Establish automated test foundation

tests/test_crates.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+
+import pytest
+
+from serato_doctor.crate_parser import clean_path, load_crate, parse_crate
+
+
+@pytest.mark.parametrize(
+    ("artifact", "expected"),
+    [
+        ("song.mp漳", "song.mp3"),
+        ("song.m4愠", "song.m4a"),
+        ("song.wa瘠", "song.wav"),
+        ("song.ai映", "song.aif"),
+    ],
+)
+def test_clean_path_repairs_known_extension_artifacts(artifact, expected):
+    assert clean_path(artifact) == expected
+
+
+def test_parse_crate_extracts_references(tmp_path):
+    crate_path = tmp_path / "House.crate"
+    crate_text = (
+        "header"
+        "Users/djsplice/OneDrive/Jukebox/House/First.mp漳牴k"
+        "metadata"
+        "Users/djsplice/OneDrive/Jukebox/House/Second.m4愠otrk"
+    )
+    crate_path.write_bytes(crate_text.encode("utf-16-le"))
+
+    crate = load_crate(crate_path)
+
+    assert crate.path == crate_path
+    assert [reference.filename for reference in crate.references] == [
+        "First.mp3",
+        "Second.m4a",
+    ]
+    assert parse_crate(crate_path) == list(crate.references)
+
+
+def test_parse_crate_ignores_record_without_stop_marker(tmp_path):
+    crate_path = Path(tmp_path) / "Incomplete.crate"
+    crate_path.write_bytes(
+        "Users/djsplice/OneDrive/Jukebox/House/Incomplete.mp3".encode("utf-16-le")
+    )
+
+    assert parse_crate(crate_path) == []