kernbench2/tests/test_verify_adr_lang_pairs.py

"""Tests for tools/verify_adr_lang_pairs.py."""

from __future__ import annotations

import sys
from pathlib import Path

_REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(_REPO_ROOT / "tools"))

import verify_adr_lang_pairs as v  # noqa: E402


def _make_adr(
    path: Path,
    title_id: str,
    title_text: str = "Some Title",
    status: str = "Accepted",
) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(
        f"# ADR-{title_id}: {title_text}\n\n"
        f"## Status\n\n{status}\n\n"
        f"## Context\n\nbody\n",
        encoding="utf-8",
    )


def test_complete_pairs_pass(tmp_path: Path) -> None:
    _make_adr(tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001", "Foo EN")
    _make_adr(tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001", "Foo KO")
    assert v.verify(tmp_path) == []


def test_empty_dirs_pass(tmp_path: Path) -> None:
    assert v.verify(tmp_path) == []


def test_missing_ko_fails(tmp_path: Path) -> None:
    _make_adr(tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001")
    errs = v.verify(tmp_path)
    assert any("missing KO" in e and "ADR-0001-foo-bar.md" in e for e in errs)


def test_orphan_ko_fails(tmp_path: Path) -> None:
    _make_adr(tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001")
    errs = v.verify(tmp_path)
    assert any("orphan KO" in e and "ADR-0001-foo-bar.md" in e for e in errs)


def test_status_mismatch_fails(tmp_path: Path) -> None:
    _make_adr(tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001", status="Accepted")
    _make_adr(tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001", status="Proposed")
    errs = v.verify(tmp_path)
    assert any("Status keyword mismatch" in e for e in errs)


def test_status_parenthetical_translation_passes(tmp_path: Path) -> None:
    """Parenthetical commentary in Status may be translated; only the
    lifecycle keyword needs to match across EN/KO."""
    _make_adr(
        tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001",
        status="Accepted (Revision 2 - concrete bit layout)",
    )
    _make_adr(
        tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001",
        status="Accepted (Revision 2 - 비트 레이아웃 확정)",
    )
    assert v.verify(tmp_path) == []


def test_status_list_after_keyword_passes(tmp_path: Path) -> None:
    """Trailing bullet list in Status may be translated; only first-line
    keyword is compared."""
    _make_adr(
        tmp_path / "docs/adr/ADR-0011-foo-bar.md", "0011",
        status="Accepted.\n\n- VA model: implemented (default).",
    )
    _make_adr(
        tmp_path / "docs/adr-ko/ADR-0011-foo-bar.md", "0011",
        status="Accepted.\n\n- VA 모델: 구현됨 (기본값).",
    )
    assert v.verify(tmp_path) == []


def test_title_id_mismatch_fails(tmp_path: Path) -> None:
    _make_adr(tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0002")
    _make_adr(tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001")
    errs = v.verify(tmp_path)
    assert any("EN title ADR-ID" in e for e in errs)


def test_multiline_status_with_parenthetical_passes(tmp_path: Path) -> None:
    """Real ADRs like ADR-0001 have multi-line Status with revision notes."""
    multiline_status = (
        "Accepted (Revision 2 - 2026-04-27: concrete bit layout,\n"
        "Supersedes ADR-0031.)"
    )
    _make_adr(
        tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001", status=multiline_status
    )
    _make_adr(
        tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001", status=multiline_status
    )
    assert v.verify(tmp_path) == []


def test_superseded_keyword_must_match(tmp_path: Path) -> None:
    """Multi-word lifecycle keywords like 'Superseded by ADR-NNNN' must
    match in full (the ADR ref is part of the keyword)."""
    _make_adr(
        tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001",
        status="Superseded by ADR-0031",
    )
    _make_adr(
        tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md", "0001",
        status="Superseded by ADR-0099",
    )
    errs = v.verify(tmp_path)
    assert any("Status keyword mismatch" in e for e in errs)


def test_crlf_normalization(tmp_path: Path) -> None:
    """KO has CRLF, EN has LF; Status content is otherwise identical -> pass."""
    en = tmp_path / "docs/adr/ADR-0001-foo-bar.md"
    ko = tmp_path / "docs/adr-ko/ADR-0001-foo-bar.md"
    en.parent.mkdir(parents=True, exist_ok=True)
    ko.parent.mkdir(parents=True, exist_ok=True)
    en.write_bytes(
        b"# ADR-0001: Foo\n\n## Status\n\nAccepted\n\n## Context\n\nbody\n"
    )
    ko.write_bytes(
        b"# ADR-0001: Foo\r\n\r\n## Status\r\n\r\nAccepted\r\n\r\n## Context\r\n\r\nbody\r\n"
    )
    assert v.verify(tmp_path) == []


def test_em_dash_title_separator_recognized(tmp_path: Path) -> None:
    """ADR-0033 uses ' — ' instead of ': ' between ADR-NNNN and the title."""
    en = tmp_path / "docs/adr/ADR-0033-foo-bar.md"
    ko = tmp_path / "docs/adr-ko/ADR-0033-foo-bar.md"
    en.parent.mkdir(parents=True, exist_ok=True)
    ko.parent.mkdir(parents=True, exist_ok=True)
    body = "## Status\n\nAccepted\n\n## Context\n\nbody\n"
    en.write_text("# ADR-0033 — Latency Model\n\n" + body, encoding="utf-8")
    ko.write_text("# ADR-0033 — Latency Model\n\n" + body, encoding="utf-8")
    assert v.verify(tmp_path) == []


def test_underscore_in_slug_recognized(tmp_path: Path) -> None:
    """Defensive: slug regex must accept underscores even though current
    ADRs use kebab-case (in case future ADRs reintroduce them)."""
    _make_adr(tmp_path / "docs/adr/ADR-0099-cat-foo_bar.md", "0099")
    _make_adr(tmp_path / "docs/adr-ko/ADR-0099-cat-foo_bar.md", "0099")
    assert v.verify(tmp_path) == []


def test_main_exit_codes(tmp_path: Path, capsys) -> None:
    assert v.main(["--root", str(tmp_path)]) == 0
    _make_adr(tmp_path / "docs/adr/ADR-0001-foo-bar.md", "0001")
    assert v.main(["--root", str(tmp_path)]) == 1
    out = capsys.readouterr().out
    assert "FAILED" in out