Establish automated test foundation

tests/test_cli.py

@@ -0,0 +1,49 @@
+import csv
+import sys
+
+from serato_doctor.cli import main
+
+
+def test_cli_writes_reports_and_prints_counts(tmp_path, monkeypatch, capsys):
+    serato = tmp_path / "serato"
+    subcrates = serato / "Subcrates"
+    music = tmp_path / "music"
+    subcrates.mkdir(parents=True)
+    music.mkdir()
+
+    crate_text = (
+        "Users/djsplice/OneDrive/Jukebox/Found.mp漳牴k"
+        "Users/djsplice/OneDrive/Jukebox/Missing.mp漳牴k"
+    )
+    (subcrates / "Test.crate").write_bytes(crate_text.encode("utf-16-le"))
+    (music / "Found.mp3").write_bytes(b"synthetic audio")
+    csv_path = tmp_path / "scan.csv"
+    report_path = tmp_path / "report.txt"
+    monkeypatch.setattr(
+        sys,
+        "argv",
+        [
+            "serato-doctor",
+            "--serato",
+            str(serato),
+            "--music",
+            str(music),
+            "--out",
+            str(csv_path),
+            "--report",
+            str(report_path),
+        ],
+    )
+
+    main()
+
+    output = capsys.readouterr().out
+    assert "Crate references: 2" in output
+    assert "Disk tracks: 1" in output
+    assert "Missing by filename: 1" in output
+    assert f"CSV: {csv_path}" in output
+    assert f"Report: {report_path}" in output
+    with csv_path.open(newline="", encoding="utf-8") as csv_file:
+        rows = list(csv.DictReader(csv_file))
+    assert [row["exists_by_filename"] for row in rows] == ["True", "False"]
+    assert "Total missing references: 1" in report_path.read_text(encoding="utf-8")

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) == []

tests/test_library.py

@@ -0,0 +1,24 @@
+from pathlib import Path
+
+from serato_doctor.models.library import Library
+from serato_doctor.models.reference import TrackReference
+from serato_doctor.models.track import DiskTrack
+
+
+def test_library_reconciles_references_by_filename():
+    crate = Path("House.crate")
+    references = [
+        TrackReference(crate, Path("/old/Found.mp3"), "Found.mp3"),
+        TrackReference(crate, Path("/old/Missing.mp3"), "Missing.mp3"),
+    ]
+    tracks = [DiskTrack(Path("/new/Found.mp3"), "Found.mp3", 10, ".mp3")]
+
+    results = Library.build(references, tracks).reconcile_by_filename()
+
+    assert [result.exists_by_filename for result in results] == [True, False]
+    assert results[1].as_row() == {
+        "crate": "House.crate",
+        "serato_path": "/old/Missing.mp3",
+        "filename": "Missing.mp3",
+        "exists_by_filename": False,
+    }

tests/test_scanner.py

@@ -0,0 +1,17 @@
+from serato_doctor.scanner import scan_audio
+
+
+def test_scan_audio_finds_supported_files(tmp_path):
+    music = tmp_path / "music"
+    nested = music / "House"
+    nested.mkdir(parents=True)
+    (nested / "First.MP3").write_bytes(b"synthetic audio")
+    (nested / "Second.flac").write_bytes(b"fixture")
+    (nested / "notes.txt").write_text("not audio", encoding="utf-8")
+
+    tracks = scan_audio(music)
+
+    assert {track.filename for track in tracks} == {"First.MP3", "Second.flac"}
+    first = next(track for track in tracks if track.filename == "First.MP3")
+    assert first.suffix == ".mp3"
+    assert first.size == len(b"synthetic audio")