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 {

cmd/gasm/main.go

@@ -240,6 +240,16 @@ func readSource(path string) (string, error) {
 	return string(b), err
 }
 
+// includeDirs collects repeatable -I flags: the directories searched for
+// #include files during macro expansion and include splicing.
+type includeDirs []string
+
+func (d *includeDirs) String() string { return strings.Join(*d, ",") }
+func (d *includeDirs) Set(v string) error {
+	*d = append(*d, v)
+	return nil
+}
+
 func cmdTokens(args []string) int {
 	fs := newCommand("tokens", "gasm tokens <file>", `
 Print the lexical token stream of FILE: position, token kind and text, one
@@ -476,7 +486,7 @@ hover, document symbols, diagnostics and semantic-token highlighting.
 }
 
 func cmdAsm(args []string) int {
-	fs := newCommand("asm", "gasm asm [--format raw|elf|goobj] [-p pkg] [-GOARCH arch] [-o out] <file>", `
+	fs := newCommand("asm", "gasm asm [--format raw|elf|goobj] [-I dir] [-p pkg] [-GOARCH arch] [-o out] <file>", `
 	Assemble FILE without the Go toolchain: every TEXT function is encoded to
 	machine code and printed as a hex dump.  Supported architectures: amd64
 	(including VEX/AVX2 and EVEX/AVX-512), arm64 (AArch64 integer, FP,
@@ -498,9 +508,11 @@ and the format version from go version).
 	format := fs.String("format", "raw", "output format: raw (concatenated image), elf or goobj (Go object)")
 	pkg := fs.String("p", "", "package path for --format goobj (qualifies the exported symbols)")
 	archName := fs.String("GOARCH", "", "target architecture: amd64, arm64, riscv64 or loong64 (overrides the file-name suffix)")
+	var dirs includeDirs
+	fs.Var(&dirs, "I", "directory to search for #include files (may be repeated)")
 	fs.Parse(args)
 	if fs.NArg() != 1 {
-		fmt.Fprintln(os.Stderr, "usage: gasm asm [--format raw|elf|goobj] [-p pkg] [-GOARCH arch] [-o out] <file>")
+		fmt.Fprintln(os.Stderr, "usage: gasm asm [--format raw|elf|goobj] [-I dir] [-p pkg] [-GOARCH arch] [-o out] <file>")
 		return 2
 	}
 	// The format is validated before anything else, so a bogus value exits 2
@@ -526,7 +538,7 @@ and the format version from go version).
 		fmt.Fprintln(os.Stderr, "gasm:", err)
 		return 1
 	}
-	f, errs := parser.Parse(path, src)
+	f, errs := parser.ParseWithOptions(path, src, parser.Options{Expand: true, IncludeDirs: dirs})
 	for _, e := range errs {
 		fmt.Fprintf(os.Stderr, "%s: %v\n", path, e)
 	}
@@ -634,7 +646,7 @@ and the format version from go version).
 
 // cmdDiff compares the machine code of two assembly files.
 func cmdDiff(args []string) int {
-	set := newCommand("diff", "gasm diff [-GOARCH arch] <file1.s> <file2.s>", `
+	set := newCommand("diff", "gasm diff [-GOARCH arch] [-I dir] <file1.s> <file2.s>", `
 Compare the machine code produced by assembling two files.
 Shows which functions differ and the byte-level differences.
 Useful for verifying that two implementations produce identical code,
@@ -645,9 +657,11 @@ e.g. --map wideCopyAVX2=wideCopyAVX512 pairs the two regardless of suffix.
 `)
 	mapSpec := set.String("map", "", "comma-separated old=new pairs to match functions with different names")
 	archName := set.String("GOARCH", "", "target architecture for both files: amd64, arm64, riscv64 or loong64")
+	var dirs includeDirs
+	set.Var(&dirs, "I", "directory to search for #include files (may be repeated)")
 	set.Parse(args)
 	if set.NArg() != 2 {
-		fmt.Fprintln(os.Stderr, "usage: gasm diff [-GOARCH arch] <file1.s> <file2.s>")
+		fmt.Fprintln(os.Stderr, "usage: gasm diff [-GOARCH arch] [-I dir] <file1.s> <file2.s>")
 		return 2
 	}
 	path1, path2 := set.Arg(0), set.Arg(1)
@@ -675,12 +689,12 @@ e.g. --map wideCopyAVX2=wideCopyAVX512 pairs the two regardless of suffix.
 	}
 
 	// Assemble both files.
-	img1, err := assemblePath(path1, forced)
+	img1, err := assemblePath(path1, forced, dirs)
 	if err != nil {
 		fmt.Fprintf(os.Stderr, "gasm diff: %s: %v\n", path1, err)
 		return 1
 	}
-	img2, err := assemblePath(path2, forced)
+	img2, err := assemblePath(path2, forced, dirs)
 	if err != nil {
 		fmt.Fprintf(os.Stderr, "gasm diff: %s: %v\n", path2, err)
 		return 1
@@ -755,14 +769,15 @@ func assembleFile(targetArch arch.Arch, f *ast.File) (*asm.Image, error) {
 	}
 }
 
-// assemblePath reads, parses and assembles a file (used by cmdDiff).  A
-// non-Unknown forced architecture overrides the file-name suffix.
-func assemblePath(path string, forced arch.Arch) (*asm.Image, error) {
+// assemblePath reads, preprocesses, parses and assembles a file (used by
+// cmdDiff).  A non-Unknown forced architecture overrides the file-name
+// suffix.
+func assemblePath(path string, forced arch.Arch, dirs includeDirs) (*asm.Image, error) {
 	src, err := readSource(path)
 	if err != nil {
 		return nil, err
 	}
-	f, errs := parser.Parse(path, src)
+	f, errs := parser.ParseWithOptions(path, src, parser.Options{Expand: true, IncludeDirs: dirs})
 	for _, e := range errs {
 		fmt.Fprintf(os.Stderr, "%s: %v\n", path, e)
 	}

cmd/gasm/main_test.go

@@ -403,7 +403,7 @@ func TestRunCorpusAudit(t *testing.T) {
 	write("generic.s", "#include \"textflag.h\"\nTEXT ·g(SB), NOSPLIT, $0-0\n\tRET\n")
 	write("broken.s", "#include \"textflag.h\"\nTEXT ·b(SB), NOSPLIT, $0-0\n\tJMP nowhere\n\tRET\n")
 
-	stats, err := runCorpusAudit(dir)
+	stats, err := runCorpusAudit(dir, nil)
 	if err != nil {
 		t.Fatalf("runCorpusAudit: %v", err)
 	}

cmd/gasm/preproc_test.go

@@ -0,0 +1,109 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// writeTree writes a directory of files and returns its root.
+func writeTree(t *testing.T, files map[string]string) string {
+	t.Helper()
+	dir := t.TempDir()
+	for name, content := range files {
+		path := filepath.Join(dir, name)
+		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+			t.Fatal(err)
+		}
+		if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+			t.Fatal(err)
+		}
+	}
+	return dir
+}
+
+// TestAsmMacroAndIncludeEndToEnd drives `gasm asm` over a source with an
+// in-file parameterised macro and an include resolved through -I, and checks
+// the assembled bytes came from the expansion (the loop body counts six
+// increments, two per expanded iteration).
+func TestAsmMacroAndIncludeEndToEnd(t *testing.T) {
+	if testing.Short() {
+		t.Skip("runs the assembler end to end")
+	}
+	dir := writeTree(t, map[string]string{
+		"inc/consts.h": "#define NITER 3\n",
+		"main_amd64.s": "#include \"textflag.h\"\n" +
+			"#include \"consts.h\"\n" +
+			"#define STEP(r) ADDQ $1, r; ADDQ $1, r\n" +
+			"TEXT ·f(SB), NOSPLIT, $0-8\n" +
+			"\tXORQ AX, AX\n" +
+			"\tMOVQ $NITER, CX\n" +
+			"loop:\n" +
+			"\tSTEP(AX)\n" +
+			"\tDECQ CX\n" +
+			"\tJNZ loop\n" +
+			"\tMOVQ AX, ret+0(FP)\n" +
+			"\tRET\n",
+	})
+	stdout, stderr, code := capture(func() int {
+		return cmdAsm([]string{"-I", filepath.Join(dir, "inc"), "-GOARCH", "amd64", filepath.Join(dir, "main_amd64.s")})
+	})
+	if code != 0 {
+		t.Fatalf("gasm asm exited %d: %s%s", code, stdout, stderr)
+	}
+	// The macro expanded to two ADDQ $1 encodings in the static body; the
+	// iteration count lives in the runtime loop.
+	if n := strings.Count(stdout, "83 c0 01"); n != 2 {
+		t.Errorf("found %d ADDQ $1 encodings in the image, want 2:\n%s", n, stdout)
+	}
+}
+
+// TestAsmIncludeResolutionOrder pins the -I search order end to end: the
+// including file's directory wins over the -I directories.
+func TestAsmIncludeResolutionOrder(t *testing.T) {
+	if testing.Short() {
+		t.Skip("runs the assembler end to end")
+	}
+	dir := writeTree(t, map[string]string{
+		"src/main_amd64.s": "#include \"textflag.h\"\n" +
+			"#include \"vals.h\"\n" +
+			"TEXT ·f(SB), NOSPLIT, $0\n" +
+			"\tMOVQ $VAL, AX\n" +
+			"\tRET\n",
+		"src/vals.h":   "#define VAL 1\n",
+		"late/vals.h":  "#define VAL 2\n",
+		"early/vals.h": "#define VAL 3\n",
+	})
+	stdout, stderr, code := capture(func() int {
+		return cmdAsm([]string{"-I", filepath.Join(dir, "early"), "-I", filepath.Join(dir, "late"),
+			"-GOARCH", "amd64", filepath.Join(dir, "src", "main_amd64.s")})
+	})
+	if code != 0 {
+		t.Fatalf("gasm asm exited %d: %s%s", code, stdout, stderr)
+	}
+	// VAL came from src/vals.h, not from either -I directory: the image
+	// loads the immediate 1.
+	if !strings.Contains(stdout, "b8 01 00 00 00") {
+		t.Errorf("expected the source-directory VAL (immediate 1) in:\n%s", stdout)
+	}
+}
+
+// TestAsmMissingIncludeIsAnError pins the diagnostic for an include that
+// resolves nowhere on the assembly path.
+func TestAsmMissingIncludeIsAnError(t *testing.T) {
+	if testing.Short() {
+		t.Skip("runs the assembler end to end")
+	}
+	path := writeTemp(t, "main_amd64.s", "#include \"textflag.h\"\n#include \"nothere.h\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n")
+	_, stderr, code := capture(func() int { return cmdAsm([]string{"-GOARCH", "amd64", path}) })
+	if code == 0 {
+		t.Fatal("gasm asm accepted a file whose include resolves nowhere")
+	}
+	if !strings.Contains(stderr, `#include "nothere.h"`) {
+		t.Errorf("stderr does not name the failing include: %s", stderr)
+	}
+}

docs/CLI.md

@@ -141,12 +141,13 @@ gasm lint kernel_amd64.s
 ## asm
 
 ```text
-Usage: gasm asm [--format raw|elf|goobj] [-p pkg] [-GOARCH arch] [-o out] <file>
+Usage: gasm asm [--format raw|elf|goobj] [-I dir] [-p pkg] [-GOARCH arch] [-o out] <file>
 ```
 
 | Flag | Default | Effect |
 |---|---|---|
 | `-format` | `raw` | output format: `raw` (concatenated image), `elf` or `goobj` (Go object) |
+| `-I` | empty | directory to search for `#include` files; may be repeated, searched in order after the source directory |
 | `-p` | empty | package path for `--format goobj`, qualifying the exported symbols |
 | `-GOARCH` | empty | target architecture: `amd64`, `arm64`, `riscv64` or `loong64`; overrides the file-name suffix |
 | `-o` | empty | write the output to this file instead of a hex dump on stdout |
@@ -162,6 +163,13 @@ system toolchain; `goobj` emits the Go toolchain's own object format, which
 installed: the object preamble is captured from `go tool asm` and the format
 version from `go version`. `raw` and `elf` need no toolchain at all.
 
+Assembly preprocessing matches the toolchain's: `#define` macros (object and
+parameterised) expand at the point of use, `#undef`, `#ifdef`, `#ifndef`,
+`#else` and `#endif` behave as in `go tool asm`, `;` separates statements,
+and `#include "file"` splices the named file in, resolved against the source
+directory and then each `-I` directory in order. `textflag.h` is the one
+header that is not spliced: gasm consumes its flag names natively.
+
 ```sh
 gasm asm hello_amd64.s
 ```
@@ -305,12 +313,13 @@ gasm debug --func add --cover hello_amd64.s
 ## diff
 
 ```text
-Usage: gasm diff [-GOARCH arch] <file1.s> <file2.s>
+Usage: gasm diff [-GOARCH arch] [-I dir] <file1.s> <file2.s>
 ```
 
 | Flag | Default | Effect |
 |---|---|---|
 | `-GOARCH` | empty | target architecture for both files, overriding the file-name suffixes |
+| `-I` | empty | directory to search for `#include` files; may be repeated, searched in order after the source directory |
 | `-map` | empty | comma-separated `old=new` pairs to match functions with different names |
 
 Functions are paired by exact name unless `--map` says otherwise, so
@@ -348,7 +357,7 @@ add: 16 bytes, args=24, frame=0 NOSPLIT
 ## audit-instructions
 
 ```text
-Usage: gasm audit-instructions [--corpus [dir]] [amd64|arm64|riscv64|loong64]
+Usage: gasm audit-instructions [--corpus [dir]] [-I dir] [amd64|arm64|riscv64|loong64]
 ```
 
 Compare the gasm encoder for the given architecture (default amd64) against the

docs/man/gasm-asm.1

@@ -2,7 +2,7 @@
 .SH NAME
 gasm-asm \- assemble Plan 9 assembly without the Go toolchain
 .SH SYNOPSIS
-.B gasm asm [\-\-format raw|elf|goobj] [\-p pkg] [\-GOARCH arch] [\-o out] <file>
+.B gasm asm [\-\-format raw|elf|goobj] [\-I dir] [\-p pkg] [\-GOARCH arch] [\-o out] <file>
 .SH DESCRIPTION
 Assemble FILE without the Go toolchain: every TEXT function is encoded
 to machine code and printed as a hex dump.  Supported architectures:
@@ -47,6 +47,10 @@ functions link too.
 .B \-\-format \fIraw|elf|goobj\fR
 Output format; the default is raw.
 .TP
+.B \-I \fIdir\fR
+Directory to search for #include files; may be repeated, searched in
+order after the source directory.
+.TP
 .B \-p \fIpkg\fR
 Package path for --format goobj, qualifying the exported symbols.
 .TP

docs/man/gasm-audit-instructions.1

@@ -2,7 +2,7 @@
 .SH NAME
 gasm-audit-instructions \- diff the encoder against the Go toolchain, or measure a corpus
 .SH SYNOPSIS
-.B gasm audit\-instructions [\-\-corpus [\fIdir\fR]] [amd64|arm64|riscv64|loong64]
+.B gasm audit\-instructions [\-\-corpus [\fIdir\fR]] [\-I dir] [amd64|arm64|riscv64|loong64]
 .SH DESCRIPTION
 Compare the gasm encoder for the given architecture (default amd64)
 against
@@ -38,6 +38,12 @@ second.
 .B \-\-corpus [\fIdir\fR]
 Assemble a corpus of .s files and report pass rates and failure
 reasons.
+.TP
+.B \-I \fIdir\fR
+Directory to search for #include files; may be repeated, searched in
+order after the source directory.  A corpus run whose files include
+toolchain headers (such as GOROOT/pkg/include) needs it, the same -I a
+toolchain comparison takes.
 .SH EXIT STATUS
 The mnemonic-diff mode reports through its output and exits 0; a failed
 probe or an unknown architecture exits non-zero.

docs/man/gasm-diff.1

@@ -2,7 +2,7 @@
 .SH NAME
 gasm-diff \- compare the machine code of two assembly files
 .SH SYNOPSIS
-.B gasm diff [\-GOARCH arch] <file1.s> <file2.s>
+.B gasm diff [\-GOARCH arch] [\-I dir] <file1.s> <file2.s>
 .SH DESCRIPTION
 Compare the machine code produced by assembling two files.  Shows which
 functions differ and the byte-level differences.  Useful for verifying
@@ -20,6 +20,10 @@ pairs two variants regardless of suffix.
 Target architecture for both files: amd64, arm64, riscv64 or loong64;
 overrides the file-name suffixes.
 .TP
+.B \-I \fIdir\fR
+Directory to search for #include files; may be repeated, searched in
+order after the source directory.
+.TP
 .B \-\-map \fIspec\fR
 Comma-separated old=new pairs to match functions with different names.
 .SH EXIT STATUS

lexer/lexer.go

@@ -119,7 +119,9 @@ func (l *Lexer) Next() token.Token {
 		// is a C-preprocessor line continuation (used by #define macros in the
 		// runtime .s files): splice the lines together by consuming both, so
 		// the whole macro becomes one logical line that the parser treats as an
-		// opaque preprocessor directive.
+		// opaque preprocessor directive.  The backslash may also reach its
+		// newline across whitespace and a trailing comment ("…; \ // note\n"),
+		// which the toolchain's scanner skips the same way.
 		for {
 			c := l.cur()
 			if c == ' ' || c == '\t' || c == '\r' {
@@ -136,6 +138,16 @@ func (l *Lexer) Next() token.Token {
 				}
 				continue
 			}
+			if c == '\\' && l.continuationAhead() {
+				l.advance() // backslash, then the runes the scan saw
+				for !l.atEnd() && l.cur() != '\n' {
+					l.advance()
+				}
+				if !l.atEnd() {
+					l.advance() // the newline that closes the continuation
+				}
+				continue
+			}
 			break
 		}
 
@@ -185,6 +197,28 @@ func (l *Lexer) Next() token.Token {
 	}
 }
 
+// continuationAhead reports, without consuming anything, whether the
+// backslash at the current position closes onto a newline through nothing
+// but horizontal whitespace and one line comment.  Positions after the
+// backslash are inspected directly on the rune slice so a non-match leaves
+// the scanner state untouched.
+func (l *Lexer) continuationAhead() bool {
+	i := l.i + 1
+	for i < len(l.src) {
+		switch r := l.src[i]; {
+		case r == ' ' || r == '\t' || r == '\r':
+			i++
+		case r == '/' && i+1 < len(l.src) && l.src[i+1] == '/':
+			for i < len(l.src) && l.src[i] != '\n' {
+				i++
+			}
+		default:
+			return r == '\n'
+		}
+	}
+	return false
+}
+
 // lineComment consumes a // comment up to, but not including, the newline.  A
 // trailing run of \r, spaces and tabs is line-ending whitespace rather than
 // comment content, so it never enters the token text.  Trimming only a \r
@@ -403,6 +437,15 @@ func (l *Lexer) punct(start token.Position) token.Token {
 	case '|':
 		l.advance()
 		return l.make(token.Pipe, start, "|")
+	case ';':
+		l.advance()
+		return l.make(token.Semicolon, start, ";")
+	case '&':
+		l.advance()
+		return l.make(token.Ampersand, start, "&")
+	case '~':
+		l.advance()
+		return l.make(token.Tilde, start, "~")
 	default:
 		// Unknown rune: emit it as Illegal and move on.
 		l.advance()

parser/expr.go

@@ -0,0 +1,146 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Constant-expression folding for operands.  The toolchain's assembler
+// evaluates arithmetic in every operand position, and macro-heavy GOROOT
+// sources lean on it: parameterised bodies carry offsets like
+// ((index*4)+0)(base), immediates like $(32-shift) and masks like
+// $~63 or $(1<<0|1<<9).  Substituting the parameters textually therefore
+// leaves constant arithmetic behind, and the parser folds it here, keeping
+// the operand AST identical to what the same literals written out would
+// produce.  Anything that is not a closed integer expression fails to fold
+// and falls through to the ordinary operand paths.
+package parser
+
+import (
+	"sourcedock.dev/petrbalvin/gasm-devkit/token"
+)
+
+// foldExpr evaluates the constant integer expression at the head of ts and
+// returns its value together with the unconsumed tokens.  ok is false when
+// the tokens do not form an expression, which is the callers' signal to use
+// the ordinary parsing paths.
+func foldExpr(ts []token.Token) (val int64, rest []token.Token, ok bool) {
+	v, rest, ok := foldAdd(ts)
+	if !ok {
+		return 0, ts, false
+	}
+	return v, rest, true
+}
+
+// foldAdd parses addition-level expressions: +, - and | bind loosest, the
+// Plan 9 convention that makes x<<1|3 read as (x<<1)|3.
+func foldAdd(ts []token.Token) (int64, []token.Token, bool) {
+	v, rest, ok := foldMul(ts)
+	if !ok {
+		return 0, ts, false
+	}
+	for len(rest) > 0 {
+		kind := rest[0].Kind
+		if kind != token.Plus && kind != token.Minus && kind != token.Pipe {
+			return v, rest, true
+		}
+		w, r2, ok := foldMul(rest[1:])
+		if !ok {
+			return v, rest, true
+		}
+		switch kind {
+		case token.Plus:
+			v += w
+		case token.Minus:
+			v -= w
+		case token.Pipe:
+			v |= w
+		}
+		rest = r2
+	}
+	return v, rest, true
+}
+
+// foldMul parses multiplication-level expressions: *, / and the bit
+// operators &, << and >>.
+func foldMul(ts []token.Token) (int64, []token.Token, bool) {
+	v, rest, ok := foldFactor(ts)
+	if !ok {
+		return 0, ts, false
+	}
+	for len(rest) > 0 {
+		switch rest[0].Kind {
+		case token.Star:
+			w, r2, ok := foldFactor(rest[1:])
+			if !ok {
+				return v, rest, true
+			}
+			v *= w
+			rest = r2
+		case token.Slash:
+			w, r2, ok := foldFactor(rest[1:])
+			if !ok || w == 0 {
+				return v, rest, true
+			}
+			v /= w
+			rest = r2
+		case token.Ampersand:
+			w, r2, ok := foldFactor(rest[1:])
+			if !ok {
+				return v, rest, true
+			}
+			v &= w
+			rest = r2
+		case token.LShift:
+			w, r2, ok := foldFactor(rest[1:])
+			if !ok || w < 0 || w >= 64 {
+				return v, rest, true
+			}
+			v <<= uint(w)
+			rest = r2
+		case token.RShift:
+			w, r2, ok := foldFactor(rest[1:])
+			if !ok || w < 0 || w >= 64 {
+				return v, rest, true
+			}
+			v >>= uint(w)
+			rest = r2
+		default:
+			return v, rest, true
+		}
+	}
+	return v, rest, true
+}
+
+// foldFactor parses a number, a parenthesised expression, or a unary sign
+// or complement.
+func foldFactor(ts []token.Token) (int64, []token.Token, bool) {
+	if len(ts) == 0 {
+		return 0, ts, false
+	}
+	switch ts[0].Kind {
+	case token.Number:
+		v, ok := tryInt(ts[0].Text)
+		if !ok {
+			return 0, ts, false
+		}
+		return v, ts[1:], true
+	case token.LParen:
+		v, rest, ok := foldAdd(ts[1:])
+		if !ok || len(rest) == 0 || rest[0].Kind != token.RParen {
+			return 0, ts, false
+		}
+		return v, rest[1:], true
+	case token.Minus:
+		v, rest, ok := foldFactor(ts[1:])
+		if !ok {
+			return 0, ts, false
+		}
+		return -v, rest, true
+	case token.Plus:
+		return foldFactor(ts[1:])
+	case token.Tilde:
+		v, rest, ok := foldFactor(ts[1:])
+		if !ok {
+			return 0, ts, false
+		}
+		return ^v, rest, true
+	}
+	return 0, ts, false
+}

parser/parser.go

@@ -408,6 +408,18 @@ func parseImmediate(g []token.Token) ast.Immediate {
 			return imm
 		}
 	}
+	// A constant expression introduced by '(' or '~'.  Textual macro
+	// substitution leaves arithmetic such as $(32-shift) and $~63 behind,
+	// and the toolchain evaluates it in place; only shapes the ordinary
+	// paths below cannot read reach the folder, so every existing form
+	// keeps its exact parse.
+	if g[0].Kind == token.LParen || g[0].Kind == token.Tilde {
+		if v, rest, ok := foldExpr(g); ok && len(rest) == 0 {
+			imm.Val = v
+			imm.HasVal = true
+			return imm
+		}
+	}
 	i := 0
 	if g[i].Kind == token.Minus {
 		imm.Neg = true
@@ -459,6 +471,17 @@ func parseAddress(g []token.Token) ast.Address {
 	}
 
 	i := 0
+	// A parenthesised constant expression as the displacement: substituted
+	// macro bodies carry ((index*4)+0)(base) shapes.  As with the signed
+	// number path below, the value is committed only when a base group
+	// follows.
+	if i < len(g) && g[i].Kind == token.LParen {
+		if v, rest, ok := foldExpr(g[i:]); ok && len(rest) > 0 && rest[0].Kind == token.LParen {
+			addr.Offset = v
+			addr.HasOff = true
+			i = len(g) - len(rest)
+		}
+	}
 	// Optional leading displacement before a '(' base group.  A sign pushes
 	// the parenthesis one token further out: -4(DX) has it at i+2.
 	if isSignedNumber(g, i) {

parser/preproc.go

@@ -0,0 +1,475 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// The preprocessor turns #define and #include directives into the token
+// stream the parser really sees, the way the Go toolchain's assembler does:
+// object and parameterised macros expand at the point of use, and an
+// #include splices the named file's lines in place of the directive.  The
+// pass runs only on the assembly path (gasm asm, diff, the corpus audit),
+// where the result is machine code; parsing for the linter, formatter and
+// language server keeps the raw file so their view of #define lines, and
+// therefore their macro-aware behaviour, is unchanged.
+package parser
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"slices"
+	"strconv"
+	"strings"
+	"unicode/utf8"
+
+	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
+	"sourcedock.dev/petrbalvin/gasm-devkit/lexer"
+	"sourcedock.dev/petrbalvin/gasm-devkit/token"
+)
+
+// Options controls the optional preprocessing applied before a file is
+// parsed.  The zero value reproduces Parse exactly.
+type Options struct {
+	// IncludeDirs lists the -I directories searched for #include files,
+	// in order, after the including file's own directory.
+	IncludeDirs []string
+	// Expand enables macro expansion, include splicing and the
+	// statement-separator reading of ';' that the expanded bodies rely on.
+	Expand bool
+}
+
+// ParseWithOptions parses src like Parse, optionally preprocessing it first.
+// The returned file is usable even when errors is non-empty.
+func ParseWithOptions(path, src string, opts Options) (*ast.File, []error) {
+	tokens := lexer.Tokenize(src)
+	var lines [][]token.Token
+	var errs []error
+	if opts.Expand {
+		pp := &preproc{opts: opts, macros: map[string]*macroDef{}}
+		lines = pp.fileLines(path, tokens, token.Position{})
+		errs = pp.errs
+	} else {
+		lines = splitLines(tokens)
+	}
+	p := &state{path: path}
+	p.parse(lines)
+	return p.file, append(errs, p.errs...)
+}
+
+// maxExpansionDepth bounds recursive macro expansion; the toolchain's
+// assembler gives up after 100 nested invocations without producing a token.
+const maxExpansionDepth = 100
+
+// textflagHeader names the one header gasm does not splice: its flag macros
+// (NOSPLIT, RODATA, …) are consumed by name throughout gasm's parser,
+// encoders and linter, and expanding them to their numeric constants would
+// leave every consumer blind to them.
+const textflagHeader = "textflag.h"
+
+// macroDef is one #define.  A nil args slice is an object macro; a non-nil
+// (possibly empty) one is parameterised, the C distinction between
+// "#define A(x)" and "#define A (x)".
+type macroDef struct {
+	name string
+	args []string
+	body []token.Token
+}
+
+// preproc carries the state of one expansion pass: the live macro table, the
+// chain of files currently being read, for cycle detection, and the
+// conditional-inclusion stack of #ifdef regions.
+type preproc struct {
+	opts       Options
+	macros     map[string]*macroDef
+	errs       []error
+	stack      []string // absolute paths of files being read, innermost last
+	ifdefStack []bool   // one entry per open #ifdef/#ifndef, its truth
+}
+
+// enabled reports whether the position being read is inside a live
+// conditional branch.  Directives inside a disabled branch contribute
+// nothing, and its content lines are dropped, exactly as the toolchain's
+// input stack does.
+func (pp *preproc) enabled() bool {
+	return len(pp.ifdefStack) == 0 || pp.ifdefStack[len(pp.ifdefStack)-1]
+}
+
+func (pp *preproc) errorf(pos token.Position, format string, args ...any) {
+	pp.errs = append(pp.errs, Error{Pos: pos, Msg: fmt.Sprintf(format, args...)})
+}
+
+// fileLines tokenizes and preprocesses one file into logical lines.
+// Directive lines are kept (the parser records them for the tooling);
+// #include lines are replaced by the included file's lines.  includePos is
+// the position of the #include that pulled this file in, zero for the
+// top-level file, and only serves cycle diagnostics.
+func (pp *preproc) fileLines(path string, tokens []token.Token, includePos token.Position) [][]token.Token {
+	abs, err := filepath.Abs(path)
+	if err != nil {
+		abs = filepath.Clean(path)
+	}
+	if slices.Contains(pp.stack, abs) {
+		if includePos.IsValid() {
+			pp.errorf(includePos, "#include %q: include cycle (%s is already being read)", path, filepath.Base(path))
+		}
+		return nil
+	}
+	pp.stack = append(pp.stack, abs)
+
+	var out [][]token.Token
+	for _, line := range splitLines(tokens) {
+		if len(line) == 0 {
+			out = append(out, line)
+			continue
+		}
+		if line[0].Kind == token.Hash {
+			out = append(out, pp.directive(line, filepath.Dir(path))...)
+			continue
+		}
+		if !pp.enabled() {
+			continue
+		}
+		out = append(out, splitOnSemicolons(pp.expandTokens(line))...)
+	}
+	pp.stack = pp.stack[:len(pp.stack)-1]
+	if len(pp.stack) == 0 && len(pp.ifdefStack) > 0 {
+		// The stack is per-input, shared across includes, so only the
+		// top-level file's end can decide the input was left unclosed.
+		pp.errorf(token.Position{Line: 1, Column: 1}, "unclosed #ifdef or #ifndef")
+	}
+	return out
+}
+
+// directive processes one '#' line and returns the lines to keep in the
+// stream: every directive line is kept as-is for the parser (which records
+// it), except #include, which is replaced by the spliced content.
+// Conditionals are tracked on every line; every other directive is inert
+// inside a disabled branch.
+func (pp *preproc) directive(line []token.Token, dir string) [][]token.Token {
+	if len(line) < 2 || line[1].Kind != token.Ident {
+		return [][]token.Token{line}
+	}
+	switch line[1].Text {
+	case "ifdef", "ifndef":
+		pp.ifdef(line, line[1].Text == "ifndef")
+	case "else":
+		pp.elseBranch(line)
+	case "endif":
+		pp.endif(line)
+	case "define":
+		if pp.enabled() {
+			pp.define(line)
+		}
+	case "undef":
+		if pp.enabled() {
+			pp.undef(line)
+		}
+	case "include":
+		if pp.enabled() {
+			return pp.include(line, dir)
+		}
+	default:
+		// #line and unknown directives are recorded but not interpreted:
+		// conservative support keeps the parser's view intact and files
+		// using them fail on their content, not silently.
+	}
+	return [][]token.Token{line}
+}
+
+// ifdef handles "#ifdef NAME" and "#ifndef NAME", pushing the branch's truth
+// onto the conditional stack.  A branch opened inside a disabled region is
+// itself disabled, however the name resolves.
+func (pp *preproc) ifdef(line []token.Token, inverted bool) {
+	truth := false
+	if len(line) >= 3 && line[2].Kind == token.Ident {
+		_, defined := pp.macros[line[2].Text]
+		truth = defined != inverted
+	} else {
+		pp.errorf(line[0].Pos, "expected identifier after #%s", line[1].Text)
+	}
+	if !pp.enabled() {
+		truth = false
+	}
+	pp.ifdefStack = append(pp.ifdefStack, truth)
+}
+
+// elseBranch flips the innermost conditional's truth, but only when the
+// region enclosing it is itself live: the toolchain keeps outer overrides.
+func (pp *preproc) elseBranch(line []token.Token) {
+	if len(pp.ifdefStack) == 0 {
+		pp.errorf(line[0].Pos, "unmatched #else")
+		return
+	}
+	if len(pp.ifdefStack) == 1 || pp.ifdefStack[len(pp.ifdefStack)-2] {
+		pp.ifdefStack[len(pp.ifdefStack)-1] = !pp.ifdefStack[len(pp.ifdefStack)-1]
+	}
+}
+
+// endif closes the innermost conditional.
+func (pp *preproc) endif(line []token.Token) {
+	if len(pp.ifdefStack) == 0 {
+		pp.errorf(line[0].Pos, "unmatched #endif")
+		return
+	}
+	pp.ifdefStack = pp.ifdefStack[:len(pp.ifdefStack)-1]
+}
+
+// define parses "#define NAME[(formals)] body" into the macro table.  The
+// body runs to the end of the logical line (the lexer has already spliced
+// backslash continuations) and stops at a comment, which never expands.
+func (pp *preproc) define(line []token.Token) {
+	if len(line) < 3 || line[2].Kind != token.Ident {
+		return
+	}
+	name := line[2]
+	args := []string(nil)
+	body := line[3:]
+	// The definition is parameterised only when '(' follows the name
+	// directly; the toolchain separates "#define A(x)" from
+	// "#define A (x)" by adjacency, and so does the column check here.
+	if len(body) > 0 && body[0].Kind == token.LParen &&
+		body[0].Pos.Column == name.Pos.Column+utf8.RuneCountInString(name.Text) {
+		args = []string{}
+		i := 1
+		for i < len(body) && body[i].Kind != token.RParen {
+			if body[i].Kind == token.Ident {
+				args = append(args, body[i].Text)
+			}
+			i++
+		}
+		if i < len(body) {
+			body = body[i+1:]
+		} else {
+			body = nil
+		}
+	}
+	if i := slices.IndexFunc(body, func(t token.Token) bool { return t.Kind == token.Comment }); i >= 0 {
+		body = body[:i]
+	}
+	if _, exists := pp.macros[name.Text]; exists {
+		// The toolchain refuses redefinition, so a file the oracle accepts
+		// never redefines; failing here keeps that contract visible.
+		pp.errorf(name.Pos, "redefinition of macro %s", name.Text)
+	}
+	pp.macros[name.Text] = &macroDef{name: name.Text, args: args, body: pp.bodyWithBreaks(body)}
+
+}
+
+// bodyWithBreaks records the statement boundaries the continuations carry.
+// The lexer splices backslash-continued lines into one logical line, but the
+// toolchain keeps the newline as a token in the stored body, which is how a
+// multi-instruction body without semicolons (the arm64 style) still splits
+// into statements on expansion.  A line change inside the logical line is
+// exactly a continuation, so the boundary is restored from the positions.
+func (pp *preproc) bodyWithBreaks(body []token.Token) []token.Token {
+	out := make([]token.Token, 0, len(body))
+	for i, t := range body {
+		if i > 0 && t.Pos.Line != body[i-1].Pos.Line {
+			out = append(out, token.Token{Kind: token.Newline, Text: "\n", Pos: t.Pos, End: t.Pos})
+		}
+		out = append(out, t)
+	}
+	return out
+}
+
+// undef handles "#undef NAME", which the toolchain honours and requires to
+// name a defined macro.
+func (pp *preproc) undef(line []token.Token) {
+	if len(line) < 3 || line[2].Kind != token.Ident {
+		return
+	}
+	if _, ok := pp.macros[line[2].Text]; !ok {
+		pp.errorf(line[2].Pos, "#undef for undefined macro %s", line[2].Text)
+		return
+	}
+	delete(pp.macros, line[2].Text)
+}
+
+// include resolves and splices "#include \"file\"".  A header that cannot be
+// read keeps the directive line in the stream, with a diagnostic.
+func (pp *preproc) include(line []token.Token, dir string) [][]token.Token {
+	if len(line) < 3 || line[2].Kind != token.String {
+		return [][]token.Token{line}
+	}
+	header := line[2]
+	name, err := strconv.Unquote(header.Text)
+	if err != nil {
+		pp.errorf(header.Pos, "unquoting include file name: %v", err)
+		return [][]token.Token{line}
+	}
+	if filepath.Base(name) == textflagHeader {
+		// Flag macros are handled natively (see textflagHeader); the
+		// directive stays so tools still see the include.
+		return [][]token.Token{line}
+	}
+	resolved, ok := pp.resolve(name, dir)
+	if !ok {
+		searched := append([]string{dir}, pp.opts.IncludeDirs...)
+		pp.errorf(header.Pos, "#include %q: file not found (searched %s)", name, strings.Join(searched, ", "))
+		return [][]token.Token{line}
+	}
+	src, err := os.ReadFile(resolved)
+	if err != nil {
+		pp.errorf(header.Pos, "#include %q: %v", name, err)
+		return [][]token.Token{line}
+	}
+	return pp.fileLines(resolved, lexer.Tokenize(string(src)), header.Pos)
+}
+
+// resolve looks an include name up the way the toolchain does: as written
+// (relative to the working directory), then relative to the including
+// file's directory, then in each -I directory in order.
+func (pp *preproc) resolve(name, dir string) (string, bool) {
+	candidates := []string{name}
+	if !filepath.IsAbs(name) {
+		candidates = append(candidates, filepath.Join(dir, name))
+		for _, d := range pp.opts.IncludeDirs {
+			candidates = append(candidates, filepath.Join(d, name))
+		}
+	}
+	for _, c := range candidates {
+		if st, err := os.Stat(c); err == nil && !st.IsDir() {
+			return c, true
+		}
+	}
+	return "", false
+}
+
+// expandTokens expands every macro invocation in a token sequence,
+// recursively, with a depth guard.  A body is spliced into the sequence in
+// place and rescanned, the way the toolchain's input stack re-reads pushed
+// tokens: an object macro may name a parameterised one, and the argument
+// list of the expansion may then come from the tokens that follow.
+func (pp *preproc) expandTokens(in []token.Token) []token.Token {
+	s := in
+	i := 0
+	consecutive := 0
+	for i < len(s) {
+		t := s[i]
+		if t.Kind != token.Ident {
+			i++
+			consecutive = 0
+			continue
+		}
+		def := pp.macros[t.Text]
+		if def == nil {
+			i++
+			consecutive = 0
+			continue
+		}
+		// The guard mirrors the toolchain's: 100 nested invocations in a
+		// row without a plain token between them means recursion.
+		consecutive++
+		if consecutive > maxExpansionDepth {
+			pp.errorf(t.Pos, "recursive macro invocation (deeper than %d levels)", maxExpansionDepth)
+			return nil
+		}
+		if def.args == nil {
+			s = append(s[:i], append(restamp(def.body, t.Pos), s[i+1:]...)...)
+			continue
+		}
+		// A parameterised macro invoked without its parentheses stands
+		// unexpanded, naming itself, as in the toolchain.
+		if i+1 >= len(s) || s[i+1].Kind != token.LParen {
+			i++
+			consecutive = 0
+			continue
+		}
+		args, next := pp.collectArgs(s, i+1, t)
+		if args == nil {
+			return nil
+		}
+		// A zero-argument macro may be invoked as NAME().
+		if len(def.args) == 0 && len(args) == 1 && len(args[0]) == 0 {
+			args = nil
+		}
+		if len(args) != len(def.args) {
+			pp.errorf(t.Pos, "wrong arg count for macro %s: got %d, want %d", t.Text, len(args), len(def.args))
+			i = next
+			consecutive = 0
+			continue
+		}
+		sub := make([]token.Token, 0, len(def.body))
+		for _, bt := range def.body {
+			if bt.Kind == token.Ident {
+				if k := slices.Index(def.args, bt.Text); k >= 0 {
+					sub = append(sub, restamp(args[k], t.Pos)...)
+					continue
+				}
+			}
+			sub = append(sub, bt)
+		}
+		s = append(s[:i], append(sub, s[next:]...)...)
+	}
+	return s
+}
+
+// collectArgs reads the actual argument tokens of an invocation; the opening
+// parenthesis is at start.  Commas separate arguments except inside nested
+// parentheses.  A nil result means the list was unterminated, which is a
+// diagnostic.
+func (pp *preproc) collectArgs(in []token.Token, start int, name token.Token) ([][]token.Token, int) {
+	var args [][]token.Token
+	var cur []token.Token
+	nesting := 0
+	for i := start + 1; i < len(in); i++ {
+		t := in[i]
+		switch t.Kind {
+		case token.LParen:
+			nesting++
+			cur = append(cur, t)
+		case token.RParen:
+			if nesting == 0 {
+				return append(args, cur), i + 1
+			}
+			nesting--
+			cur = append(cur, t)
+		case token.Comma:
+			if nesting == 0 {
+				args = append(args, cur)
+				cur = nil
+				continue
+			}
+			cur = append(cur, t)
+		case token.Comment:
+			pp.errorf(name.Pos, "unterminated arg list invoking macro %s", name.Text)
+			return nil, i
+		default:
+			cur = append(cur, t)
+		}
+	}
+	pp.errorf(name.Pos, "unterminated arg list invoking macro %s", name.Text)
+	return nil, len(in)
+}
+
+// restamp copies body tokens to the invocation's position, so diagnostics
+// and the line table point where the macro was used, as the toolchain's
+// input stack does.
+func restamp(body []token.Token, pos token.Position) []token.Token {
+	out := make([]token.Token, len(body))
+	for i, t := range body {
+		t.Pos, t.End = pos, pos
+		out[i] = t
+	}
+	return out
+}
+
+// splitOnSemicolons breaks a token sequence at ';' statement separators and
+// at the Newline markers that record continuation boundaries inside macro
+// bodies, producing the logical lines the parser expects.  The separators
+// carry no meaning beyond the break, so the pieces are exactly what the same
+// statements on separate lines would produce.
+func splitOnSemicolons(ts []token.Token) [][]token.Token {
+	var out [][]token.Token
+	start := 0
+	for i, t := range ts {
+		if t.Kind == token.Semicolon || t.Kind == token.Newline {
+			if i > start {
+				out = append(out, ts[start:i])
+			}
+			start = i + 1
+		}
+	}
+	if start < len(ts) {
+		out = append(out, ts[start:])
+	}
+	return out
+}

parser/preproc_test.go

@@ -0,0 +1,552 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package parser
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
+)
+
+// expand parses src with preprocessing enabled and returns the first TEXT's
+// body instructions as "MNEMONIC operand|operand" strings, the shape the
+// expansion assertions below compare against.  Runs of spaces are
+// collapsed: Raw renders a token group as its tokens joined with single
+// spaces, so "$(32-7)" arrives as "$ ( 32 - 7 )" and the comparison must
+// not depend on that spelling.
+func expand(t *testing.T, src string) (*ast.File, []string) {
+	t.Helper()
+	f, errs := ParseWithOptions("t_amd64.s", src, Options{Expand: true})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	ts := texts(f)
+	if len(ts) == 0 {
+		t.Fatalf("no TEXT in:\n%s", src)
+	}
+	var got []string
+	for _, s := range ts[0].Body {
+		in, ok := s.(*ast.Instr)
+		if !ok {
+			continue
+		}
+		var ops []string
+		for _, op := range in.Operands {
+			ops = append(ops, op.Raw)
+		}
+		line := in.Mnemonic.Text + " " + strings.Join(ops, ", ")
+		got = append(got, strings.ReplaceAll(line, " ", ""))
+	}
+	return f, got
+}
+
+func wantLines(t *testing.T, got []string, want ...string) {
+	t.Helper()
+	strip := func(lines []string) string {
+		var out []string
+		for _, l := range lines {
+			out = append(out, strings.ReplaceAll(l, " ", ""))
+		}
+		return strings.Join(out, "\n")
+	}
+	if strip(got) != strip(want) {
+		t.Errorf("expanded body:\n  %s\nwant:\n  %s", strings.Join(got, "\n  "), strings.Join(want, "\n  "))
+	}
+}
+
+func TestObjectMacroExpandsAtUse(t *testing.T) {
+	_, got := expand(t, `
+#define REGTMP CX
+#define TWICE ADDQ CX, AX; ADDQ CX, AX
+TEXT ·f(SB), NOSPLIT, $0
+	MOVQ 8(SP), REGTMP
+	TWICE
+	RET
+`)
+	wantLines(t, got,
+		"MOVQ 8(SP), CX",
+		"ADDQ CX, AX",
+		"ADDQ CX, AX",
+		"RET",
+	)
+}
+
+func TestParameterisedMacroSubstitutesArguments(t *testing.T) {
+	f, errs := ParseWithOptions("t_amd64.s", `
+#define ROUND1(a, index, const, shift) \
+	ADDQ $const, a; \
+	MOVW (index*4)(SP), a; \
+	RORQ $(32-shift), a
+TEXT ·f(SB), NOSPLIT, $0
+	ROUND1(AX, 3, 0xd76aa478, 7)
+	RET
+`, Options{Expand: true})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	body := texts(f)[0].Body
+	add := body[0].(*ast.Instr)
+	if add.Mnemonic.Text != "ADDQ" || !add.Operands[0].Imm.HasVal ||
+		add.Operands[0].Imm.Val != 0xd76aa478 || add.Operands[1].Addr.Sym == nil ||
+		add.Operands[1].Addr.Sym.Name != "AX" {
+		t.Errorf("ADDQ operands substituted wrong: %+v %+v", add.Operands[0].Imm, add.Operands[1].Addr)
+	}
+	mov := body[1].(*ast.Instr)
+	if addr := mov.Operands[0].Addr; !addr.HasOff || addr.Offset != 12 {
+		t.Errorf("MOVW offset = %+v, want 12 from 3*4", addr)
+	}
+	ror := body[2].(*ast.Instr)
+	if !ror.Operands[0].Imm.HasVal || ror.Operands[0].Imm.Val != 25 {
+		t.Errorf("RORQ immediate = %+v, want 25 from (32-7)", ror.Operands[0].Imm)
+	}
+}
+
+func TestMacroArgumentsKeepCommasInParens(t *testing.T) {
+	// An argument may itself be an unparenthesised expression: the tokens
+	// substitute verbatim and the parser folds the result, as the
+	// toolchain's parser does.
+	f, errs := ParseWithOptions("t_amd64.s", `
+#define LOAD(dst, off) MOVQ off(SP), dst
+TEXT ·f(SB), NOSPLIT, $0
+	LOAD(AX, 1*8)
+	RET
+`, Options{Expand: true})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	in := texts(f)[0].Body[0].(*ast.Instr)
+	addr := in.Operands[0].Addr
+	if !addr.HasOff || addr.Offset != 8 {
+		t.Errorf("offset = %+v, want 8", addr)
+	}
+	if sym := in.Operands[1].Addr.Sym; sym == nil || sym.Name != "AX" {
+		t.Errorf("destination = %+v, want AX", in.Operands[1].Addr)
+	}
+}
+
+func TestNestedMacroInvocations(t *testing.T) {
+	// An object macro naming a parameterised one, and a parameterised body
+	// invoking another parameterised macro: the toolchain's input stack
+	// rescans substituted tokens, and so does expansion here.
+	_, got := expand(t, `
+#define DOUBLE(x) ADDQ x, x
+#define TWICE2 DOUBLE
+#define FOUR(a, b) DOUBLE(a); DOUBLE(b)
+TEXT ·f(SB), NOSPLIT, $0
+	TWICE2(AX)
+	FOUR(AX, CX)
+	RET
+`)
+	wantLines(t, got,
+		"ADDQ AX, AX",
+		"ADDQ AX, AX",
+		"ADDQ CX, CX",
+		"RET",
+	)
+}
+
+func TestMultiLineBodySplitsWithoutSemicolons(t *testing.T) {
+	// The arm64 style: backslash-continued lines with no semicolons.  The
+	// continuation newline is a statement boundary, as in the toolchain.
+	_, got := expand(t, `
+#define PAIR \
+	ADDQ AX, AX \
+	MOVQ AX, CX
+TEXT ·f(SB), NOSPLIT, $0
+	PAIR
+	RET
+`)
+	wantLines(t, got,
+		"ADDQ AX, AX",
+		"MOVQ AX, CX",
+		"RET",
+	)
+}
+
+func TestZeroArgumentMacro(t *testing.T) {
+	_, got := expand(t, `
+#define BARRIER()
+TEXT ·f(SB), NOSPLIT, $0
+	BARRIER()
+	RET
+`)
+	wantLines(t, got, "RET")
+}
+
+func TestParameterisedWithoutParensStandsAsName(t *testing.T) {
+	// A parameterised macro invoked without its parentheses names itself,
+	// which the parser then reports as an unknown instruction rather than
+	// silently expanding nothing.
+	f, errs := ParseWithOptions("t_amd64.s", `
+#define M(x) ADDQ x, x
+TEXT ·f(SB), NOSPLIT, $0
+	M
+	RET
+`, Options{Expand: true})
+	if len(errs) != 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	fn := texts(f)[0]
+	if len(fn.Body) == 0 {
+		t.Fatal("body empty")
+	}
+	in, ok := fn.Body[0].(*ast.Instr)
+	if !ok || in.Mnemonic.Text != "M" {
+		t.Fatalf("bare parameterised macro did not stand as its name: %+v", fn.Body[0])
+	}
+}
+
+func TestDefinitionScoping(t *testing.T) {
+	// A definition applies from its point onward: the use before the
+	// #define stays untouched.
+	_, got := expand(t, `
+TEXT ·f(SB), NOSPLIT, $0
+	SPECIAL
+#define SPECIAL ADDQ AX, AX
+	SPECIAL
+	RET
+`)
+	wantLines(t, got,
+		"SPECIAL",
+		"ADDQ AX, AX",
+		"RET",
+	)
+}
+
+func TestUndefRemovesMacro(t *testing.T) {
+	_, got := expand(t, `
+#define TEMP AX
+TEXT ·f(SB), NOSPLIT, $0
+	TEMP
+#undef TEMP
+	TEMP
+	RET
+`)
+	wantLines(t, got,
+		"AX",
+		"TEMP",
+		"RET",
+	)
+}
+
+func TestUndefUndefinedMacroIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#undef NOSUCH\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "undefined macro NOSUCH") {
+		t.Fatalf("#undef of an undefined macro: got %v, want an error naming it", errs)
+	}
+}
+
+func TestRedefinitionIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#define A X\n#define A Y\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "redefinition of macro A") {
+		t.Fatalf("redefinition: got %v, want an error", errs)
+	}
+}
+
+func TestRecursiveMacroIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#define A B\n#define B A\nTEXT ·f(SB), NOSPLIT, $0\n\tA\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "recursive macro invocation") {
+		t.Fatalf("recursion: got %v, want a recursive-macro error, not a hang", errs)
+	}
+}
+
+func TestWrongArgumentCountIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#define M(a, b) ADDQ a, b\nTEXT ·f(SB), NOSPLIT, $0\n\tM(AX)\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "wrong arg count for macro M") {
+		t.Fatalf("arg count: got %v, want an error", errs)
+	}
+}
+
+func TestConditionalsSelectOneBranch(t *testing.T) {
+	_, got := expand(t, `
+#define MODE2
+TEXT ·f(SB), NOSPLIT, $0
+#ifdef MODE2
+	ADDQ AX, AX
+#else
+	SUBQ AX, AX
+#endif
+#ifndef MODE2
+	SUBQ CX, CX
+#else
+	ADDQ CX, CX
+#endif
+	RET
+`)
+	wantLines(t, got,
+		"ADDQ AX, AX",
+		"ADDQ CX, CX",
+		"RET",
+	)
+}
+
+func TestConditionalsHideDefinitionsAndIncludes(t *testing.T) {
+	// A definition inside a disabled branch must not exist, and an
+	// unresolvable include there must not be followed.
+	_, got := expand(t, `
+TEXT ·f(SB), NOSPLIT, $0
+#ifdef NOTDEFINED
+#define HIDEN ADDQ AX, AX
+#include "nowhere.h"
+#endif
+	HIDEN
+	RET
+`)
+	wantLines(t, got, "HIDEN", "RET")
+}
+
+func TestUnclosedConditionalIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#ifdef X\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "unclosed #ifdef") {
+		t.Fatalf("unclosed conditional: got %v, want an error", errs)
+	}
+}
+
+func TestUnmatchedConditionalDelimitersAreErrors(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#endif\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "unmatched #endif") {
+		t.Fatalf("unmatched #endif: got %v, want an error", errs)
+	}
+	_, errs = ParseWithOptions("t_amd64.s", "#else\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n", Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "unmatched #else") {
+		t.Fatalf("unmatched #else: got %v, want an error", errs)
+	}
+}
+
+// includeTree writes a directory of include files and returns its path.
+func includeTree(t *testing.T, files map[string]string) string {
+	t.Helper()
+	dir := t.TempDir()
+	for name, content := range files {
+		path := filepath.Join(dir, name)
+		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+			t.Fatal(err)
+		}
+		if err := os.WriteFile(path, []byte(content), 0o644); err != nil {
+			t.Fatal(err)
+		}
+	}
+	return dir
+}
+
+func TestIncludeSplicesAndDefinesAreShared(t *testing.T) {
+	dir := includeTree(t, map[string]string{
+		"consts.h": "#define KONST $42\n",
+	})
+	f, errs := ParseWithOptions("t_amd64.s", `
+#include "consts.h"
+TEXT ·f(SB), NOSPLIT, $0
+	MOVQ KONST, AX
+	RET
+`, Options{Expand: true, IncludeDirs: []string{dir}})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	in := texts(f)[0].Body[0].(*ast.Instr)
+	if in.Mnemonic.Text != "MOVQ" || strings.ReplaceAll(in.Operands[0].Raw, " ", "") != "$42" {
+		t.Fatalf("include splicing failed: %+v", in)
+	}
+}
+
+func TestIncludeResolutionOrder(t *testing.T) {
+	// The including file's directory wins over the -I list, and the -I list
+	// is searched in order.
+	src := includeTree(t, map[string]string{
+		"inc/main.s":     "#include \"which.h\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n",
+		"inc/which.h":    "#define WHO ONE\n",
+		"first/which.h":  "#define WHO TWO\n",
+		"second/which.h": "#define WHO THREE\n",
+	})
+	main := filepath.Join(src, "inc", "main.s")
+	body, err := os.ReadFile(main)
+	if err != nil {
+		t.Fatal(err)
+	}
+	// The header exists in the including file's directory and in two -I
+	// directories; the source-directory copy must win.
+	f, errs := ParseWithOptions(main, string(body), Options{Expand: true, IncludeDirs: []string{
+		filepath.Join(src, "first"), filepath.Join(src, "second"),
+	}})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	found := false
+	for _, d := range f.Decls {
+		if pp, ok := d.(*ast.Preproc); ok && strings.Contains(pp.Raw, "define WHO ONE") {
+			found = true
+		}
+	}
+	if !found {
+		t.Error("the including file's directory did not win include resolution")
+	}
+}
+
+func TestIncludeSearchesIncludeDirsInOrder(t *testing.T) {
+	src := includeTree(t, map[string]string{
+		"inc/main.s":     "#include \"which.h\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n",
+		"first/which.h":  "#define WHO TWO\n",
+		"second/which.h": "#define WHO THREE\n",
+	})
+	main := filepath.Join(src, "inc", "main.s")
+	body, err := os.ReadFile(main)
+	if err != nil {
+		t.Fatal(err)
+	}
+	f, errs := ParseWithOptions(main, string(body), Options{Expand: true, IncludeDirs: []string{
+		filepath.Join(src, "first"), filepath.Join(src, "second"),
+	}})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	for _, d := range f.Decls {
+		if pp, ok := d.(*ast.Preproc); ok && strings.Contains(pp.Raw, "define WHO THREE") {
+			t.Error("the second -I directory was searched before the first")
+		}
+	}
+}
+
+func TestIncludeCycleIsDetected(t *testing.T) {
+	src := includeTree(t, map[string]string{
+		"a.s": "#include \"b.s\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n",
+		"b.s": "#include \"a.s\"\n",
+	})
+	_, errs := ParseWithOptions(filepath.Join(src, "a.s"), "#include \"b.s\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n",
+		Options{Expand: true})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), "include cycle") {
+		t.Fatalf("include cycle: got %v, want a cycle diagnostic, not a hang", errs)
+	}
+}
+
+func TestUnresolvableIncludeIsAnError(t *testing.T) {
+	_, errs := ParseWithOptions("t_amd64.s", "#include \"nothere.h\"\nTEXT ·f(SB), NOSPLIT, $0\n\tRET\n",
+		Options{Expand: true, IncludeDirs: []string{t.TempDir()}})
+	if len(errs) == 0 || !strings.Contains(errs[0].Error(), `#include "nothere.h"`) {
+		t.Fatalf("missing include: got %v, want a clear diagnostic", errs)
+	}
+}
+
+func TestTextflagHeaderIsNeverSpliced(t *testing.T) {
+	// textflag.h resolves nowhere here, yet the file must parse: the flag
+	// names are consumed natively and the include stays in the tree.
+	f, errs := ParseWithOptions("t_amd64.s", `
+#include "textflag.h"
+TEXT ·f(SB), NOSPLIT, $0
+	RET
+`, Options{Expand: true})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	hasInclude := false
+	for _, d := range f.Decls {
+		if _, ok := d.(*ast.Include); ok {
+			hasInclude = true
+		}
+	}
+	if !hasInclude {
+		t.Error("textflag.h include was dropped from the tree")
+	}
+}
+
+func TestSemicolonSplitsRawLinesToo(t *testing.T) {
+	_, got := expand(t, `
+TEXT ·f(SB), NOSPLIT, $0
+	BYTE $0x0f; BYTE $0x1f
+	RET
+`)
+	wantLines(t, got, "BYTE $0x0f", "BYTE $0x1f", "RET")
+}
+
+func TestParseUnchangedWithoutExpand(t *testing.T) {
+	// Without Expand the preprocessor must not exist: a macro invocation
+	// stays an unexpanded instruction line and ';' keeps the old parse.
+	f, errs := Parse("t_amd64.s", `
+#define TWICE ADDQ AX, AX
+TEXT ·f(SB), NOSPLIT, $0
+	TWICE
+	BYTE $0x0f; BYTE $0x1f
+	RET
+`)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	fn := texts(f)[0]
+	var mnemonics []string
+	for _, s := range fn.Body {
+		if in, ok := s.(*ast.Instr); ok {
+			mnemonics = append(mnemonics, in.Mnemonic.Text)
+		}
+	}
+	if strings.Join(mnemonics, " ") != "TWICE BYTE RET" {
+		t.Errorf("non-expanding parse changed: %v", mnemonics)
+	}
+}
+
+func TestConstantExpressionFolding(t *testing.T) {
+	// The shapes substituted macro bodies leave behind: parenthesised
+	// arithmetic in immediates and displacements, tilde complements.  The
+	// assertions read the semantic fields; Raw keeps the operand's tokens
+	// in the canonicalised rendering, not the folded values.
+	f, errs := ParseWithOptions("t_amd64.s", `
+TEXT ·f(SB), NOSPLIT, $0
+	RORQ $(32-7), AX
+	ANDQ $~63, AX
+	MOVQ ((2*4)+0)(SP), AX
+	MOVQ $((1<<3)|(1<<1)), AX
+	RET
+`, Options{Expand: true})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	body := texts(f)[0].Body
+	ror := body[0].(*ast.Instr)
+	if !ror.Operands[0].Imm.HasVal || ror.Operands[0].Imm.Val != 25 {
+		t.Errorf("RORQ immediate = %+v, want 25", ror.Operands[0].Imm)
+	}
+	and := body[1].(*ast.Instr)
+	if !and.Operands[0].Imm.HasVal || and.Operands[0].Imm.Val != -64 {
+		t.Errorf("ANDQ immediate = %+v, want -64", and.Operands[0].Imm)
+	}
+	mov := body[2].(*ast.Instr)
+	addr := mov.Operands[0].Addr
+	if !addr.HasOff || addr.Offset != 8 || addr.Base != "SP" {
+		t.Errorf("MOVQ address = %+v, want 8(SP)", addr)
+	}
+	mov2 := body[3].(*ast.Instr)
+	if !mov2.Operands[0].Imm.HasVal || mov2.Operands[0].Imm.Val != 10 {
+		t.Errorf("MOVQ immediate = %+v, want 10", mov2.Operands[0].Imm)
+	}
+}
+
+func TestConstantExpressionFoldsWithoutExpand(t *testing.T) {
+	// Folding is a parser capability, not a preprocessing one: a
+	// hand-written $(32-7) folds the same way with expansion off.
+	f, errs := ParseWithOptions("t_amd64.s", "TEXT ·f(SB), NOSPLIT, $0\n\tRORQ $(32-7), AX\n\tRET\n", Options{})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	in := texts(f)[0].Body[0].(*ast.Instr)
+	if !in.Operands[0].Imm.HasVal || in.Operands[0].Imm.Val != 25 {
+		t.Errorf("Imm = %+v, want 25", in.Operands[0].Imm)
+	}
+}
+
+func TestNotAnExpressionFallsBack(t *testing.T) {
+	// Symbol immediates and floats must keep their ordinary parse.
+	f, errs := ParseWithOptions("t_amd64.s", "TEXT ·f(SB), NOSPLIT, $0\n\tMOVQ $1.5, AX\n\tMOVQ $·sym(SB), AX\n\tRET\n", Options{})
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	fn := texts(f)[0]
+	mov1 := fn.Body[0].(*ast.Instr)
+	if mov1.Operands[0].Imm.HasVal || mov1.Operands[0].Imm.Float != "1.5" {
+		t.Errorf("float immediate parsed as %+v", mov1.Operands[0].Imm)
+	}
+	mov2 := fn.Body[1].(*ast.Instr)
+	if mov2.Operands[0].Imm.Sym == nil {
+		t.Errorf("symbol immediate parsed as %+v", mov2.Operands[0].Imm)
+	}
+}

token/token.go

@@ -43,6 +43,13 @@ const (
 	At     // @
 	Hash   // #
 	Pipe   // |
+
+	// Semicolon separates statements on one line (a Plan 9 statement
+	// terminator); Ampersand and Tilde are the expression operators & and ~
+	// of constant expressions.  All three appear mostly inside macro bodies.
+	Semicolon // ;
+	Ampersand // &
+	Tilde     // ~
 )
 
 var kindNames = map[Kind]string{
@@ -71,6 +78,10 @@ var kindNames = map[Kind]string{
 	At:      "@",
 	Hash:    "#",
 	Pipe:    "|",
+
+	Semicolon: ";",
+	Ampersand: "&",
+	Tilde:     "~",
 }
 
 // String returns a human-readable name for the kind.