voice-transcriptor/tests/test_settings.py

import json
from pathlib import Path

import pytest

from voice_transcriptor.models import AppSettings
from voice_transcriptor.services.settings import DEFAULT_CONTEXT, SettingsError, SettingsRepository


def test_load_missing_file_returns_documented_defaults(monkeypatch, tmp_path: Path) -> None:
    documents = tmp_path / "Documents"
    documents.mkdir()
    monkeypatch.setattr(Path, "home", classmethod(lambda cls: tmp_path))

    settings, warning = SettingsRepository(tmp_path / "settings.json").load()

    assert settings == AppSettings("gpt-transcribe", "pt-BR", documents)
    assert "AWS, Kubernetes, OpenAI" in settings.context_vocabulary
    assert warning is None


def test_load_missing_file_uses_home_when_documents_is_unavailable(
    monkeypatch, tmp_path: Path
) -> None:
    monkeypatch.setattr(Path, "home", classmethod(lambda cls: tmp_path))

    settings, warning = SettingsRepository(tmp_path / "settings.json").load()

    assert settings.output_directory == tmp_path
    assert warning is None


def test_save_and_load_round_trip_utf8_settings(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    expected = AppSettings("gpt-4o-transcribe", "pt-BR", tmp_path / "Transcrições")
    repository = SettingsRepository(path)

    repository.save(expected)
    actual, warning = repository.load()

    assert actual == expected
    assert warning is None
    assert json.loads(path.read_text(encoding="utf-8")) == {
        "model": "gpt-4o-transcribe",
        "language": "pt-BR",
        "output_directory": str(tmp_path / "Transcrições"),
        "chunk_duration_seconds": 900,
        "chunk_overlap_seconds": 15,
        "retain_temporary_files": False,
        "context_vocabulary": DEFAULT_CONTEXT,
    }


def test_load_malformed_file_recovers_defaults_with_nonfatal_warning(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    path.write_text("not json", encoding="utf-8")

    settings, warning = SettingsRepository(path).load()

    assert settings.model == "gpt-transcribe"
    assert warning is not None
    assert "settings" in warning.lower()


def test_save_replaces_existing_file_atomically(monkeypatch, tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    path.write_text("old", encoding="utf-8")
    calls: list[tuple[Path, Path]] = []
    original_replace = Path.replace

    def recording_replace(source: Path, destination: Path) -> Path:
        calls.append((source, destination))
        return original_replace(source, destination)

    monkeypatch.setattr(Path, "replace", recording_replace)

    SettingsRepository(path).save(AppSettings("model", "pt-BR", tmp_path / "out"))

    assert calls
    source, destination = calls[0]
    assert source.parent == path.parent
    assert destination == path
    assert json.loads(path.read_text(encoding="utf-8"))["model"] == "model"


def test_save_preserves_settings_error_when_replace_and_cleanup_fail(
    monkeypatch, tmp_path: Path
) -> None:
    path = tmp_path / "settings.json"
    replacement_failure = OSError("target is locked")

    def failing_replace(source: Path, destination: Path) -> Path:
        raise replacement_failure

    def failing_unlink(path: Path, missing_ok: bool = False) -> None:
        raise OSError("temporary file is locked")

    monkeypatch.setattr(Path, "replace", failing_replace)
    monkeypatch.setattr(Path, "unlink", failing_unlink)

    with pytest.raises(SettingsError) as caught:
        SettingsRepository(path).save(AppSettings("model", "pt-BR", tmp_path / "out"))

    assert caught.value.__cause__ is replacement_failure


def test_saved_settings_never_include_api_key_fields(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"

    SettingsRepository(path).save(AppSettings("model", "pt-BR", tmp_path / "out"))

    serialized = path.read_text(encoding="utf-8").lower()
    assert "api" not in serialized
    assert "key" not in serialized


def test_preprocessing_settings_round_trip(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    expected = AppSettings("model", "pt-BR", tmp_path, 1200, 20, True)
    repository = SettingsRepository(path)
    repository.save(expected)
    actual, warning = repository.load()
    assert actual == expected
    assert warning is None


def test_legacy_settings_receive_preprocessing_defaults(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    path.write_text(json.dumps({"model": "model", "language": "pt-BR", "output_directory": str(tmp_path)}), encoding="utf-8")
    settings, warning = SettingsRepository(path).load()
    assert (settings.chunk_duration_seconds, settings.chunk_overlap_seconds, settings.retain_temporary_files) == (900, 15, False)
    assert settings.context_vocabulary == DEFAULT_CONTEXT
    assert warning is None


def test_context_vocabulary_round_trips_as_non_secret_setting(tmp_path: Path) -> None:
    path = tmp_path / "settings.json"
    expected = AppSettings("future-transcribe", "pt-BR", tmp_path, context_vocabulary="Brasília, Pix")

    SettingsRepository(path).save(expected)
    actual, warning = SettingsRepository(path).load()

    assert actual == expected
    assert warning is None