fix(代码规则): 给 C 题配的规则一半是哑弹，C++ 题根本配不了

后台的节点下拉是一张 C/Python 混在一起的 15 条表，整份铺给每种语言。给 C 题选到只有 Python 有的 list_comprehension、f-string，规则存得进去，判题时拿裸名去比节点类型，C 的语法树里永远不存在它——「必须使用列表推导式」永远失败、「不能使用 f-string」永远通过，两头都不报错，只有学生受着。反过来 mappings 支持的 do_while、 switch、struct、include 在表里没有，编辑器根本选不到。标签表改成按语言分组，和判题机 mappings 的键集逐条对齐；保存时校验规则与语言是否匹配，不匹配给中文提示。C 的 target 从 8 个可用变成 14 个。 C++ 接上了 tree-sitter-cpp，386 道 C++ 题从此能配规则。它继承 tree-sitter-c 的语法， C 那 14 个 target 实测全部通用，另加范围 for、类定义、try-catch、throw、namespace、模板、lambda、using 共 22 个。调用形态和 C/Python 都不同，一并处理：a.push_back() 和 p->push_back() 是 call_expression + field_expression，不是 Python 的 attribute； std::sort(...) 的 function 是 qualified_identifier 而不是 identifier，所以额外比一次 :: 末段，否则学生写没写 using namespace std 会得到不同判定。一起收掉的几处： - Java/Golang/JavaScript 配的规则一条都不会跑，题目页却照常把它们渲染成「要求」挂给学生看。现在后台不给这些语言开 tab，下发给学生的要求也按语言过滤。 - 「出现次数」不填数字存下来是一条恒真规则，描述还退化成光秃秃一个「for 循环」。切换引擎时给默认值，保存时拦下，读取时整条丢弃。 - 次数规则失败只说「if 条件出现 2 次 ✗」，学生不知道自己写了几次，补上「当前 N 次」。旧栈的引擎其实算了这个数，但 checker 只取 describe，算完就扔。 - must_have_nesting 的文案没走标签表，学生看到的是「必须使用 for_loop 嵌套」。 - 运算符文案给的是逻辑名，C 题的学生看到「必须使用 and 运算符」，而 C 里写的是 &&。语义校验放在 astRulesError() 而不是 zod 的 refine 上：astRulesSchema 同时用于读后台题目详情，在读路径上抛错会让历史脏数据把整个题目详情打不开。保存前先 pickAstRules() 剔除够不着的分组再校验，否则早年配过 C++ 规则的题会把老师锁死——tab 里看不到那组规则，保存却被拦下。生产库那 17 条规则（全是 Python3 的 must_exist_node / count_node）行为不变，逐条实跑核对过。C++ 的 22 个节点 target、25 个运算符也逐个跑了，没有恒假的哑弹。改了带 wasm 内嵌的 ast.ts，dev 和编译两种形态都验过。 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-27 11:53:37 -06:00
parent 280443c892
commit f38444c97a
9 changed files with 444 additions and 94 deletions
--- a/apps/api/src/judge/ast.ts
+++ b/apps/api/src/judge/ast.ts
@@ -1,14 +1,21 @@
 import {
+  AST_NODE_TARGETS_BY_LANGUAGE,
+  AST_OPERATOR_TARGETS_BY_LANGUAGE,
+  astNodeLabel,
+  astOperatorLabel,
+  astRuleIsMeaningful,
  astRuleSchema,
-  AST_NODE_TARGET_LABELS,
+  AST_SUPPORTED_LANGUAGES,
  type AstRequirement,
  type AstRequirements,
  type AstRule,
+  type AstRules,
 } from "@oj2/contract"
 import { Language, Parser, type Node } from "web-tree-sitter"
 // 语法 wasm 内嵌成资源。原来是 `Bun.resolveSync(pkg + "/" + name, import.meta.dir)`，
 // 编译成单二进制后 import.meta.dir 是 /$bunfs/root，解析不到 node_modules。见 vendor/jieba.ts
 import cWasmPath from "tree-sitter-c/tree-sitter-c.wasm" with { type: "file" }
+import cppWasmPath from "tree-sitter-cpp/tree-sitter-cpp.wasm" with { type: "file" }
 import pythonWasmPath from "tree-sitter-python/tree-sitter-python.wasm" with { type: "file" }
 // web-tree-sitter 自己的运行时 wasm，Parser.init() 要用
 import treeSitterWasmPath from "web-tree-sitter/web-tree-sitter.wasm" with { type: "file" }
@@ -20,8 +27,17 @@ export type { AstRule } from "@oj2/contract"
 export interface AstResult {
  description: string
  passed: boolean
+  /** count_* 引擎实际数到的次数。失败时前端拿它补一句「当前 N 次」 */
+  actual?: number
 }

+/**
+ * target → tree-sitter 节点类型。恒等的条目（`+`、`==` 这些运算符）不列，
+ * 走 `mapping[target] ?? target` 回落。
+ *
+ * **这里的键集是契约 AST_NODE_TARGETS_BY_LANGUAGE 的另一半**，两边必须同增同减：
+ * 那边决定后台下拉能选什么，这边决定判题机认得什么。只加一边就是静默错判。
+ */
 const mappings: Record<string, Record<string, string>> = {
  C: {
    for_loop: "for_statement",
@@ -42,6 +58,35 @@ const mappings: Record<string, Record<string, string>> = {
    or: "||",
    not: "!",
  },
+  "C++": {
+    // C 的那 14 条原样通用（tree-sitter-cpp 继承 tree-sitter-c 的语法）
+    for_loop: "for_statement",
+    while_loop: "while_statement",
+    do_while: "do_statement",
+    if_statement: "if_statement",
+    else_clause: "else_clause",
+    break: "break_statement",
+    continue: "continue_statement",
+    function_definition: "function_definition",
+    return: "return_statement",
+    switch_statement: "switch_statement",
+    case_statement: "case_statement",
+    assignment: "assignment_expression",
+    struct: "struct_specifier",
+    include: "preproc_include",
+    // C++ 独有
+    range_for_loop: "for_range_loop",
+    class_definition: "class_specifier",
+    try_except: "try_statement",
+    throw: "throw_statement",
+    namespace: "namespace_definition",
+    template: "template_declaration",
+    lambda: "lambda_expression",
+    using: "using_declaration",
+    and: "&&",
+    or: "||",
+    not: "!",
+  },
  Python3: {
    for_loop: "for_statement",
    while_loop: "while_statement",
@@ -79,7 +124,12 @@ async function loadLanguage(language: string) {
  const cached = languages.get(language)
  if (cached) return cached

-  const loaded = await Language.load(language === "C" ? cWasmPath : pythonWasmPath)
+  const wasmPath = language === "C"
+    ? cWasmPath
+    : language === "C++"
+      ? cppWasmPath
+      : pythonWasmPath
+  const loaded = await Language.load(wasmPath)
  languages.set(language, loaded)
  return loaded
 }
@@ -95,9 +145,9 @@ function hasNode(root: Node, type: string): boolean {
  return root.children.some((child) => hasNode(child, type))
 }

-function targetName(rule: AstRule) {
+function targetName(rule: AstRule, language?: string) {
  const target = rule.target ?? ""
-  return rule.label || AST_NODE_TARGET_LABELS[target] || target || "指定语法"
+  return rule.label || astNodeLabel(target, language) || "指定语法"
 }

 function countPhrase(verb: string, rule: AstRule) {
@@ -114,9 +164,9 @@ function countPhrase(verb: string, rule: AstRule) {
 * 用的是同一份 —— 原来前端 ProblemContent.vue 里另有一份几乎一样的实现，
 * 只有 min/max 同时给出时的措辞不一样（生产库里没有这种规则）。
 */
-export function describeAstRule(rule: AstRule): string {
+export function describeAstRule(rule: AstRule, language?: string): string {
  if (rule.message) return rule.message
-  const name = targetName(rule)
+  const name = targetName(rule, language)
  const target = rule.target ?? ""
  switch (rule.engine) {
    case "must_exist_node":
@@ -136,10 +186,12 @@ export function describeAstRule(rule: AstRule): string {
    case "must_not_call_method":
      return `不能调用 .${target}()`
    case "must_use_operator":
-      return `必须使用 ${target} 运算符`
+      return `必须使用 ${astOperatorLabel(target, language)} 运算符`
    case "must_have_nesting": {
-      const outer = rule.outer ?? ""
-      const inner = rule.inner ?? ""
+      // 这两个走 astNodeLabel 而不是裸值 —— 少了这一步文案就是
+      // 「必须使用 for_loop 嵌套」，旧栈 ast_checker/engines/nesting.py 是翻的
+      const outer = astNodeLabel(rule.outer ?? "", language)
+      const inner = astNodeLabel(rule.inner ?? "", language)
      return outer === inner
        ? `必须使用 ${outer} 嵌套`
        : `必须在 ${outer} 中嵌套使用 ${inner}`
@@ -157,6 +209,10 @@ function requirementKind(engine: AstRule["engine"]): AstRequirement["kind"] {
 /**
 * 把规则原文投影成下发给学生的「代码要求」。规则里的 engine / target 不出现在
 * 响应里 —— 阶段 3 泄露评审收掉 ast_rules 时要的就是这个，见契约的注释。
+ *
+ * 只投影判题机真检查得了的语言。原来这里不看语言，给 C++ 题配的规则照样渲染成
+ * 「必须使用 for 循环」挂在题目页上，而 loadLanguage 对 C++ 返回 null、
+ * checkAst 直接放行 —— 学生看得见要求，判题从不检查。
 */
 export function astRequirements(value: unknown): AstRequirements | null {
  const grouped = value && typeof value === "object" && !Array.isArray(value)
@@ -166,11 +222,13 @@ export function astRequirements(value: unknown): AstRequirements | null {
  const out: AstRequirements = {}
  for (const [language, rules] of Object.entries(grouped)) {
    if (!Array.isArray(rules)) continue
+    if (!AST_SUPPORTED_LANGUAGES.includes(language)) continue
    const items = rules.flatMap((rule) => {
      const parsed = astRuleSchema.safeParse(rule)
      if (!parsed.success) return []
+      if (!astRuleIsMeaningful(parsed.data)) return []
      return [{
-        description: describeAstRule(parsed.data),
+        description: describeAstRule(parsed.data, language),
        kind: requirementKind(parsed.data.engine),
      }]
    })
@@ -179,6 +237,63 @@ export function astRequirements(value: unknown): AstRequirements | null {
  return Object.keys(out).length > 0 ? out : null
 }

+/**
+ * AST 规则的语义校验。zod 只管形状（engine 在枚举里、min 是整数），管不了
+ * 「给 C 题选了只有 Python 才有的 list_comprehension」这类组合 —— 那种规则存得进去，
+ * 判题时 `mapping[target] ?? target` 拿裸名去比节点类型，永远失败或永远通过，
+ * 两头都不报错，只有学生受着。
+ *
+ * 放这儿而不是 astRulesSchema 的 refine 上：那个 schema 同时用于**读**后台题目详情，
+ * 在读路径上抛错会让历史脏数据直接把题目详情打不开。
+ */
+export function astRulesError(astRules: AstRules | null): string | null {
+  if (!astRules) return null
+  for (const [language, rules] of Object.entries(astRules)) {
+    if (rules.length === 0) continue
+    if (!AST_SUPPORTED_LANGUAGES.includes(language)) {
+      return `代码规则暂不支持 ${language}，判题机只检查 ${AST_SUPPORTED_LANGUAGES.join(" / ")}`
+    }
+    const nodes = AST_NODE_TARGETS_BY_LANGUAGE[language] ?? {}
+    const operators = AST_OPERATOR_TARGETS_BY_LANGUAGE[language] ?? {}
+    for (const [index, rule] of rules.entries()) {
+      const at = `代码规则 ${language} 第 ${index + 1} 条`
+      const target = rule.target ?? ""
+      if (rule.engine.endsWith("_node")) {
+        if (!(target in nodes)) return `${at}：${language} 没有「${target}」这种语法`
+      } else if (rule.engine === "must_use_operator") {
+        if (!(target in operators)) return `${at}：${language} 没有「${target}」运算符`
+      } else if (rule.engine === "must_have_nesting") {
+        for (const value of [rule.outer ?? "", rule.inner ?? ""]) {
+          if (!(value in nodes)) return `${at}：${language} 没有「${value}」这种语法`
+        }
+      } else if (!target.trim()) {
+        return `${at}：要检查的函数名/方法名不能为空`
+      }
+      if (!astRuleIsMeaningful(rule)) return `${at}：次数检查至少要填一个数字`
+    }
+  }
+  return null
+}
+
+/**
+ * 保存前清掉够不着的规则分组：不在题目 languages 里的（老师改过语言列表），
+ * 以及判题机检查不了的（C++ / Java / …）。两者编辑器都不给开 tab，留着就是死数据。
+ *
+ * 必须先剔除再校验，否则历史脏数据会把老师锁死：一道 languages 含 C++ 的题，
+ * 早年配过 C++ 规则，如今 tab 里看不到那组规则，保存却被「暂不支持 C++」拦下，
+ * 老师在界面上无从修改。
+ */
+export function pickAstRules(astRules: AstRules | null, languages: string[]): AstRules | null {
+  if (!astRules) return null
+  const out: AstRules = {}
+  for (const [language, rules] of Object.entries(astRules)) {
+    if (!languages.includes(language)) continue
+    if (!AST_SUPPORTED_LANGUAGES.includes(language)) continue
+    if (rules.length > 0) out[language] = rules
+  }
+  return Object.keys(out).length > 0 ? out : null
+}
+
 function rangePassed(count: number, rule: AstRule) {
  if (rule.exact !== undefined && count !== rule.exact) return false
  if (rule.min !== undefined && count < rule.min) return false
@@ -186,16 +301,41 @@ function rangePassed(count: number, rule: AstRule) {
  return true
 }

+const CALL_NODE_TYPES: Record<string, string> = {
+  C: "call_expression",
+  "C++": "call_expression",
+  Python3: "call",
+}
+
 function functionCalls(root: Node, target: string, language: string) {
-  const callType = language === "C" ? "call_expression" : "call"
+  const callType = CALL_NODE_TYPES[language] ?? "call"
  return collectNodes(root, callType).filter((call) => {
    const fn = call.childForFieldName("function")
-    return fn?.type === "identifier" && fn.text === target
+    if (!fn) return false
+    if (fn.type === "identifier") return fn.text === target
+    // `std::sort(...)` 是 qualified_identifier。学生写 sort 还是 std::sort 取决于
+    // 有没有 using namespace std，两种都得认，所以末段也比一次
+    if (language === "C++" && fn.type === "qualified_identifier") {
+      return fn.text === target || fn.text.split("::").pop() === target
+    }
+    return false
  })
 }

 function methodCalls(root: Node, target: string, language: string) {
-  if (language === "C") return []
+  // C++ 的 `a.push_back()` / `p->push_back()` 都是 call_expression + field_expression，
+  // 和 Python 的 attribute 不是一回事 —— 少了这个分支，C++ 的「必须调用 .push_back()」
+  // 会静默地永远失败
+  if (language === "C++") {
+    return collectNodes(root, "call_expression").filter((call) => {
+      const fn = call.childForFieldName("function")
+      return (
+        fn?.type === "field_expression" &&
+        fn.childForFieldName("field")?.text === target
+      )
+    })
+  }
+  if (language !== "Python3") return []
  return collectNodes(root, "call").filter((call) => {
    const fn = call.childForFieldName("function")
    return (
@@ -217,51 +357,53 @@ function evaluateRule(
  switch (rule.engine) {
    case "must_exist_node":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: hasNode(root, nodeType),
      }
    case "must_not_exist_node":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: !hasNode(root, nodeType),
      }
    case "count_node": {
      const count = collectNodes(root, nodeType).length
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: rangePassed(count, rule),
+        actual: count,
      }
    }
    case "must_call_function":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: functionCalls(root, target, language).length > 0,
      }
    case "must_not_call_function":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: functionCalls(root, target, language).length === 0,
      }
    case "count_function_call": {
      const count = functionCalls(root, target, language).length
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: rangePassed(count, rule),
+        actual: count,
      }
    }
    case "must_call_method":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: methodCalls(root, target, language).length > 0,
      }
    case "must_not_call_method":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: methodCalls(root, target, language).length === 0,
      }
    case "must_use_operator":
      return {
-        description: describeAstRule(rule),
+        description: describeAstRule(rule, language),
        passed: hasNode(root, nodeType),
      }
    case "must_have_nesting": {
@@ -272,7 +414,7 @@ function evaluateRule(
      const passed = collectNodes(root, outerType).some((node) =>
        node.children.some((child) => hasNode(child, innerType)),
      )
-      return { description: describeAstRule(rule), passed }
+      return { description: describeAstRule(rule, language), passed }
    }
    default:
      return null
@@ -297,6 +439,7 @@ export async function checkAst(
    try {
      const mapping = mappings[language] ?? {}
      const results = rules
+        .filter(astRuleIsMeaningful)
        .map((rule) => evaluateRule(tree.rootNode, rule, language, mapping))
        .filter((result): result is AstResult => result !== null)
      return { passed: results.every((result) => result.passed), results }
--- a/apps/api/src/routes/admin/problem.ts
+++ b/apps/api/src/routes/admin/problem.ts
@@ -11,6 +11,7 @@ import {
  sqlPreviewRequestSchema,
  sqlTestCaseScriptSchema,
  uploadTestCaseResponseSchema,
+  type AstRules,
  type SqlConfig,
 } from "@oj2/contract"
 import { and, count, desc, eq, ilike, inArray, isNull, ne, or, sql } from "drizzle-orm"
@@ -20,6 +21,7 @@ import { requireProblemPermission, type AppEnv } from "../../auth/middleware"
 import type { AuthUser } from "../../auth/session"
 import { db, schema } from "../../db"
 import { failure, success } from "../../http"
+import { astRulesError, pickAstRules } from "../../judge/ast"
 import { buildSqlDisplay } from "../../judge/sql"
 import { completeChat } from "../../services/ai"
 import { contestStatus } from "../../services/contest"
@@ -176,7 +178,10 @@ function commonChecks(data: {
  samples: unknown[]
  sqlConfig: SqlConfig | null
  answers: Record<string, unknown>[]
+  astRules: AstRules | null
 }): { error: string } | { sql: boolean } {
+  const astError = astRulesError(pickAstRules(data.astRules, data.languages))
+  if (astError) return { error: astError }
  if (data.languages.includes("SQL")) {
    if (data.languages.length !== 1) return { error: "SQL problem cannot be mixed with other languages" }
    if (!data.sqlConfig) return { error: "SQL problem requires sql_config" }
@@ -247,7 +252,7 @@ function problemValues(data: ReturnType<typeof createProblemRequestSchema.parse>
    showFlowchart: data.showFlowchart,
    mermaidCode: data.mermaidCode,
    flowchartHint: data.flowchartHint,
-    astRules: data.astRules ?? null,
+    astRules: pickAstRules(data.astRules, data.languages),
    answers: data.answers,
    prompt: data.prompt,
    // 防脏数据：非 SQL 题不应携带 SQL 配置，对齐旧 common_checks