feat(parser): macro expansion, conditionals and include splicing with -I

Assisted-by: GLM 5.3 Flash

cmd/gasm/audit.go

@@ -37,7 +37,7 @@ import (
 // construction and are excluded from the diff; the other architectures list
 // their conditional branches outright.
 func cmdAuditInstructions(args []string) error {
-	fs := newCommand("audit-instructions", "gasm audit-instructions [--corpus [dir]] [amd64|arm64|riscv64|loong64]", `
+	fs := newCommand("audit-instructions", "gasm audit-instructions [--corpus [dir]] [-I dir] [amd64|arm64|riscv64|loong64]", `
 Compare the gasm encoder for the given architecture (default amd64) against
 go tool asm and print the diff: superset encodings (gasm-only, shippable via
 gasm asm --format goobj) and known-but-unencodable names (the backlog).  The
@@ -57,11 +57,13 @@ per-architecture pass rates and the most common failure reasons, which drive
 the encodability backlog by frequency rather than by table order.
 `)
 	corpus := fs.Bool("corpus", false, "assemble a corpus of .s files and report pass rates and failure reasons")
+	var dirs includeDirs
+	fs.Var(&dirs, "I", "directory to search for #include files (may be repeated)")
 	if err := fs.Parse(args); err != nil {
 		return err
 	}
 	if *corpus {
-		return cmdAuditCorpus(fs.Args())
+		return cmdAuditCorpus(fs.Args(), dirs)
 	}
 	archName := "amd64"
 	switch n := len(fs.Args()); {
@@ -395,8 +397,11 @@ func (t *corpusTally) fail(path, reason string) {
 	}
 }
 
-// cmdAuditCorpus implements audit-instructions --corpus.
-func cmdAuditCorpus(args []string) error {
+// cmdAuditCorpus implements audit-instructions --corpus.  The include
+// directories carry #include resolution over a corpus whose files refer to
+// headers such as GOROOT/pkg/include, the same -I a toolchain comparison
+// needs.
+func cmdAuditCorpus(args []string, dirs includeDirs) error {
 	if len(args) > 1 {
 		return &usageError{fmt.Errorf("audit-instructions --corpus takes at most one directory argument")}
 	}
@@ -410,7 +415,25 @@ func cmdAuditCorpus(args []string) error {
 		}
 		root = filepath.Join(strings.TrimSpace(string(out)), "src")
 	}
-	stats, err := runCorpusAudit(root)
+	// The toolchain's shipped headers (funcdata.h and friends) define the
+	// macros GOROOT files include; a corpus audit measures those files, so
+	// the header directory joins the search path automatically.  go_asm.h
+	// is compiler-generated per package and stays unresolvable on purpose.
+	if out, err := exec.Command("go", "env", "GOROOT").Output(); err == nil {
+		pkgInclude := filepath.Join(strings.TrimSpace(string(out)), "pkg", "include")
+		if fi, err := os.Stat(pkgInclude); err == nil && fi.IsDir() {
+			seen := false
+			for _, d := range dirs {
+				if d == pkgInclude {
+					seen = true
+				}
+			}
+			if !seen {
+				dirs = append(dirs, pkgInclude)
+			}
+		}
+	}
+	stats, err := runCorpusAudit(root, dirs)
 	if err != nil {
 		return err
 	}
@@ -454,7 +477,7 @@ func otherPortFile(path string) bool {
 	return false
 }
 
-func runCorpusAudit(root string) (*corpusStats, error) {
+func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 	files, err := asmFiles(root)
 	if err != nil {
 		return nil, err
@@ -479,7 +502,7 @@ func runCorpusAudit(root string) (*corpusStats, error) {
 		if err != nil {
 			return nil, err
 		}
-		f, errs := parser.Parse(path, src)
+		f, errs := parser.ParseWithOptions(path, src, parser.Options{Expand: true, IncludeDirs: dirs})
 
 		var wanted []int // indexes into targets
 		if a := arch.FromFilename(path); a != arch.Unknown {