fix(cmd): honour //go:build in the corpus audit

Assisted-by: GLM 5.3 Flash

cmd/gasm/audit.go

@@ -5,6 +5,7 @@ package main
 
 import (
 	"fmt"
+	"go/build/constraint"
 	"maps"
 	"os"
 	"os/exec"
@@ -476,8 +477,10 @@ type corpusStats struct {
 	root      string
 	files     int
 	generic   int // files attempted for all four architectures
+	narrowed  int // files whose //go:build admits a proper subset of the four
+	excluded  int // files whose //go:build admits none of the four: never compiled
 	otherPort int // files named for another Go port: never attempted
-	full      int // files that assembled for every target architecture
+	full      int // files that assembled for every applicable target architecture
 	targets   []corpusTarget
 	tallies   []*corpusTally
 }
@@ -573,6 +576,57 @@ func otherGOOSFile(path string) bool {
 	return false
 }
 
+// buildConstraint returns the file's leading //go:build expression, or nil
+// when the file carries none.  The constraint governs the same header block
+// go/build reads: blank lines and comments may precede it, and the first
+// line that is neither ends the block.  A constraint that does not parse
+// narrows nothing, so the file stays in the attempted set: the audit must
+// never exclude a file the toolchain would compile.
+func buildConstraint(src string) constraint.Expr {
+	for line := range strings.SplitSeq(src, "\n") {
+		t := strings.TrimSpace(line)
+		switch {
+		case t == "":
+			continue
+		case strings.HasPrefix(t, "//"):
+			if constraint.IsGoBuild(t) {
+				e, err := constraint.Parse(t)
+				if err != nil {
+					return nil
+				}
+				return e
+			}
+			continue
+		default:
+			return nil
+		}
+	}
+	return nil
+}
+
+// unixOS is go/build's unixOS set: the GOOSes the unix build tag admits.
+var unixOS = map[string]bool{
+	"aix": true, "android": true, "darwin": true, "dragonfly": true,
+	"freebsd": true, "hurd": true, "illumos": true, "ios": true,
+	"linux": true, "netbsd": true, "openbsd": true, "solaris": true,
+}
+
+// constraintTags answers the build tags a plain `go build` sets for a
+// target: the GOOS and GOARCH, gc, and unix on the unix-like GOOSes.  No
+// experiment, sanitiser or cgo tag is ever true: the audit models the
+// default build, and no GOROOT assembly file's constraint hinges on cgo.
+func constraintTags(goarch, goos string) func(string) bool {
+	return func(tag string) bool {
+		switch tag {
+		case goarch, goos, "gc":
+			return true
+		case "unix":
+			return unixOS[goos]
+		}
+		return false
+	}
+}
+
 func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 	files, err := asmFiles(root)
 	if err != nil {
@@ -590,8 +644,8 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 		tallies[i] = &corpusTally{reasons: map[string]int{}, example: map[string]string{}}
 	}
 	// full is the north-star number: a file counts when every architecture
-	// its name allows assembles it.
-	full, generic, otherPort := 0, 0, 0
+	// its build admits assembles it.
+	full, generic, otherPort, narrowedCount, excluded := 0, 0, 0, 0, 0
 
 	// Header generation is created on first use, so a corpus with no
 	// go_asm.h includes never pays for a temp directory.
@@ -614,28 +668,78 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 		// invisible to a file-name rule).
 		goos := goosFromFilename(path)
 
+		// The GOOS the header generation type-checks under follows the
+		// file's name when the name carries one; the ambient GOOS is the
+		// honest guess otherwise.
+		namedArch := arch.FromFilename(path)
 		var wanted []int // indexes into targets
-		if a := arch.FromFilename(path); a != arch.Unknown {
+		other := false
+		switch {
+		case namedArch != arch.Unknown:
 			for i, tg := range targets {
-				if tg.a == a {
+				if tg.a == namedArch {
 					wanted = append(wanted, i)
 				}
 			}
-		} else if otherPortFile(path) {
+		case otherPortFile(path):
 			// A file named for a Go port gasm does not support (arm,
 			// 386, s390x, ...) or for another GOOS is compiled by no
 			// supported-arch build, so it is neither generic nor a
 			// per-arch attempt: counting it as generic would make the
 			// headline unreachably low for reasons no supported target
 			// can fix.
+			other = true
 			otherPort++
-		} else {
-			generic++
+		default:
 			for i := range targets {
 				wanted = append(wanted, i)
 			}
 		}
 
+		// A //go:build constraint narrows the set of targets the file is
+		// assembled for, the way the go command compiles the file only for
+		// the targets the expression admits: cpu_x86.s belongs to the x86
+		// build alone, and a file whose constraint admits none of the four
+		// targets (the goexperiment.runtimesecret and msan trees) is
+		// compiled by no supported build.  The tags mirror what a plain
+		// `go build` sets: the GOOS and GOARCH, gc, and unix on the
+		// unix-like GOOSes; no experiment, sanitiser or cgo tag is ever
+		// true.  The GOOS is the file's own when the name carries one,
+		// else the ambient one.
+		goosForEval := goos
+		if goosForEval == "" {
+			goosForEval = runtime.GOOS
+		}
+		narrowed := false
+		if len(wanted) > 0 {
+			if ce := buildConstraint(src); ce != nil {
+				kept := make([]int, 0, len(wanted))
+				for _, i := range wanted {
+					tg := targets[i]
+					if ce.Eval(constraintTags(goarchName(tg.a), goosForEval)) {
+						kept = append(kept, i)
+					}
+				}
+				if len(kept) < len(wanted) {
+					narrowed = true
+				}
+				wanted = kept
+			}
+		}
+
+		switch {
+		case other:
+			// already tallied above
+		case len(wanted) == 0:
+			excluded++
+		case namedArch != arch.Unknown:
+			// a per-arch attempt over the constraint's subset
+		case narrowed:
+			narrowedCount++
+		default:
+			generic++
+		}
+
 		// A file that includes go_asm.h parses against a per-target header:
 		// the defines differ per architecture (internal/cpu's layout, for
 		// one) and per GOOS (sys_darwin_arm64.s's trampoline constants,
@@ -719,6 +823,8 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 		root:      root,
 		files:     len(files),
 		generic:   generic,
+		narrowed:  narrowedCount,
+		excluded:  excluded,
 		otherPort: otherPort,
 		full:      full,
 		targets:   targets,
@@ -728,13 +834,15 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 
 // printCorpusStats renders the corpus audit report.
 func printCorpusStats(s *corpusStats, list bool) {
-	fmt.Printf("corpus %s: %d files (%d generic, attempted for all architectures; %d named for other Go ports, never attempted)\n", s.root, s.files, s.generic, s.otherPort)
+	fmt.Printf("corpus %s: %d files (%d generic, attempted for all architectures; %d narrowed by //go:build; %d excluded by //go:build; %d named for other Go ports, never attempted)\n",
+		s.root, s.files, s.generic, s.narrowed, s.excluded, s.otherPort)
 	// The rate is over the files a supported build would attempt: the
-	// other ports' files sit in the count for completeness but can never
-	// assemble, so counting them in the denominator would report the gap
-	// of architectures gasm deliberately does not target.
-	attemptable := max(s.files-s.otherPort, 1)
-	fmt.Printf("  assemble for every target architecture: %d of %d attemptable (%.1f%%)\n", s.full, attemptable, 100*float64(s.full)/float64(attemptable))
+	// other ports' files and the ones no supported target compiles sit in
+	// the count for completeness but can never assemble, so counting them
+	// in the denominator would report the gap of platforms gasm
+	// deliberately does not target.
+	attemptable := max(s.files-s.otherPort-s.excluded, 1)
+	fmt.Printf("  assemble for every applicable target: %d of %d attemptable (%.1f%%)\n", s.full, attemptable, 100*float64(s.full)/float64(attemptable))
 	for i, tg := range s.targets {
 		t := s.tallies[i]
 		fmt.Printf("  %s: %d/%d attempted\n", tg.name, t.assembled, t.attempted)