sermon-clean/tests/test_processing.py

"""Tests for sermon_clean.processing — normalize, silence_stats, threshold_tune."""

from pathlib import Path

import pytest

from sermon_clean.processing import (
    normalize_loudness,
    silence_stats,
    threshold_tune,
    SilenceStats,
)


def _make_wav(path: Path, *, freq: float = 440.0, duration: float = 5.0) -> Path:
    """Create a synthetic WAV file for testing. Returns the path."""
    import subprocess
    subprocess.run([
        "ffmpeg", "-y", "-v", "error",
        "-f", "lavfi", "-i", f"sine=frequency={freq}:duration={duration}",
        str(path),
    ], check=True)
    return path


def _make_silent_wav(path: Path, duration: float = 5.0) -> Path:
    """Create a silent WAV file."""
    import subprocess
    subprocess.run([
        "ffmpeg", "-y", "-v", "error",
        "-f", "lavfi", "-i", f"anullsrc=r=8000:cl=mono",
        "-t", str(duration),
        str(path),
    ], check=True)
    return path


# ---------------------------------------------------------------------------
# silence_stats
# ---------------------------------------------------------------------------


class TestSilenceStats:
    def test_silent_audio_all_silence(self, tmp_path):
        audio = _make_silent_wav(tmp_path / "silent.wav", duration=5.0)
        stats = silence_stats(audio, threshold_db=-30.0, min_duration_seconds=0.3)
        assert isinstance(stats, SilenceStats)
        assert stats.duration_seconds == pytest.approx(5.0, abs=0.5)
        # A silent file should have 1 big silence run
        assert stats.n_silence_runs == 1
        assert stats.silence_fraction > 0.9
        assert stats.longest_silence_seconds > 4.0
        assert stats.silence_per_minute > 10.0  # very dense silence

    def test_loud_tone_no_silences(self, tmp_path):
        audio = _make_wav(tmp_path / "tone.wav", freq=440.0, duration=5.0)
        stats = silence_stats(audio, threshold_db=-30.0, min_duration_seconds=0.3)
        # 440Hz tone has no silences above the threshold
        assert stats.n_silence_runs == 0
        assert stats.total_silence_seconds == 0.0
        assert stats.silence_fraction == 0.0
        assert stats.silence_per_minute == 0.0

    def test_to_dict_roundtrip(self, tmp_path):
        audio = _make_silent_wav(tmp_path / "silent.wav")
        stats = silence_stats(audio)
        d = stats.to_dict()
        assert d["audio_path"] == str(audio)
        assert isinstance(d["longest_silence_range"], list)
        assert d["threshold_db"] == -35.0


# ---------------------------------------------------------------------------
# threshold_tune
# ---------------------------------------------------------------------------


class TestThresholdTune:
    def test_picks_threshold_closest_to_target(self, tmp_path):
        # 5s silence + 1s tone alternating — moderate silence density
        import subprocess
        audio = tmp_path / "mixed.wav"
        # 5s silence, 1s tone, 5s silence, 1s tone (12s total, 10s silence, ~83% silence)
        subprocess.run([
            "ffmpeg", "-y", "-v", "error",
            "-f", "lavfi", "-i", "anullsrc=r=8000:cl=mono",
            "-f", "lavfi", "-i", "sine=frequency=440",
            "-filter_complex", "[0:a]atrim=0:5[s1];[1:a]atrim=0:1[t1];[0:a]atrim=0:5[s2];[1:a]atrim=0:1[t2];[s1][t1][s2][t2]concat=n=4:v=0:a=1[out]",
            "-map", "[out]", "-t", "12",
            str(audio),
        ], check=True)

        result = threshold_tune(audio, candidates=[-25.0, -35.0, -50.0], target_silence_per_minute=4.0)
        assert "picked_threshold_db" in result
        assert "candidates" in result
        assert len(result["candidates"]) == 3
        # The picked threshold should have the smallest distance
        picked = result["picked_threshold_db"]
        picked_row = next(r for r in result["candidates"] if r["threshold_db"] == picked)
        assert picked_row["distance_from_target"] == min(r["distance_from_target"] for r in result["candidates"])

    def test_handles_no_silences_at_all(self, tmp_path):
        # A pure tone has zero silences regardless of threshold
        audio = _make_wav(tmp_path / "tone.wav", freq=440.0, duration=3.0)
        result = threshold_tune(audio, candidates=[-25.0, -40.0], target_silence_per_minute=4.0)
        # All candidates give 0 silence/min, all distance == 4.0. Picked is just the first.
        assert result["picked_threshold_db"] in [-25.0, -40.0]


# ---------------------------------------------------------------------------
# normalize
# ---------------------------------------------------------------------------


class TestNormalize:
    def test_produces_output_file(self, tmp_path):
        src = _make_wav(tmp_path / "src.wav", freq=440.0, duration=5.0)
        out = tmp_path / "out.wav"
        result = normalize_loudness(src, out, target_lufs=-16.0)
        assert out.exists()
        assert out.stat().st_size > 1000  # not a silent stub
        assert result["target_lufs"] == -16.0
        assert result["measured_input_i"] is not None
        assert result["output_path"] == str(out)

    def test_normalized_audio_is_quieter_than_loud_input(self, tmp_path):
        # Generate a LOUD sine (0.9 amplitude) — should be normalized DOWN
        import subprocess
        src = tmp_path / "loud.wav"
        subprocess.run([
            "ffmpeg", "-y", "-v", "error",
            "-f", "lavfi", "-i", "sine=frequency=440:duration=5",
            "-af", "volume=0.9",
            str(src),
        ], check=True)
        out = tmp_path / "out.wav"
        result = normalize_loudness(src, out, target_lufs=-16.0)
        # The applied offset should be NEGATIVE (reducing volume) for a hot input
        offset = float(result["applied_offset"])
        assert offset < 0.0, f"expected negative gain offset for loud input, got {offset}"