fix(题单): 进度重算漏了分数和完成状态，奖章没人补发

进度算法在学生路径和后台路径各写了一遍，于是各自漂了一段。后台那份（resyncProgress）名叫「把所有参与者的进度重算一遍」，实际只更新分母和百分比： - 不碰 total_score。改题目分值时专门调了它，函数体里却没这个字段，score 类奖章因此按陈旧分数判定。 - 不碰 is_completed。加一道题之后分母变大、百分比掉下来，人还标着「已完成」。 - 不清理 progress_detail。删掉一道题之后 least(completed, total) 只保证不超过分母，会把没做的题算成做了 —— 3 题的题单只做出 C，删掉 C 就变成 1/2 = 50%。 - 不重算奖章。题目集一变 all_problems 的达标面就变了，没有任何地方补发。最后一条攒下了实打实的欠账：8-07 的快照里 53 条应发未发，涉及 30 名学生，误发 0 条。其中 23 条来自 2026-05-22 00:50 那次一分钟内跨 7 个题单的批量补进度 —— 进度补了，奖章没人回头判。两边不再分叉的唯一办法是只留一处算法，所以抽出 services/problemset.ts： computeProgress 是纯函数，学生做出一题和后台改题目都只是调用者； eligibleForBadge / recalculateBadge / resyncProgress 一并搬过来，补发脚本才能复用同一套判定。批量写回仍是一条 UPDATE ... FROM (VALUES ...)，没退回逐行往返。顺带修掉空题单的坑：isCompleted 加了 total > 0 前提。原来 0 === 0 也成立，老师先建题单、学生先加入、题目后加，加入那一刻就写下 complete_time 并计进「完成题单数」成就，而且后面补上题目也不会自愈。一处行为变化：退回未完成时 complete_time 会清空。后台那份原来保留旧时间，学生那份一直是清空的，统一成后者 —— 否则同一行会出现「未完成 + 有完成时间」，破坏现有数据里「complete_time 非空 ⟺ is_completed」这条不变量。代价是加题再删题会把历史完成时间洗成「现在」。 scripts/backfill-problemset-badges.ts 补历史欠账，默认只读预演，--apply 才落库。只要存在误发就拒绝执行并打出名单，要连收回一起做得显式加 --allow-revoke —— recalculateBadge 的删除是真删，user_badge 的 earned_time 没有别处备份。在生产快照上实跑：补发 1180 → 1233 条，复核全部一致，历史 earned_time 未被刷新； resyncProgress 对题单 9（7 题 / 117 人 / 100 人完成）加题后正确退回 0 人完成并收回 100 枚奖章，删题后完整恢复；改题目分值 10→20 使总分和 7460 → 8590，正好 +113×10。 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QqqZwxtXLo2GTqMi51C94D
2026-08-31 08:23:38 -06:00
parent ff31f7abd1
commit f9354b0df1
5 changed files with 280 additions and 89 deletions
--- a/apps/api/src/routes/admin/problemset.ts
+++ b/apps/api/src/routes/admin/problemset.ts
@@ -12,19 +12,19 @@ import {
  updateProblemSetRequestSchema,
  updateProblemSetStatusRequestSchema,
 } from "@oj2/contract"
-import { and, asc, count, desc, eq, ilike, inArray, isNull, notInArray, or, sql } from "drizzle-orm"
+import { and, asc, count, desc, eq, ilike, inArray, isNull, or, sql } from "drizzle-orm"
 import { Hono } from "hono"

 import { requireTeacher, type AppEnv } from "../../auth/middleware"
 import type { AuthUser } from "../../auth/session"
 import { db, schema } from "../../db"
 import { failure, success } from "../../http"
+import { recalculateBadge, resyncProgress } from "../../services/problemset"
 import { queryInteger, sampleUser } from "../helpers"

 export const adminProblemSetRoutes = new Hono<AppEnv>()

 type BadgeRow = typeof schema.problemsetBadge.$inferSelect
-type ProgressRow = typeof schema.problemsetProgress.$inferSelect

 /** 对齐旧 ensure_created_by：超管放行，其余人只能碰自己建的。越权报「不存在」 */
 function ownedBy(user: AuthUser, row: { createdById: number }) {
@@ -305,46 +305,6 @@ async function badgesWithCount(badges: BadgeRow[]) {
  }))
 }

-/** 纯逻辑判定，对齐旧 `ProblemSetBadge._is_eligible` */
-function eligible(badge: BadgeRow, progress: ProgressRow) {
-  if (badge.conditionType === "all_problems") {
-    return progress.totalProblemsCount > 0 &&
-      progress.completedProblemsCount === progress.totalProblemsCount
-  }
-  if (badge.conditionType === "problem_count") return progress.completedProblemsCount >= badge.conditionValue
-  if (badge.conditionType === "score") return progress.totalScore >= badge.conditionValue
-  return false
-}
-
-/**
- * 重算某个奖章的获得者，对齐旧 `recalculate_user_badges`（由 post_save 信号触发）。
- * 保留已有记录的 earnedTime —— 只增删差集，不是先清空再重建，
- * 否则每改一次条件所有人的获得时间都会刷新成今天。
- */
-async function recalculateBadge(badge: BadgeRow) {
-  const progresses = await db.select().from(schema.problemsetProgress)
-    .where(eq(schema.problemsetProgress.problemsetId, badge.problemsetId))
-  const eligibleIds = progresses.filter((item) => eligible(badge, item)).map((item) => item.userId)
-  await db.transaction(async (tx) => {
-    await tx.delete(schema.userBadge).where(and(
-      eq(schema.userBadge.badgeId, badge.id),
-      eligibleIds.length ? notInArray(schema.userBadge.userId, eligibleIds) : undefined,
-    ))
-    if (!eligibleIds.length) return
-    const existing = await tx.select({ userId: schema.userBadge.userId }).from(schema.userBadge)
-      .where(eq(schema.userBadge.badgeId, badge.id))
-    const have = new Set(existing.map((item) => item.userId))
-    const missing = eligibleIds.filter((id) => !have.has(id))
-    if (missing.length) {
-      await tx.insert(schema.userBadge).values(missing.map((userId) => ({
-        userId,
-        badgeId: badge.id,
-        earnedTime: new Date().toISOString(),
-      })))
-    }
-  })
-}
-
 adminProblemSetRoutes.get("/problem-sets/:id/badges", requireTeacher, async (c) => {
  const row = await loadOwned(c, c.get("user")!)
  if (!row) return failure(c, 404, "problem-set-not-found", "题单不存在")
@@ -408,31 +368,6 @@ adminProblemSetRoutes.delete("/problem-sets/:id/badges/:badgeId", requireTeacher

 // ---------------------------------------------------------------- 学生进度

-/**
- * 题目集或分值变动后，把所有参与者的进度重算一遍。
- *
- * 旧后端不做这件事：往题单里加一道题，学生那边的 totalProblemsCount 还是老数字，
- * 进度百分比因此偏高，甚至已经「完成」的人分母变了却还标着完成。
- * 只重算分母与百分比，不碰 completeTime —— 已经完成过的事实不因加题而撤销。
- */
-async function resyncProgress(problemsetId: number) {
-  const [totalRow] = await db.select({ value: count() }).from(schema.problemsetProblem)
-    .where(eq(schema.problemsetProblem.problemsetId, problemsetId))
-  const total = totalRow?.value ?? 0
-  // 一条 UPDATE 把整个题单的参与者刷完。以前是先把 progress 全查出来再逐行 update，
-  // 一个班的题单就是几十次往返，而算出来的值只跟 total 和这一行自己的 completed 有关。
-  // completed 用 least(...) 夹住，百分比按 JS 那边同样的「乘 10000 四舍五入再除 100」
-  // 保留两位小数 —— 数都是非负的，numeric 的 round 和 Math.round 在这个区间一致。
-  const completed = sql`least(${schema.problemsetProgress.completedProblemsCount}, ${total})`
-  await db.update(schema.problemsetProgress).set({
-    totalProblemsCount: total,
-    completedProblemsCount: completed,
-    progressPercentage: total > 0
-      ? sql`round((${completed}::numeric / ${total}) * 10000) / 100`
-      : sql`0`,
-  }).where(eq(schema.problemsetProgress.problemsetId, problemsetId))
-}
-
 adminProblemSetRoutes.get("/problem-sets/:id/progress", requireTeacher, async (c) => {
  const row = await loadOwned(c, c.get("user")!)
  if (!row) return failure(c, 404, "problem-set-not-found", "题单不存在")
--- a/apps/api/src/routes/problemset.ts
+++ b/apps/api/src/routes/problemset.ts
@@ -20,7 +20,6 @@ import {
  gt,
  ilike,
  inArray,
-  isNull,
  ne,
  or,
  sql,
@@ -33,6 +32,7 @@ import { publishAchievementNotification } from "../events"
 import { failure, success } from "../http"
 import { JudgeStatus } from "../judge/status"
 import { updateAchievementsForProblemSet } from "../services/achievements"
+import { computeProgress } from "../services/problemset"
 import { objectValue, queryInteger, sampleUser } from "./helpers"

 export const problemsetRoutes = new Hono<AppEnv>()
@@ -216,27 +216,9 @@ async function recomputeProgress(
 ) {
  const links = await tx.select({ problemId: schema.problemsetProblem.problemId, score: schema.problemsetProblem.score })
    .from(schema.problemsetProblem).where(eq(schema.problemsetProblem.problemsetId, progress.problemsetId))
-  const valid = new Map(links.map((link) => [String(link.problemId), link.score]))
-  for (const key of Object.keys(detail)) if (!valid.has(key)) delete detail[key]
-  let totalScore = 0
-  for (const [key, value] of Object.entries(detail)) {
-    const score = valid.get(key)
-    if (score === undefined) continue
-    totalScore += score
-    detail[key] = { ...objectValue(value), score }
-  }
-  const completed = Object.keys(detail).length
-  const total = links.length
-  const isCompleted = completed === total
-  const update = {
-    progressDetail: detail,
-    totalProblemsCount: total,
-    completedProblemsCount: completed,
-    totalScore,
-    progressPercentage: total > 0 ? completed / total * 100 : 0,
-    isCompleted,
-    completeTime: isCompleted ? progress.completeTime ?? new Date().toISOString() : null,
-  }
+  // 算法本身在 services/problemset.ts —— 后台改题目后的批量重算走的是同一份，
+  // 两边曾经各写一遍，结果后台那份少算了 total_score 和 is_completed
+  const update = computeProgress(detail, links, progress.completeTime)
  await tx.update(schema.problemsetProgress).set(update).where(eq(schema.problemsetProgress.id, progress.id))
  return { ...progress, ...update }
 }
--- a/apps/api/src/scripts/backfill-problemset-badges.ts
+++ b/apps/api/src/scripts/backfill-problemset-badges.ts
@@ -0,0 +1,93 @@
+import { eq } from "drizzle-orm"
+
+import { db, schema } from "../db"
+import { badgeHolderDiff, recalculateBadge } from "../services/problemset"
+
+/**
+ * 补发历史欠账的题单奖章。
+ *
+ * 奖章原本只在「学生做出一道题」那一刻发（`PUT /problem-set-progress`），进度要是从别的
+ * 路径变了 —— 后台加减题目、手工批量补进度 —— 就没人回头判过达标。生产快照里因此攒下
+ * 53 条应发未发、涉及 30 名学生，其中 23 条来自 2026-05-22 00:50 那次一分钟内跨 7 个题单
+ * 的批量补进度。
+ *
+ * 默认只读，把差异打出来；确认无误再加 --apply 落库。
+ * 补发用的是 recalculateBadge，它同时会**收回**已经不达标的人的奖章，所以只要存在
+ * 「误发」就先停下来让人看清楚，要真的收回得显式加 --allow-revoke。
+ *
+ *   bun src/scripts/backfill-problemset-badges.ts
+ *   bun src/scripts/backfill-problemset-badges.ts --apply
+ */
+const apply = process.argv.includes("--apply")
+const allowRevoke = process.argv.includes("--allow-revoke")
+
+const rows = await db
+  .select({ badge: schema.problemsetBadge, title: schema.problemset.title })
+  .from(schema.problemsetBadge)
+  .innerJoin(schema.problemset, eq(schema.problemset.id, schema.problemsetBadge.problemsetId))
+  .orderBy(schema.problemsetBadge.problemsetId, schema.problemsetBadge.id)
+
+if (rows.length === 0) {
+  console.log("没有任何题单奖章，无事可做")
+  process.exit(0)
+}
+
+const diffs = []
+for (const { badge, title } of rows) {
+  diffs.push({ badge, title, ...(await badgeHolderDiff(badge)) })
+}
+
+const missingTotal = diffs.reduce((sum, d) => sum + d.missing.length, 0)
+const extraTotal = diffs.reduce((sum, d) => sum + d.extra.length, 0)
+const affected = new Set(diffs.flatMap((d) => [...d.missing, ...d.extra]))
+
+console.log(`共 ${rows.length} 枚奖章\n`)
+for (const d of diffs) {
+  if (!d.missing.length && !d.extra.length) continue
+  const cond = `${d.badge.conditionType}/${d.badge.conditionValue}`
+  console.log(
+    `  题单${String(d.badge.problemsetId).padStart(2)} ${d.title}  [${d.badge.name}] ${cond}\n` +
+      `      应发 ${d.eligible} / 现有 ${d.held}` +
+      (d.missing.length ? `  漏发 ${d.missing.length}：user ${d.missing.join(", ")}` : "") +
+      (d.extra.length ? `  误发 ${d.extra.length}：user ${d.extra.join(", ")}` : ""),
+  )
+}
+console.log(`\n合计：漏发 ${missingTotal} 条，误发 ${extraTotal} 条，涉及 ${affected.size} 名学生`)
+
+if (missingTotal === 0 && extraTotal === 0) {
+  console.log("奖章与规则一致，无需补发")
+  process.exit(0)
+}
+
+if (!apply) {
+  console.log("\n这是只读预演。确认无误后加 --apply 落库。")
+  process.exit(0)
+}
+
+if (extraTotal > 0 && !allowRevoke) {
+  console.error(
+    `\n存在 ${extraTotal} 条误发。补发用的 recalculateBadge 会把它们**删掉**，` +
+      `而 user_badge 没有别处备份、earnedTime 删了就找不回来。\n` +
+      `确认要连同收回一起执行，加 --allow-revoke。`,
+  )
+  process.exit(1)
+}
+
+let touched = 0
+for (const d of diffs) {
+  if (!d.missing.length && !d.extra.length) continue
+  await recalculateBadge(d.badge)
+  touched += 1
+}
+console.log(`\n已重算 ${touched} 枚奖章，复核中……`)
+
+let remaining = 0
+for (const { badge, title } of rows) {
+  const after = await badgeHolderDiff(badge)
+  if (after.missing.length || after.extra.length) {
+    remaining += after.missing.length + after.extra.length
+    console.error(`  仍不一致：题单${badge.problemsetId} ${title} [${badge.name}]`, after)
+  }
+}
+console.log(remaining === 0 ? "复核通过：全部奖章与规则一致" : `复核未通过，仍有 ${remaining} 条差异`)
+process.exit(remaining === 0 ? 0 : 1)
--- a/apps/api/src/services/problemset.ts
+++ b/apps/api/src/services/problemset.ts
@@ -0,0 +1,180 @@
+import { and, eq, notInArray, sql } from "drizzle-orm"
+
+import { db, schema } from "../db"
+import { objectValue } from "../routes/helpers"
+
+type BadgeRow = typeof schema.problemsetBadge.$inferSelect
+type ProgressRow = typeof schema.problemsetProgress.$inferSelect
+type ProblemLink = { problemId: number; score: number }
+type BadgeCheck = Pick<ProgressRow, "completedProblemsCount" | "totalProblemsCount" | "totalScore">
+
+/**
+ * 题单进度的唯一算法：学生做出一道题后的增量更新、后台改动题目后的批量重算，都走这一份。
+ *
+ * 以前两边各写一遍，于是各自漂了一段。后台那份（resyncProgress）只更新分母和百分比：
+ *   - 改题目分值时调了它，可它根本不碰 total_score，score 类奖章按陈旧分数判定；
+ *   - 不碰 is_completed，加一道题之后分母变大、百分比掉下来，人还标着「已完成」；
+ *   - 不清理 progress_detail，删掉一道题之后 least(completed, total) 会把没做的题算成做了。
+ * 两边不再分叉的唯一办法是只留一处算法，所以这里做成纯函数，两边都只是调用者。
+ */
+export function computeProgress(
+  detail: Record<string, unknown>,
+  links: ProblemLink[],
+  previousCompleteTime: string | null,
+  now = new Date().toISOString(),
+) {
+  const scoreByProblem = new Map(links.map((link) => [String(link.problemId), link.score]))
+  // 已经移出题单的题目要从 detail 里剔掉，留着它 completed 就会比实际做出的题还多
+  const kept: Record<string, unknown> = {}
+  let totalScore = 0
+  for (const [key, value] of Object.entries(detail)) {
+    const score = scoreByProblem.get(key)
+    if (score === undefined) continue
+    totalScore += score
+    // 分值以题单当前的设置为准，detail 里存的是做出那一刻的快照
+    kept[key] = { ...objectValue(value), score }
+  }
+  const completed = Object.keys(kept).length
+  const total = links.length
+  // total > 0 这个前提不能省：0 === 0 同样成立，没有题目的题单会让人一加入就算「完成」，
+  // 还会写下 complete_time、计进「完成题单数」成就，而且后面补上题目也不会自愈。
+  const isCompleted = total > 0 && completed === total
+  return {
+    progressDetail: kept,
+    totalProblemsCount: total,
+    completedProblemsCount: completed,
+    totalScore,
+    // 乘 10000 四舍五入再除 100，保留两位小数
+    progressPercentage: total > 0 ? Math.round((completed / total) * 10000) / 100 : 0,
+    isCompleted,
+    // 完成状态没了，complete_time 也不该留着。学生那一路本来就是这么写的，
+    // 后台这一路以前保留旧时间，于是同一行会出现「未完成 + 有完成时间」。
+    completeTime: isCompleted ? previousCompleteTime ?? now : null,
+  }
+}
+
+type ProgressWrite = ReturnType<typeof computeProgress> & { id: number }
+
+/**
+ * 一条 UPDATE 刷完整批参与者。逐行 update 的话一个班的题单就是上百次往返，
+ * 而每行要写的值都已经在内存里算好了，没有一个依赖数据库现有的值。
+ */
+async function writeProgress(rows: ProgressWrite[]) {
+  // 每行 8 个参数，留足余量避开 Postgres 的 65535 个绑定参数上限
+  for (let start = 0; start < rows.length; start += 1000) {
+    const chunk = rows.slice(start, start + 1000)
+    const values = sql.join(
+      chunk.map((row) => sql`(
+        ${row.id}::bigint,
+        ${JSON.stringify(row.progressDetail)}::jsonb,
+        ${row.totalProblemsCount}::int,
+        ${row.completedProblemsCount}::int,
+        ${row.totalScore}::int,
+        ${row.progressPercentage}::double precision,
+        ${row.isCompleted}::boolean,
+        ${row.completeTime}::timestamptz
+      )`),
+      sql`, `,
+    )
+    await db.execute(sql`
+      update ${schema.problemsetProgress} as pg set
+        progress_detail = v.detail,
+        total_problems_count = v.total_count,
+        completed_problems_count = v.completed_count,
+        total_score = v.total_score,
+        progress_percentage = v.percentage,
+        is_completed = v.is_completed,
+        complete_time = v.complete_time
+      from (values ${values}) as v(
+        id, detail, total_count, completed_count, total_score, percentage, is_completed, complete_time
+      )
+      where pg.id = v.id
+    `)
+  }
+}
+
+/** 纯逻辑判定，对齐旧 `ProblemSetBadge._is_eligible` */
+export function eligibleForBadge(badge: BadgeRow, progress: BadgeCheck) {
+  if (badge.conditionType === "all_problems") {
+    return progress.totalProblemsCount > 0 &&
+      progress.completedProblemsCount === progress.totalProblemsCount
+  }
+  if (badge.conditionType === "problem_count") return progress.completedProblemsCount >= badge.conditionValue
+  if (badge.conditionType === "score") return progress.totalScore >= badge.conditionValue
+  return false
+}
+
+/**
+ * 重算某枚奖章的获得者，对齐旧 `recalculate_user_badges`（由 post_save 信号触发）。
+ * 保留已有记录的 earnedTime —— 只增删差集，不是先清空再重建，
+ * 否则每改一次条件所有人的获得时间都会刷新成今天。
+ *
+ * 调用方手里已经有最新的进度时把它传进来（`known`），省掉一次回表；
+ * 更要紧的是别用刚写完库之前的旧值去判定。
+ */
+export async function recalculateBadge(badge: BadgeRow, known?: (BadgeCheck & { userId: number })[]) {
+  const progresses = known ?? await db.select().from(schema.problemsetProgress)
+    .where(eq(schema.problemsetProgress.problemsetId, badge.problemsetId))
+  const eligibleIds = progresses.filter((item) => eligibleForBadge(badge, item)).map((item) => item.userId)
+  await db.transaction(async (tx) => {
+    await tx.delete(schema.userBadge).where(and(
+      eq(schema.userBadge.badgeId, badge.id),
+      eligibleIds.length ? notInArray(schema.userBadge.userId, eligibleIds) : undefined,
+    ))
+    if (!eligibleIds.length) return
+    const existing = await tx.select({ userId: schema.userBadge.userId }).from(schema.userBadge)
+      .where(eq(schema.userBadge.badgeId, badge.id))
+    const have = new Set(existing.map((item) => item.userId))
+    const missing = eligibleIds.filter((id) => !have.has(id))
+    if (missing.length) {
+      await tx.insert(schema.userBadge).values(missing.map((userId) => ({
+        userId,
+        badgeId: badge.id,
+        earnedTime: new Date().toISOString(),
+      })))
+    }
+  })
+}
+
+/**
+ * 题目集或分值变动后，把所有参与者的进度整体重算一遍，再重算这份题单的奖章。
+ *
+ * 旧后端两件事都不做：往题单里加一道题，学生那边的 totalProblemsCount 还是老数字，
+ * 进度百分比因此偏高；奖章那边更是没人回头判过，生产快照里因此攒下 53 条应发未发
+ * （30 名学生，其中 23 条来自 2026-05-22 那次批量补进度）。
+ */
+export async function resyncProgress(problemsetId: number) {
+  const [links, progresses, badges] = await Promise.all([
+    db.select({ problemId: schema.problemsetProblem.problemId, score: schema.problemsetProblem.score })
+      .from(schema.problemsetProblem).where(eq(schema.problemsetProblem.problemsetId, problemsetId)),
+    db.select().from(schema.problemsetProgress)
+      .where(eq(schema.problemsetProgress.problemsetId, problemsetId)),
+    db.select().from(schema.problemsetBadge)
+      .where(eq(schema.problemsetBadge.problemsetId, problemsetId)),
+  ])
+  const now = new Date().toISOString()
+  const updated = progresses.map((progress) => ({
+    ...progress,
+    ...computeProgress(objectValue(progress.progressDetail), links, progress.completeTime, now),
+  }))
+  if (updated.length) await writeProgress(updated)
+  for (const badge of badges) await recalculateBadge(badge, updated)
+}
+
+/** 按奖章算出「现在应该有谁」，只读，供补发脚本先看后写 */
+export async function badgeHolderDiff(badge: BadgeRow) {
+  const [progresses, holders] = await Promise.all([
+    db.select().from(schema.problemsetProgress)
+      .where(eq(schema.problemsetProgress.problemsetId, badge.problemsetId)),
+    db.select({ userId: schema.userBadge.userId }).from(schema.userBadge)
+      .where(eq(schema.userBadge.badgeId, badge.id)),
+  ])
+  const eligible = new Set(progresses.filter((item) => eligibleForBadge(badge, item)).map((item) => item.userId))
+  const have = new Set(holders.map((item) => item.userId))
+  return {
+    missing: [...eligible].filter((id) => !have.has(id)),
+    extra: [...have].filter((id) => !eligible.has(id)),
+    eligible: eligible.size,
+    held: have.size,
+  }
+}