gart/code/tests/test_voice_features_tool.py

"""Tests for the analyze_voice_features MCP tool.

librosa and Whisper are monkeypatched so these run without the optional
extras, matching the pattern used by TestDetectBeatsHandler.
"""

import json
import struct
import wave

import pytest


def _write_silent_wav(path: str, seconds: float = 2.0) -> None:
    n = int(44100 * seconds)
    with wave.open(path, "w") as f:
        f.setnchannels(1)
        f.setsampwidth(2)
        f.setframerate(44100)
        f.writeframes(struct.pack("<%dh" % n, *([0] * n)))


_FAKE_TRANSCRIPT = {
    "language": "pt",
    "duration": 3.0,
    "text": "isso e seguranca",
    "segments": [{"text": "isso e seguranca", "start": 0.0, "end": 3.0}],
    "words": [
        {"word": "isso", "start": 0.0, "end": 0.4, "confidence": 0.9},
        {"word": "e", "start": 0.5, "end": 0.7, "confidence": 0.9},
        {"word": "seguranca", "start": 2.0, "end": 2.9, "confidence": 0.9},
    ],
}


@pytest.fixture
def wav(tmp_path):
    path = tmp_path / "clip.wav"
    _write_silent_wav(str(path))
    return path


@pytest.fixture
def patched_analysis(monkeypatch):
    """Make the tool's transcription + librosa extractors deterministic."""
    import server_tools._shared.media as _shared_mod
    import server_tools.voice as server_mod

    monkeypatch.setattr(_shared_mod, "transcribe", lambda *a, **k: _FAKE_TRANSCRIPT)
    monkeypatch.setattr(server_mod, "features_capability", lambda: (True, "ok"))
    # "seguranca" (2.0-2.9s) is the loud, high-pitched, emphatic word
    monkeypatch.setattr(
        server_mod,
        "extract_pitch",
        lambda *a, **k: [(0.2, 120.0), (0.6, 118.0), (2.4, 260.0)],
    )
    monkeypatch.setattr(
        server_mod,
        "extract_energy",
        lambda *a, **k: [(0.2, 0.10), (0.6, 0.12), (2.4, 0.95)],
    )


class TestAnalyzeVoiceFeaturesHandler:
    async def test_reports_when_librosa_unavailable(self, wav, monkeypatch):
        import server_tools.voice as server_mod
        from server import handle_analyze_voice_features

        monkeypatch.setattr(
            server_mod, "features_capability", lambda: (False, "componente librosa ausente.")
        )
        result = await handle_analyze_voice_features({"media_path": str(wav)})
        assert "librosa" in result[0].text.lower()

    async def test_rejects_disallowed_extension(self, tmp_path):
        from server import handle_analyze_voice_features

        bad = tmp_path / "clip.txt"
        bad.write_text("not audio")
        with pytest.raises(ValueError):
            await handle_analyze_voice_features({"media_path": str(bad)})

    async def test_writes_features_json_with_emphasis_per_word(self, wav, patched_analysis):
        from server import handle_analyze_voice_features

        result = await handle_analyze_voice_features({"media_path": str(wav)})
        text = result[0].text

        json_path = wav.parent / "clip_voice_features.json"
        assert str(json_path) in text
        data = json.loads(json_path.read_text())
        assert len(data["words"]) == 3
        assert all("emphasis" in w for w in data["words"])
        assert all(0.0 <= w["emphasis"] <= 1.0 for w in data["words"])

    async def test_loudest_word_scores_highest_emphasis(self, wav, patched_analysis):
        from server import handle_analyze_voice_features

        await handle_analyze_voice_features({"media_path": str(wav)})
        data = json.loads((wav.parent / "clip_voice_features.json").read_text())
        by_word = {w["word"]: w["emphasis"] for w in data["words"]}
        assert by_word["seguranca"] > by_word["isso"]
        assert by_word["seguranca"] > by_word["e"]

    async def test_persisted_config_is_embedded_in_output(self, wav, patched_analysis):
        from server import handle_analyze_voice_features

        await handle_analyze_voice_features({"media_path": str(wav)})
        data = json.loads((wav.parent / "clip_voice_features.json").read_text())
        assert "energy_threshold" in data["config"]
        assert "emphasis_weights" in data["config"]

    async def test_empty_transcript_reports_instead_of_crashing(self, wav, monkeypatch):
        import server_tools._shared.media as _shared_mod
        import server_tools.voice as server_mod
        from server import handle_analyze_voice_features

        monkeypatch.setattr(server_mod, "features_capability", lambda: (True, "ok"))
        monkeypatch.setattr(
            _shared_mod, "transcribe", lambda *a, **k: {**_FAKE_TRANSCRIPT, "words": []}
        )
        result = await handle_analyze_voice_features({"media_path": str(wav)})
        assert "no words" in result[0].text.lower()

    async def test_untranscribable_media_reports_install_hint(self, wav, monkeypatch):
        import server_tools._shared.media as _shared_mod
        import server_tools.voice as server_mod
        from server import handle_analyze_voice_features

        monkeypatch.setattr(server_mod, "features_capability", lambda: (True, "ok"))
        monkeypatch.setattr(_shared_mod, "transcribe", lambda *a, **k: None)
        result = await handle_analyze_voice_features({"media_path": str(wav)})
        assert "faster-whisper" in result[0].text

    async def test_missing_pitch_track_degrades_without_crashing(self, wav, monkeypatch):
        import server_tools._shared.media as _shared_mod
        import server_tools.voice as server_mod
        from server import handle_analyze_voice_features

        monkeypatch.setattr(_shared_mod, "transcribe", lambda *a, **k: _FAKE_TRANSCRIPT)
        monkeypatch.setattr(server_mod, "features_capability", lambda: (True, "ok"))
        monkeypatch.setattr(server_mod, "extract_pitch", lambda *a, **k: None)
        monkeypatch.setattr(server_mod, "extract_energy", lambda *a, **k: None)
        result = await handle_analyze_voice_features({"media_path": str(wav)})
        assert "Voice Feature Analysis" in result[0].text
        data = json.loads((wav.parent / "clip_voice_features.json").read_text())
        assert all(w["emphasis"] >= 0.0 for w in data["words"])