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

package asm

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

	"sourcedock.dev/petrbalvin/gasm-sdk/parser"
)

// arm64AcceptedErrorShapes lists the toolchain's arm64error.s spellings gasm
// still accepts, each an acceptance superset with a known shape.  The list
// only shrinks: every tightening of the encoder moves spellings out of it,
// and a spelling reappearing here means a regression.
var arm64AcceptedErrorShapes = []string{
	// VLD1/VST1 post-index shapes: the register post-index without the .P
	// spelling, the .P immediate against the aggregate register size, the
	// scaled register increment and the replicating register count.
	"VLD1 (R8)(R13), [V2.B16]",
	"VST1 [V1.B16], (R8)(R13)",
	"VST1.P [V4.S4,V5.S4], 48(R1)",
	"VST1.P [V4.S4], 8(R1)",
	"VLD1.P 32(R1), [V8.S4, V9.S4, V10.S4]",
	"VLD1.P 48(R1), [V7.S4, V8.S4, V9.S4, V10.S4]",
	"VLD1.P (R8)(R9<<2), [V2.B16]",
	"VST1.P [V1.B16], (R8)(R9<<1)",
	"VLD3R.P 24(R15), [V15.H4,V16.H4,V17.H4]",
	// REGTMP (R27) as an explicit operand the toolchain refuses, the pair
	// split paths included.
	"ADD $0x1234567, R27, R3",
	"ADD $0x3fffffffc000, R27, R5",
	"AND $0x22220000, R27, R4",
	"ANDW $0x6006000060060, R27, R5",
	"STP (R3, R4), 0x1234567(R27)",
	"LDP 0x1234567(R27), (R3, R4)",
	"STP (R26, R27), 700(R2)",
	// TLBI operand arity and the range-prefetch operand shapes.
	"TLBI VMALLE1IS, R0",
	"TLBI ALLE3OS, ZR",
	"TLBI VAE1IS",
	"TLBI RVALE3",
	"RPRFM (R1), RSP, PLDKEEP",
	// The GP register pairs on the FP mnemonics, the other way round.
	"LDP (R0), (F0, F1)",
	"STP (F2, F3), (R0)",
	// FCVTL exists for the S to D pair alone.
	"VFCVTL V1.H4, V2.S4",
}

// TestArm64ToolchainErrorParity walks the toolchain's arm64error.s (Go
// 1.27, arm64) and requires gasm to reject every case the toolchain rejects,
// the documented acceptance supersets above excepted.  A live Go toolchain
// is needed for the source file; the test skips without one or in -short.
func TestArm64ToolchainErrorParity(t *testing.T) {
	if testing.Short() {
		t.Skip("live arm64error.s corpus: skipped in -short mode")
	}
	goroot := os.Getenv("GOROOT")
	if goroot == "" {
		t.Skip("no GOROOT")
	}
	path := filepath.Join(goroot, "src", "cmd", "asm", "internal", "asm", "testdata", "arm64error.s")
	data, err := os.ReadFile(path)
	if err != nil {
		t.Skip(err)
	}
	allowed := map[string]bool{}
	for _, s := range arm64AcceptedErrorShapes {
		allowed[s] = true
	}
	for raw := range strings.SplitSeq(string(data), "\n") {
		line := strings.TrimSpace(raw)
		if line == "" || strings.HasPrefix(line, "//") || strings.HasPrefix(line, "TEXT") || !strings.Contains(line, "ERROR") {
			continue
		}
		body := line
		if i := strings.Index(body, "//"); i >= 0 {
			body = strings.TrimSpace(body[:i])
		}
		body = strings.ReplaceAll(body, "\t", " ")
		body = strings.Join(strings.Fields(body), " ")
		// Label-relative and non-operand lines need their function context.
		if strings.Contains(body, "(PC)") || strings.Contains(body, "(SB)") || strings.Contains(body, "PCALIGN") ||
			strings.HasPrefix(body, "RET") || strings.HasPrefix(body, "NOP") || strings.HasPrefix(body, "BRK") ||
			strings.Contains(body, "again") || strings.Contains(body, "next") || strings.Contains(body, "loop") {
			continue
		}
		src := "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n\t" + body + "\n\tRET\n"
		f, perr := parser.Parse("errorparity.s", src)
		if len(perr) > 0 {
			continue // the parser already rejects the spelling
		}
		if _, aerr := AssembleFileARM64(f); aerr == nil && !allowed[body] {
			t.Errorf("gasm accepts what the toolchain rejects: %s", body)
		}
	}
}