textmachine/backend/internal/lang/langpack_test.go

package lang

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

// realRoot is the in-repo langpack root, relative to this package's test cwd (internal/lang/).
const realRoot = "../../configs/langpacks"

// TestLoadResolvesRealZhRu loads the REAL zh→ru pack from disk and pins a spot-check of the moved data
// (the const→file move must be byte-faithful; the full-book parity that pins the exact miner output is
// the stand-gated TestMinerFullBookParity, so this is the CI-runnable anchor). It exercises the real
// disk-loading path end to end.
func TestLoadResolvesRealZhRu(t *testing.T) {
	p, err := Load(realRoot, "zh", "ru")
	if err != nil {
		t.Fatalf("Load(zh,ru): %v", err)
	}
	if p.Pair != "zh-ru" {
		t.Errorf("Pair = %q, want zh-ru", p.Pair)
	}
	// Source morphology spot-check (byte-faithful move).
	if !p.SurnamesSingle['赵'] || !p.SurnamesSingle['方'] {
		t.Error("surnames-single missing 赵/方")
	}
	if p.SurnamesSingle['凝'] {
		t.Error("surnames-single must NOT contain 凝 (discarded — not a surname)")
	}
	if !p.SurnamesCompound["古月"] || !p.SurnamesCompound["欧阳"] {
		t.Error("surnames-compound missing 古月/欧阳")
	}
	if len(p.TitleSuffix) == 0 || p.TitleSuffix[0] != "公子" {
		t.Errorf("title-suffix order not preserved: %v", p.TitleSuffix)
	}
	if !p.TopoSuffix['山'] || !p.Numeral['三'] || !p.GradePrefix['甲'] || !p.AliasParticle['的'] {
		t.Error("rune-set membership missing an expected char (山/三/甲/的)")
	}
	// Pair transliteration spot-check.
	if p.PalladiusInitials["b"] != "б" || p.PalladiusInitials["zh"] != "чж" {
		t.Errorf("palladius initials wrong: b=%q zh=%q", p.PalladiusInitials["b"], p.PalladiusInitials["zh"])
	}
	if p.PalladiusSpecialI["zhi"] != "чжи" {
		t.Errorf("palladius special_i zhi = %q, want чжи", p.PalladiusSpecialI["zhi"])
	}
	if !strings.HasPrefix(p.Version(), packAlgoVersion+"-") {
		t.Errorf("Version() = %q, want %s-<hash>", p.Version(), packAlgoVersion)
	}
}

// TestRoutesByPairToDifferentBytes is the load-bearing generality proof: a SECOND pair, dropped as data
// (no pipeline/ edit, no recompile), routes to DIFFERENT bytes and a DIFFERENT version. Proves "add a
// language = data only" — the pair is a genuine routing key, not a baked-in zh constant.
func TestRoutesByPairToDifferentBytes(t *testing.T) {
	root := t.TempDir()
	writeSyntheticPack(t, root, "xx", "yy")

	real, err := Load(realRoot, "zh", "ru")
	if err != nil {
		t.Fatalf("load real: %v", err)
	}
	synth, err := Load(root, "xx", "yy")
	if err != nil {
		t.Fatalf("load synthetic xx-yy: %v", err)
	}

	// The synthetic pair carries its OWN surnames (not zh's), proving the resolver routes by pair, not
	// to a hardcoded set.
	if !synth.SurnamesSingle['甴'] {
		t.Error("synthetic pack must carry its own surname 甴")
	}
	if synth.SurnamesSingle['赵'] {
		t.Error("synthetic pack must NOT inherit zh's surname 赵 (would mean a baked-in constant)")
	}
	if !real.SurnamesSingle['赵'] || real.SurnamesSingle['甴'] {
		t.Error("real zh pack routing leaked/borrowed synthetic bytes")
	}
	if real.Version() == synth.Version() {
		t.Errorf("different-byte packs must have different versions (real=%s synth=%s)", real.Version(), synth.Version())
	}
}

// TestFailsLoudOnMissingPair pins the fail-loud contract: a pair with no pack directory errors, naming the
// missing file — never a silent empty pack (mirrors the prompt seam's PromptPathFor fail-loud). This is
// the load-time invariant a live consumer relies on (fail before billing).
func TestFailsLoudOnMissingPair(t *testing.T) {
	_, err := Load(realRoot, "ja", "ru")
	if err == nil {
		t.Fatal("Load(ja,ru) must fail loud (no ja langpack), got nil error")
	}
	if !strings.Contains(err.Error(), "ja-ru") {
		t.Errorf("error must name the missing pair ja-ru, got: %v", err)
	}
}

// TestFailsLoudOnEmptyTable pins the "never silently empty" contract: a present-but-empty (comment-only)
// required file is a corrupt pack and must fail loud at load — not parse to an empty set that silently
// disables a miner channel once packs are hand-authored (R1).
func TestFailsLoudOnEmptyTable(t *testing.T) {
	root := t.TempDir()
	writeSyntheticPack(t, root, "xx", "yy")
	// Blank out one required table (keep the file present, drop its content).
	if err := os.WriteFile(filepath.Join(root, "xx", "surnames-single.txt"), []byte("# emptied by a bad edit\n"), 0o644); err != nil {
		t.Fatal(err)
	}
	_, err := Load(root, "xx", "yy")
	if err == nil {
		t.Fatal("an empty required table must fail loud, got nil error")
	}
	if !strings.Contains(err.Error(), "surnames-single") {
		t.Errorf("error must name the empty table, got: %v", err)
	}
}

// writeSyntheticPack writes a minimal, VALID pack for (src, tgt) under root with bytes distinct from zh —
// enough for Load to succeed and for the routing assertion to bite.
func writeSyntheticPack(t *testing.T, root, src, tgt string) {
	t.Helper()
	pair := src + "-" + tgt
	files := map[string]string{
		filepath.Join(src, "surnames-single.txt"):   "# synthetic\n甴甶甹\n",
		filepath.Join(src, "surnames-compound.txt"): "# synthetic\n甲乙\n",
		filepath.Join(src, "title-suffix.txt"):      "# synthetic\n阁下\n",
		filepath.Join(src, "ordinal-title.txt"):     "# synthetic\n第甲\n",
		filepath.Join(src, "rank-word.txt"):         "# synthetic\n級\n",
		filepath.Join(src, "topo-suffix.txt"):       "# synthetic\n峰\n",
		filepath.Join(src, "grade-prefix.txt"):      "# synthetic\n子丑\n",
		filepath.Join(src, "numeral.txt"):           "# synthetic\n壹貳\n",
		filepath.Join(src, "alias-particle.txt"):    "# synthetic\n之乎\n",
		filepath.Join(pair, "palladius.txt"):        "# synthetic\ninitials\tb\tб\nfinals\ta\tа\nyw\tyi\tи\nspecial_i\tzhi\tчжи\n",
	}
	for rel, body := range files {
		p := filepath.Join(root, rel)
		if err := os.MkdirAll(filepath.Dir(p), 0o755); err != nil {
			t.Fatal(err)
		}
		if err := os.WriteFile(p, []byte(body), 0o644); err != nil {
			t.Fatal(err)
		}
	}
}