Add explainable matching engine

tests/test_matcher.py

@@ -0,0 +1,62 @@
+from pathlib import Path
+
+from serato_doctor.matching import MatchingEngine, score_candidate
+from serato_doctor.models.reference import TrackReference
+from serato_doctor.models.track import DiskTrack
+
+
+def reference(filename, folder="House"):
+    return TrackReference(
+        Path("Test.crate"), Path("/old") / folder / filename, filename
+    )
+
+
+def track(filename, folder="House"):
+    path = Path("/new") / folder / filename
+    return DiskTrack(path, filename, 100, path.suffix.lower())
+
+
+def test_exact_candidate_has_full_evidence_score():
+    match = score_candidate(reference("Track.mp3"), track("Track.mp3"))
+
+    assert match.score == 90
+    assert match.max_score == 90
+    assert match.score_percent == 100.0
+    assert all(item.matched for item in match.evidence)
+
+
+def test_cloud_conflict_suffix_is_explained():
+    match = score_candidate(reference("Track.mp3"), track("Track 2.mp3"))
+
+    assert match.score == 80
+    assert match.score_percent == 88.9
+    assert match.evidence[0].explanation == (
+        "Filename matches after removing a numeric conflict suffix"
+    )
+
+
+def test_case_normalized_match_scores_below_exact():
+    match = score_candidate(reference("TRACK.MP3"), track("track.mp3"))
+
+    assert match.score == 85
+    assert match.evidence[0].points == 55
+
+
+def test_engine_omits_unrelated_filenames():
+    engine = MatchingEngine([track("Different.mp3")])
+
+    assert engine.candidates_for(reference("Missing.mp3")) == ()
+
+
+def test_ambiguous_candidates_are_ranked_deterministically():
+    engine = MatchingEngine(
+        [track("Track 2.mp3", "Other"), track("Track 3.mp3", "House")]
+    )
+
+    matches = engine.candidates_for(reference("Track.mp3"))
+
+    assert [match.track.filename for match in matches] == [
+        "Track 3.mp3",
+        "Track 2.mp3",
+    ]
+    assert [match.score for match in matches] == [80, 60]