对撞:
|
||
* 先证明结果逐字相同(预聚合不是靠少算蒙过去的),再同尺量时间。
|
||
*/
|
||
function occ(asin: string, shopName: string, country: string): DuplicateOccurrence {
|
||
return {
|
||
asin,
|
||
date: '2026-09-01',
|
||
price: '',
|
||
brand: 'B',
|
||
shopName,
|
||
groupName: '',
|
||
countryCodes: [country],
|
||
country,
|
||
}
|
||
}
|
||
|
||
const shopKey = (name: string): string => (name || '').trim().toLowerCase()
|
||
|
||
interface CellView {
|
||
count: number
|
||
dots: string[]
|
||
title: string
|
||
}
|
||
|
||
/** 原页面的逐格算法(一格扫整行 occurrences 若干次,并且每格造一条文案)。 */
|
||
function legacyCellOccurrences(item: DuplicateItem, shop: string): DuplicateOccurrence[] {
|
||
const key = shopKey(shop)
|
||
return (item.occurrences || []).filter((entry) => shopKey(entry.shopName) === key)
|
||
}
|
||
|
||
function legacyCell(item: DuplicateItem, shop: string): CellView {
|
||
const count = legacyCellOccurrences(item, shop).length
|
||
const codes = new Set<string>()
|
||
for (const entry of legacyCellOccurrences(item, shop)) if (entry.country) codes.add(entry.country.toUpperCase())
|
||
const dots = [...codes]
|
||
const sites = dots.map((code) => `${code} ${legacyCellOccurrences(item, shop).filter((entry) => (entry.country || '').toUpperCase() === code).length}条`)
|
||
return {
|
||
count,
|
||
dots,
|
||
title: count ? `${shop} 在售 ${count} 条 · ${sites.join('、')}` : `${shop} 无此 ASIN`,
|
||
}
|
||
}
|
||
|
||
/** 页面现在的读法:一次取值;空格取该列那一份共用视图(不再造文案)。 */
|
||
function fastCell(cells: ReturnType<typeof buildMatrixCells>, item: DuplicateItem, shop: string, blank: CellView): CellView {
|
||
const cell = matrixCellOf(cells, item.asin, shop)
|
||
if (!cell.count) return blank
|
||
const sites = cell.sites.map((site) => `${site.code} ${site.count}条`)
|
||
return {
|
||
count: cell.count,
|
||
dots: cell.sites.map((site) => site.code),
|
||
title: sites.length ? `${shop} 在售 ${cell.count} 条 · ${sites.join('、')}` : `${shop} 在售 ${cell.count} 条`,
|
||
}
|
||
}
|
||
|
||
function fixtureItem(asin: string, shops: [string, string][]): DuplicateItem {
|
||
const occurrences = shops.map(([shop, country]) => occ(asin, shop, country))
|
||
return {
|
||
asin,
|
||
shopCount: new Set(occurrences.map((entry) => shopKey(entry.shopName))).size,
|
||
recordCount: occurrences.length,
|
||
occurrences,
|
||
}
|
||
}
|
||
|
||
function blankViews(columns: string[]): CellView[] {
|
||
return columns.map((shop) => ({ count: 0, dots: [] as string[], title: `${shop} 无此 ASIN` }))
|
||
}
|
||
|
||
/**
|
||
* 200 列 × 50 行的矩阵夹具。`shopsPerRow` 决定密度:现实中一个撞款 ASIN 落在几家到几十家店,
|
||
* 而逐格 filter 的代价正是按「行内 occurrences × 列数」乘出来的——密度越高旧算法越吃亏,
|
||
* 所以两种密度都取读数,不挑对自己有利的那一档。
|
||
*/
|
||
function matrixFixture(columns: string[], shopsPerRow: number): DuplicateItem[] {
|
||
return Array.from({ length: 50 }, (_, index) => {
|
||
const pairs: [string, string][] = []
|
||
for (let offset = 0; offset < shopsPerRow; offset++) {
|
||
const shop = columns[(index * 7 + offset * 61) % columns.length]
|
||
pairs.push([shop, 'UK'], [shop, 'DE'])
|
||
}
|
||
return fixtureItem(`B${String(index).padStart(4, '0')}`, pairs)
|
||
})
|
||
}
|
||
|
||
test('矩阵预聚合与逐格 filter 结果逐字相同', () => {
|
||
const rows = [
|
||
fixtureItem('A1', [['Shop a', 'UK'], ['Shop a', 'uk'], ['ShopB', ''], ['ShopB', 'DE']]),
|
||
fixtureItem('A2', [['ShopC', 'FR']]),
|
||
]
|
||
const columns = storeColumnsOf(rows)
|
||
const cells = buildMatrixCells(rows, columns)
|
||
const blanks = blankViews(columns)
|
||
columns.forEach((column, index) => {
|
||
for (const item of rows) {
|
||
assert.deepEqual(fastCell(cells, item, column, blanks[index]), legacyCell(item, column), `${item.asin}/${column}`)
|
||
}
|
||
})
|
||
// 每行只给「本行真涉及」的列建格:A1 涉及 2 店(大小写/空格归一后同店)+ A2 涉及 1 店。
|
||
assert.equal(cells.size, 3)
|
||
})
|
||
|
||
test('列集或行集为空时不建任何格', () => {
|
||
const rows = [fixtureItem('A1', [['ShopA', 'UK']])]
|
||
assert.equal(buildMatrixCells(rows, []).size, 0)
|
||
assert.equal(buildMatrixCells([], ['ShopA']).size, 0)
|
||
})
|
||
|
||
/** 列窗口:只给本窗点名的列建格(120 列的夹具切 40 列窗口,格子数就按 40 乘)。 */
|
||
test('列窗口切窗后每行最多铺满窗口宽度的格', () => {
|
||
const window = 40
|
||
const rows = Array.from({ length: 50 }, (_, index) =>
|
||
fixtureItem(`A${index}`, Array.from({ length: window * 3 }, (_, shop) => [`Shop${shop}`, 'UK'])))
|
||
const all = storeColumnsOf(rows)
|
||
assert.equal(all.length, window * 3, '夹具本身就有 120 列(不设上限时的形状)')
|
||
|
||
const columns = all.slice(0, window)
|
||
const cells = buildMatrixCells(rows, columns)
|
||
assert.equal(columns.length, window, '本窗只铺 40 列')
|
||
assert.equal(cells.size, rows.length * window, '窗口外的 80 列一格都不建')
|
||
})
|
||
|
||
/**
|
||
* B60 判据的读数:200 列 × 50 行,同一把尺前后各跑一遍(5 轮取最好一次——本机同时有别的路在跑,
|
||
* 单次读数能被调度噪声放大好几倍)。
|
||
*
|
||
* 度量对象是「矩阵格集合的 JS 计算」,审计点名的就是这条。**浏览器首屏/交互耗时本机拿不到**
|
||
* (没有真实店铺数据、也没有浏览器现场),按准出括注登记为现网复量项,不许拿这条当"首屏已实测"读。
|
||
*/
|
||
test('200列×50行:预聚合与按列切窗都必须快过逐格 filter', () => {
|
||
const columns = Array.from({ length: 200 }, (_, index) => `Shop${index}`)
|
||
const blanks = blankViews(columns)
|
||
const windowColumns = columns.slice(0, 40)
|
||
const windowBlanks = blanks.slice(0, 40)
|
||
const best = (run: () => unknown): number => {
|
||
let ms = Number.POSITIVE_INFINITY
|
||
for (let attempt = 0; attempt < 5; attempt++) {
|
||
const start = performance.now()
|
||
run()
|
||
ms = Math.min(ms, performance.now() - start)
|
||
}
|
||
return ms
|
||
}
|
||
|
||
const readings: string[] = []
|
||
for (const shopsPerRow of [3, 40]) {
|
||
const rows = matrixFixture(columns, shopsPerRow)
|
||
const legacySweep = () => {
|
||
const out: CellView[] = []
|
||
for (const item of rows) for (const column of columns) out.push(legacyCell(item, column))
|
||
return out
|
||
}
|
||
const precomputedSweep = (cols: string[], cellBlanks: CellView[]) => {
|
||
const cells = buildMatrixCells(rows, cols)
|
||
const out: CellView[] = []
|
||
for (const item of rows) {
|
||
cols.forEach((column, index) => out.push(fastCell(cells, item, column, cellBlanks[index])))
|
||
}
|
||
return out
|
||
}
|
||
|
||
assert.deepEqual(precomputedSweep(columns, blanks), legacySweep(), '前后必须同一份格子(快不是靠少算)')
|
||
|
||
const beforeMs = best(legacySweep)
|
||
const precomputeMs = best(() => precomputedSweep(columns, blanks))
|
||
const shippedMs = best(() => precomputedSweep(windowColumns, windowBlanks))
|
||
readings.push(`每行${shopsPerRow}店:逐格filter=${beforeMs.toFixed(1)}ms → 预聚合=${precomputeMs.toFixed(1)}ms(${(beforeMs / precomputeMs).toFixed(1)}×) → 预聚合+切窗40列=${shippedMs.toFixed(1)}ms(${(beforeMs / shippedMs).toFixed(1)}×)`)
|
||
assert.ok(precomputeMs < beforeMs, `预聚合没省下来(每行${shopsPerRow}店):${beforeMs.toFixed(1)}ms → ${precomputeMs.toFixed(1)}ms`)
|
||
assert.ok(shippedMs * 2 < beforeMs, `切窗后仍不够快(每行${shopsPerRow}店):${beforeMs.toFixed(1)}ms → ${shippedMs.toFixed(1)}ms`)
|
||
}
|
||
console.log(`[B60 读数] 200列×50行 ${readings.join(' | ')}`)
|
||
})
|