gasm-sdk/format/format_test.go

// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: BSD-3-Clause

package format

import (
	"os"
	"path/filepath"
	"strings"
	"testing"

	"sourcedock.dev/petrbalvin/gasm-devkit/lexer"
	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
	"sourcedock.dev/petrbalvin/gasm-devkit/token"
)

func TestGolden(t *testing.T) {
	in := "#include \"textflag.h\"\n" +
		"\n" +
		"TEXT ·f(SB), NOSPLIT, $0\n" +
		"MOVQ swin_base+0(FP), SI\n" +
		"LEAQ (SI)(BX*4), R9\n" +
		"ANDQ $-8, R10\n" +
		"VFMADD231PD Z14, Z12, Z10\n" +
		"RET\n"

	want := "#include \"textflag.h\"\n" +
		"\n" +
		"TEXT ·f(SB), NOSPLIT, $0\n" +
		"\tMOVQ        swin_base+0(FP), SI\n" +
		"\tLEAQ        (SI)(BX*4), R9\n" +
		"\tANDQ        $-8, R10\n" +
		"\tVFMADD231PD Z14, Z12, Z10\n" +
		"\tRET\n"

	got := Source("f_amd64.s", in)
	if got != want {
		t.Fatalf("formatting mismatch:\n--- got ---\n%q\n--- want ---\n%q", got, want)
	}
}

// TestDocCommentIndent checks that a doc comment preceding a TEXT directive
// sits at column 0 even when another function (ending in RET) precedes it —
// the RET must terminate the previous body for indentation purposes.
func TestDocCommentIndent(t *testing.T) {
	in := "#include \"textflag.h\"\n" +
		"\n" +
		"// func first()\n" +
		"TEXT ·first(SB), NOSPLIT, $0\n" +
		"XORQ AX, AX\n" +
		"RET\n" +
		"\n" +
		"// func second()\n" +
		"TEXT ·second(SB), NOSPLIT, $0\n" +
		"RET\n"

	want := "#include \"textflag.h\"\n" +
		"\n" +
		"// func first()\n" +
		"TEXT ·first(SB), NOSPLIT, $0\n" +
		"\tXORQ AX, AX\n" +
		"\tRET\n" +
		"\n" +
		"// func second()\n" +
		"TEXT ·second(SB), NOSPLIT, $0\n" +
		"\tRET\n"

	got := Source("d_amd64.s", in)
	if got != want {
		t.Fatalf("formatting mismatch:\n--- got ---\n%q\n--- want ---\n%q", got, want)
	}
	// Body comments stay indented.
	body := "#include \"textflag.h\"\nTEXT ·f(SB), NOSPLIT, $0\n// inside the body\nXORQ AX, AX\nRET\n"
	gotBody := Source("b_amd64.s", body)
	if !strings.Contains(gotBody, "\t// inside the body\n") {
		t.Fatalf("body comment must stay indented:\n%q", gotBody)
	}
}

// TestBlankLines checks the blank-line canonicalisation: exactly one blank
// line before a new block (a label, or TEXT/GLOBL), runs of blanks collapsed
// to one, and no blank forced after TEXT, between stacked labels, or at the
// top of the file.  Leading comments belong to the block they precede.
func TestBlankLines(t *testing.T) {
	in := "#include \"textflag.h\"\n" +
		"TEXT ·f(SB), NOSPLIT, $0\n" +
		"first:\n" + // first label: no blank after TEXT
		"XORQ AX, AX\n" +
		"JMP next\n" + // unlabeled glue: fmt inserts a blank before next:
		"next:\n" +
		"stacked:\n" + // stacked labels share an address: no blank between
		"INCQ AX\n" +
		"\n" +
		"\n" + // two blanks collapse to one
		"// separated block\n" + // comment belongs to the label below
		"later:\n" +
		"RET\n" +
		"// func g()\n" + // doc comment: blank goes before it
		"TEXT ·g(SB), NOSPLIT, $0\n" +
		"RET\n" +
		"GLOBL ·mask(SB), RODATA, $8\n" + // blank before GLOBL…
		"DATA ·mask+0(SB)/4, $1\n" + // …but not before DATA
		"\n" +
		"\n" +
		"\n" // trailing blanks dropped

	want := "#include \"textflag.h\"\n" +
		"\n" +
		"TEXT ·f(SB), NOSPLIT, $0\n" +
		"first:\n" +
		"\tXORQ AX, AX\n" +
		"\tJMP  next\n" +
		"\n" +
		"next:\n" +
		"stacked:\n" +
		"\tINCQ AX\n" +
		"\n" +
		"\t// separated block\n" + // body comment before a label stays indented
		"later:\n" +
		"\tRET\n" +
		"\n" +
		"// func g()\n" +
		"TEXT ·g(SB), NOSPLIT, $0\n" +
		"\tRET\n" +
		"\n" +
		"GLOBL ·mask(SB), RODATA, $8\n" +
		"DATA ·mask+0(SB)/4, $1\n"

	got := Source("b_amd64.s", in)
	if got != want {
		t.Fatalf("formatting mismatch:\n--- got ---\n%q\n--- want ---\n%q", got, want)
	}
	if again := Source("b_amd64.s", got); again != got {
		t.Fatalf("not idempotent:\n%q", again)
	}
}

func TestOperandSpacing(t *testing.T) {
	cases := map[string]string{
		"4(SI)":           "4(SI)",
		"(SI)(BX*4)":      "(SI)(BX*4)",
		"$-8":             "$-8",
		"$0x80020100":     "$0x80020100",
		"swin_base+0(FP)": "swin_base+0(FP)",
		"mask24<>(SB)":    "mask24<>(SB)",
		"·idx16+0(SB)/4":  "·idx16+0(SB)/4",
	}
	for in, want := range cases {
		toks := lexOperands(in)
		if got := renderOps(toks); got != want {
			t.Errorf("renderOps(%q) = %q, want %q", in, got, want)
		}
	}
}

// lexOperands lexes a single operand string and drops the EOF token.
func lexOperands(s string) []token.Token {
	toks := lexer.Tokenize(s)
	return toks[:len(toks)-1] // drop trailing EOF
}

func TestIdempotent(t *testing.T) {
	src, err := os.ReadFile("../testdata/sample_amd64.s")
	if err != nil {
		t.Fatal(err)
	}
	once := Source("sample_amd64.s", string(src))
	twice := Source("sample_amd64.s", once)
	if once != twice {
		t.Fatal("formatting is not idempotent on the fixture")
	}
}

// TestRoundTrip checks that formatting produces source that still parses
// cleanly, on the fixture and on the real go-flac kernels when present.
func TestRoundTrip(t *testing.T) {
	files := []string{"../testdata/sample_amd64.s"}
	real, _ := filepath.Glob("../../go-libraries/go-*/*.s")
	files = append(files, real...)
	for _, path := range files {
		src, err := os.ReadFile(path)
		if err != nil {
			t.Fatal(err)
		}
		formatted := Source(path, string(src))
		if _, errs := parser.Parse(path, formatted); len(errs) > 0 {
			t.Errorf("formatted %s no longer parses: %v", path, errs)
		}
		if strings.TrimSpace(formatted) == "" {
			t.Errorf("formatted %s is empty", path)
		}
	}
}