feat(cli): реализован шаг 5 — CLI-связка всех модулей с исправлениями из ревью

- Зачем: - шаг 5 плана: нужен рабочий CLI-happy path, связывающий utils / transcriber / formatter. - ревью этапов 4–5 выявило два medium-бага в formatter и отсутствие тестов для CLI. - Что: - cli.py: все опции по PRD 3.2 (--model, --language, --output, --device, --compute-type, --verbose), rich Status + stderr-консоль, предупреждение на пустую речь, статистика времени. - transcriber.py: добавлена ensure_model_available() с проверкой кэша HF и валидацией локальной директории; on_status callback для передачи прогресса в CLI; обработка ImportError при отсутствии socksio через SOCKS proxy. - formatter.py: исправлен overflow в format_timestamp (0.995 → 00:01.00 вместо 00:00.100); сегменты теперь пишутся с явным пробелом и strip() независимо от whisper-формата текста. - deps: добавлен socksio>=1.0.0 для поддержки SOCKS proxy при загрузке модели. - tests: test_cli.py (8 тестов на CLI-контракт), расширены test_formatter.py и test_transcriber.py. - Проверка: - uv run pytest — 42 passed. - uv run transcribe --help показывает все опции.
2026-03-17 23:38:32 +03:00
parent 0d1a734479
commit 3d14ed7b86
11 changed files with 804 additions and 12 deletions
@@ -3,8 +3,9 @@ from pathlib import Path
 from unittest.mock import MagicMock, patch

 import pytest
+from huggingface_hub.errors import LocalEntryNotFoundError

-from local_transcriber.transcriber import Segment, TranscribeResult, transcribe
+from local_transcriber.transcriber import Segment, TranscribeResult, ensure_model_available, transcribe


 def _make_raw_segments(count: int) -> list:
@@ -27,6 +28,16 @@ def _make_info(language: str = "ru", probability: float = 0.95, duration: float
    return info


+def _create_model_dir(path: Path) -> Path:
+    path.mkdir(parents=True, exist_ok=True)
+    (path / "config.json").write_text("{}")
+    (path / "preprocessor_config.json").write_text("{}")
+    (path / "tokenizer.json").write_text("{}")
+    (path / "vocabulary.json").write_text("{}")
+    (path / "model.bin").write_bytes(b"ok")
+    return path
+
+
@patch("local_transcriber.transcriber.WhisperModel")
 def test_transcribe_collects_segments(mock_model_cls):
    raw_segments = _make_raw_segments(3)
@@ -201,3 +212,146 @@ def test_transcribe_midstream_fallback_no_duplicate_callbacks(mock_model_cls):
    # This is acceptable — on_segment is a live progress callback.
    # The important thing is that result.segments contains only CPU segments.
    assert all(s.text.startswith(" Segment") for s in result.segments)
+
+
+@patch("local_transcriber.transcriber.WhisperModel")
+def test_transcribe_reports_missing_socksio_for_proxy(mock_model_cls):
+    mock_model_cls.side_effect = ImportError(
+        "Using SOCKS proxy, but the 'socksio' package is not installed."
+    )
+
+    with pytest.raises(RuntimeError, match="socksio"):
+        transcribe(
+            file_path=Path("test.mp3"),
+            model_name="tiny",
+            device="cpu",
+        )
+
+
+@patch("local_transcriber.transcriber.WhisperModel")
+def test_transcribe_reports_status_transitions(mock_model_cls):
+    raw_segments = _make_raw_segments(1)
+    info = _make_info()
+
+    instance = MagicMock()
+    instance.transcribe.return_value = (iter(raw_segments), info)
+    mock_model_cls.return_value = instance
+
+    statuses: list[str] = []
+
+    transcribe(
+        file_path=Path("test.mp3"),
+        model_name="tiny",
+        device="cpu",
+        on_status=statuses.append,
+    )
+
+    assert statuses == [
+        "Загружаю модель на cpu...",
+        "Транскрибирую...",
+    ]
+
+
+@patch("local_transcriber.transcriber.snapshot_download")
+def test_ensure_model_available_uses_cache_first(mock_snapshot_download, tmp_path):
+    model_dir = _create_model_dir(tmp_path / "cache-model")
+    mock_snapshot_download.return_value = str(model_dir)
+
+    result = ensure_model_available("large-v3")
+
+    assert result == str(model_dir)
+    mock_snapshot_download.assert_called_once_with(
+        "Systran/faster-whisper-large-v3",
+        local_files_only=True,
+        allow_patterns=[
+            "config.json",
+            "preprocessor_config.json",
+            "model.bin",
+            "tokenizer.json",
+            "vocabulary.*",
+        ],
+    )
+
+
+@patch("local_transcriber.transcriber._validate_model_dir")
+@patch("local_transcriber.transcriber.snapshot_download")
+def test_ensure_model_available_downloads_on_cache_miss(mock_snapshot_download, mock_validate_model_dir):
+    mock_snapshot_download.side_effect = [
+        LocalEntryNotFoundError("not cached"),
+        "/downloaded/model",
+    ]
+    statuses: list[str] = []
+
+    result = ensure_model_available("large-v3", on_status=statuses.append)
+
+    assert result == "/downloaded/model"
+    assert mock_snapshot_download.call_args_list[0].kwargs["local_files_only"] is True
+    assert mock_snapshot_download.call_args_list[1].kwargs["local_files_only"] is False
+    assert statuses == [
+        "Проверяю кэш модели large-v3...",
+        "Скачиваю модель large-v3 из Hugging Face...",
+    ]
+
+
+def test_ensure_model_available_accepts_local_directory(tmp_path):
+    model_dir = _create_model_dir(tmp_path / "model")
+
+    result = ensure_model_available(str(model_dir))
+
+    assert result == str(model_dir)
+
+
+def test_ensure_model_available_accepts_repo_id(tmp_path):
+    model_dir = _create_model_dir(tmp_path / "repo-model")
+    with patch("local_transcriber.transcriber.snapshot_download", return_value=str(model_dir)) as mock_snapshot_download:
+        result = ensure_model_available("org/model")
+
+    assert result == str(model_dir)
+    assert mock_snapshot_download.call_args.kwargs["local_files_only"] is True
+
+
+def test_ensure_model_available_rejects_unsupported_alias():
+    with pytest.raises(ValueError, match="Неподдерживаемая модель"):
+        ensure_model_available("distil-large-v3")
+
+
+@patch("local_transcriber.transcriber.snapshot_download")
+def test_ensure_model_available_redownloads_incomplete_cache(mock_snapshot_download, tmp_path):
+    incomplete = tmp_path / "incomplete"
+    incomplete.mkdir()
+    (incomplete / "config.json").write_text("{}")
+    (incomplete / "preprocessor_config.json").write_text("{}")
+    (incomplete / "tokenizer.json").write_text("{}")
+    (incomplete / "vocabulary.json").write_text("{}")
+
+    complete = tmp_path / "complete"
+    complete.mkdir()
+    (complete / "config.json").write_text("{}")
+    (complete / "preprocessor_config.json").write_text("{}")
+    (complete / "tokenizer.json").write_text("{}")
+    (complete / "vocabulary.json").write_text("{}")
+    (complete / "model.bin").write_bytes(b"ok")
+
+    mock_snapshot_download.side_effect = [
+        str(incomplete),
+        str(complete),
+    ]
+    statuses: list[str] = []
+
+    result = ensure_model_available("large-v3", on_status=statuses.append)
+
+    assert result == str(complete)
+    assert statuses == [
+        "Проверяю кэш модели large-v3...",
+        "Кэш модели large-v3 неполный, докачиваю...",
+        "Скачиваю модель large-v3 из Hugging Face...",
+    ]
+
+
+def test_ensure_model_available_rejects_incomplete_local_directory(tmp_path):
+    model_dir = tmp_path / "model"
+    model_dir.mkdir()
+    (model_dir / "config.json").write_text("{}")
+
+    with pytest.raises(ValueError, match="Неполная локальная модель"):
+        ensure_model_available(str(model_dir))