chore: atualização geral

code/tests/test_emphasis.py

@@ -0,0 +1,112 @@
+"""Tests for fcpxml/emphasis.py — the emphasis index (pure, no audio needed)."""
+
+from fcpxml.emphasis import (
+    EmphasisWeights,
+    annotate_emphasis,
+    compute_emphasis,
+    pause_weight,
+)
+
+
+def test_zero_input_gives_zero_score():
+    assert compute_emphasis(0.0, 0.0, 0.0, 0.0, 0.0) == 0.0
+
+
+def test_max_input_gives_max_score():
+    # pause sits inside the "dramatic beat" window, not a scene-change gap
+    score = compute_emphasis(
+        energy=1.0, pitch_delta=1.0, rate_delta=1.0, pause_before=1.5, word_duration=10.0
+    )
+    assert score == 1.0
+
+
+def test_negative_pitch_delta_uses_magnitude():
+    a = compute_emphasis(0.0, pitch_delta=0.5, rate_delta=0.0, pause_before=0.0, word_duration=0.0)
+    b = compute_emphasis(0.0, pitch_delta=-0.5, rate_delta=0.0, pause_before=0.0, word_duration=0.0)
+    assert a == b > 0.0
+
+
+def test_duration_saturates_beyond_cap():
+    at_cap = compute_emphasis(0.0, 0.0, 0.0, 0.0, word_duration=1.0, max_duration=1.0)
+    beyond = compute_emphasis(0.0, 0.0, 0.0, 0.0, word_duration=30.0, max_duration=1.0)
+    assert at_cap == beyond
+
+
+class TestPauseWeight:
+    """A long gap is a scene change, not emphasis — it must not outrank a
+    word the speaker actually hit hard. Grounded in real footage where 6-9s
+    gaps were topping the emphasis ranking."""
+
+    def test_dramatic_beat_counts_fully(self):
+        assert pause_weight(1.5, max_pause=1.5) == 1.0
+
+    def test_short_beat_counts_proportionally(self):
+        assert pause_weight(0.75, max_pause=1.5) == 0.5
+
+    def test_long_gap_is_ignored(self):
+        assert pause_weight(8.7, max_pause=1.5, ignore_above=3.0) == 0.0
+
+    def test_no_pause_is_zero(self):
+        assert pause_weight(0.0) == 0.0
+
+    def test_cutoff_can_be_disabled(self):
+        assert pause_weight(30.0, max_pause=1.5, ignore_above=0.0) == 1.0
+
+    def test_scene_change_scores_below_a_loud_word(self):
+        gap = compute_emphasis(0.25, 0.04, 0.0, pause_before=6.2, word_duration=0.5)
+        loud = compute_emphasis(1.00, 0.28, 0.0, pause_before=1.9, word_duration=0.2)
+        assert loud > gap
+
+
+def test_higher_energy_weight_increases_energy_contribution():
+    low_weight = EmphasisWeights(energy=0.1, pitch_variation=0.0, rate_variation=0.0, pause_before=0.0, duration=0.0)
+    high_weight = EmphasisWeights(energy=1.0, pitch_variation=0.0, rate_variation=0.0, pause_before=0.0, duration=0.0)
+    # energy is the only nonzero factor for both weight sets, so normalized
+    # score should be identical regardless of the absolute weight value.
+    score_low = compute_emphasis(0.6, 0.0, 0.0, 0.0, 0.0, weights=low_weight)
+    score_high = compute_emphasis(0.6, 0.0, 0.0, 0.0, 0.0, weights=high_weight)
+    assert score_low == score_high
+
+
+def test_all_zero_weights_returns_zero_not_error():
+    zero_weights = EmphasisWeights(0.0, 0.0, 0.0, 0.0, 0.0)
+    assert compute_emphasis(1.0, 1.0, 1.0, 1.0, 1.0, weights=zero_weights) == 0.0
+
+
+def test_weights_round_trip_dict():
+    w = EmphasisWeights(energy=0.4, pitch_variation=0.3, rate_variation=0.1, pause_before=0.1, duration=0.1)
+    restored = EmphasisWeights.from_dict(w.as_dict())
+    assert restored == w
+
+
+def test_from_dict_fills_missing_with_defaults():
+    restored = EmphasisWeights.from_dict({"energy": 0.9})
+    defaults = EmphasisWeights()
+    assert restored.energy == 0.9
+    assert restored.pitch_variation == defaults.pitch_variation
+
+
+def test_annotate_emphasis_adds_score_per_word():
+    words = [
+        {"word": "hi", "start": 0.0, "end": 0.3, "energy": 0.2, "pitch_delta": 0.1, "rate_delta": 0.1, "pause_before": 0.0},
+        {"word": "WOW", "start": 1.0, "end": 1.5, "energy": 0.9, "pitch_delta": 0.8, "rate_delta": 0.7, "pause_before": 1.0},
+    ]
+    annotated = annotate_emphasis(words)
+    assert len(annotated) == 2
+    assert all("emphasis" in w for w in annotated)
+    assert annotated[1]["emphasis"] > annotated[0]["emphasis"]
+
+
+def test_annotate_emphasis_does_not_mutate_input():
+    words = [{"word": "hi", "start": 0.0, "end": 0.3, "energy": 0.5}]
+    annotate_emphasis(words)
+    assert "emphasis" not in words[0]
+
+
+def test_annotate_emphasis_derives_duration_from_start_end():
+    """A word with no explicit "duration" key gets it from end - start."""
+    base = {"energy": 0.0, "pitch_delta": 0.0, "rate_delta": 0.0, "pause_before": 0.0}
+    derived = annotate_emphasis([{"word": "hi", "start": 1.0, "end": 1.5, **base}], max_duration=0.5)
+    explicit = annotate_emphasis([{"word": "hi", "start": 0.0, "end": 0.0, "duration": 0.5, **base}], max_duration=0.5)
+    # duration is the only nonzero factor in both, so scores must match
+    assert derived[0]["emphasis"] == explicit[0]["emphasis"] > 0.0