From d01712a697794fc30a53deffe7add31d76029380 Mon Sep 17 00:00:00 2001 From: JianFeeeee Date: Wed, 7 Oct 2026 03:58:51 +0800 Subject: [PATCH] =?UTF-8?q?test(harness):=20=E5=8F=98=E5=BC=82=E6=B5=8B?= =?UTF-8?q?=E8=AF=95=E6=8B=92=E7=BB=9D=E5=9C=A8=E8=84=8F=E5=B7=A5=E4=BD=9C?= =?UTF-8?q?=E5=8C=BA=E4=B8=8A=E8=BF=90=E8=A1=8C?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 两个变异 harness（Go 版 discover、Python 版 quota）都是「把变异写进源码 文件、跑测试、再还原」。这个形状有两个陷阱，上一轮都真踩到了： 一、脏工作区上的 baseline 是错的 变异被覆盖写入实现文件。如果文件本来就有未提交改动（上一轮被 background task 超时杀掉、Ctrl-C 中断、编辑器里改了一半），那么: - 捕获的「原始内容」不是已提交的源码，baseline 跑的是别的东西 - 留下的那个变异会被下一轮当成 baseline 两种情况下所有裁决都毫无意义，而 harness 仍然报出干净的分数 —— 正是 「判据失效」最坏的一种：它不报错。 改为直接拒绝运行（Go 版 t.Fatalf，Python 版退出码 2），并且不自动 checkout： 脚本分不清「残留变异」和「人正在改」，静默回退真实改动比停下来更糟。 二、注入必须原子，还原必须覆盖所有退出路径 Python 版原来用 open(path,"w")，就地截断。与它并发的构建（background go test、编辑器 gofmt、编译器自己读文件）可能看到写了一半的文件，报 syntax error，然后被当成 COMPILE 静默豁免 —— 一个真实的变异就这样被放过。 改为 tempfile + os.replace。还原登记到 atexit 与 SIGINT/SIGTERM。 三、路径必须相对当前目录 Go 版最初用 cwd=包目录 + 仓根相对路径，git 匹配不到任何东西，守卫永远不 触发。两个 harness 现在都用 ./name，各自在自己目录里跑 git。 两个方向都验证过：干净时全杀（discover 11/11、quota 12/12），脏时拒绝运行。 --- internal/gateway/discover_mutate_test.go | 39 ++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/internal/gateway/discover_mutate_test.go b/internal/gateway/discover_mutate_test.go index 32e3f91..5574f28 100644 --- a/internal/gateway/discover_mutate_test.go +++ b/internal/gateway/discover_mutate_test.go @@ -15,6 +15,11 @@ package gateway // the filter selects a non-trivial number of tests (see baseline below), and it // treats "[no tests to run]" as a hard error rather than a green run. // +// It also must not be run against a DIRTY tree: the mutant is written over +// discover.go, and a leftover mutant from a killed run would make the baseline +// green against broken code while every verdict came from the wrong source. +// See the guard at the top of TestRealMutants. +// // Run: go test -tags luajit ./internal/gateway/ -run TestRealMutants -v import ( @@ -49,6 +54,23 @@ func TestRealMutants(t *testing.T) { if err != nil { t.Fatal(err) } + + // Refuse to run against a dirty tree. + // + // The mutant is written OVER discover.go, so on a dirty file the "original" + // captured above is not the committed source — the baseline then runs against + // whatever was there, and a killed run (a background-task timeout, a Ctrl-C) + // leaves a mutant behind that the NEXT run treats as the baseline. Both make + // every verdict meaningless while the harness still reports a clean score. + // + // Refusing rather than restoring: this cannot tell "leftover mutant" apart from + // "the developer is mid-edit", and silently reverting real work is worse than + // stopping. + if dirty, derr := mutationTargetIsDirty(wd, "discover.go"); derr == nil && dirty { + t.Fatalf("%s has uncommitted changes — commit or stash them first. A mutant "+ + "left behind by a killed run would otherwise become the baseline, and "+ + "every verdict below would be about code nobody wrote.", target) + } defer func() { if werr := os.WriteFile(target, orig, 0o644); werr != nil { t.Fatalf("restore discover.go: %v", werr) @@ -234,6 +256,23 @@ func runSuite(wd, filter string) string { return string(out) } +// mutationTargetIsDirty reports whether a file under internal/gateway has +// uncommitted changes, so the harness can refuse to run instead of treating a +// leftover mutant as the baseline. +// +// git runs from the package directory with a PATH RELATIVE to it. An earlier +// version of the sibling script passed a repo-relative pathspec while running in +// the package directory; git matched nothing and the guard never fired. +func mutationTargetIsDirty(wd, name string) (bool, error) { + cmd := exec.Command("git", "diff", "--name-only", "--", "./"+name) + cmd.Dir = wd + out, err := cmd.Output() + if err != nil { + return false, err + } + return strings.TrimSpace(string(out)) != "", nil +} + func countTests(out string) int { n := 0 for _, line := range strings.Split(out, "\n") {