Add configurable library reference roots

tests/test_cli.py

@@ -12,8 +12,8 @@ def test_cli_writes_reports_and_prints_counts(tmp_path, monkeypatch, capsys):
     music.mkdir()
 
     crate_text = (
-        "Users/djsplice/OneDrive/Jukebox/Found.mp漳牴k"
-        "Users/djsplice/OneDrive/Jukebox/Missing.mp漳牴k"
+        "Users/sample-user/OneDrive/Jukebox/Found.mp漳牴k"
+        "Users/sample-user/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")
@@ -47,3 +47,38 @@ def test_cli_writes_reports_and_prints_counts(tmp_path, monkeypatch, capsys):
         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")
+
+
+def test_cli_accepts_old_reference_root(tmp_path, monkeypatch, capsys):
+    serato = tmp_path / "serato"
+    subcrates = serato / "Subcrates"
+    music = tmp_path / "music"
+    subcrates.mkdir(parents=True)
+    music.mkdir()
+    (subcrates / "Test.crate").write_bytes(
+        "Archive/Jukebox/Found.mp3otrk".encode("utf-16-le")
+    )
+    (music / "Found.mp3").write_bytes(b"synthetic audio")
+    monkeypatch.setattr(
+        sys,
+        "argv",
+        [
+            "serato-doctor",
+            "--serato",
+            str(serato),
+            "--music",
+            str(music),
+            "--out",
+            str(tmp_path / "scan.csv"),
+            "--report",
+            str(tmp_path / "report.txt"),
+            "--reference-root",
+            "/Archive/Jukebox",
+        ],
+    )
+
+    main()
+
+    output = capsys.readouterr().out
+    assert "Crate references: 1" in output
+    assert "Missing by filename: 0" in output

tests/test_config.py

@@ -0,0 +1,17 @@
+from pathlib import Path
+
+from serato_doctor.config import ScanConfig
+
+
+def test_scan_config_freezes_reference_roots():
+    roots = (Path(root) for root in ["/old/one", "/old/two"])
+
+    config = ScanConfig.build(
+        serato=Path("serato"),
+        music=Path("music"),
+        out=Path("scan.csv"),
+        report=Path("report.txt"),
+        reference_roots=roots,
+    )
+
+    assert config.reference_roots == (Path("/old/one"), Path("/old/two"))

tests/test_crates.py

@@ -2,7 +2,13 @@ from pathlib import Path
 
 import pytest
 
-from serato_doctor.crate_parser import clean_path, load_crate, parse_crate
+from serato_doctor.crate_parser import (
+    clean_path,
+    load_crate,
+    parse_crate,
+    parse_crates,
+    path_markers,
+)
 
 
 @pytest.mark.parametrize(
@@ -22,9 +28,9 @@ 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"
+        "Users/sample-user/OneDrive/Jukebox/House/First.mp漳牴k"
         "metadata"
-        "Users/djsplice/OneDrive/Jukebox/House/Second.m4愠otrk"
+        "Users/sample-user/OneDrive/Jukebox/House/Second.m4愠otrk"
     )
     crate_path.write_bytes(crate_text.encode("utf-16-le"))
 
@@ -41,7 +47,40 @@ def test_parse_crate_extracts_references(tmp_path):
 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")
+        "Users/sample-user/OneDrive/Jukebox/House/Incomplete.mp3".encode(
+            "utf-16-le"
+        )
     )
 
     assert parse_crate(crate_path) == []
+
+
+def test_parse_crate_uses_configured_reference_root(tmp_path):
+    crate_path = tmp_path / "Migrated.crate"
+    crate_path.write_bytes(
+        "Archive/Old Library/House/Track.mp3otrk".encode("utf-16-le")
+    )
+
+    references = parse_crate(crate_path, [Path("/Archive/Old Library")])
+
+    assert references[0].path == Path("/Archive/Old Library/House/Track.mp3")
+
+
+def test_default_path_markers_do_not_contain_a_username():
+    assert path_markers([]) == ("Users/", "Volumes/")
+
+
+def test_parse_crates_reuses_configured_roots_for_every_crate(tmp_path):
+    for name in ("First", "Second"):
+        (tmp_path / f"{name}.crate").write_bytes(
+            f"Archive/Jukebox/{name}.mp3otrk".encode("utf-16-le")
+        )
+
+    references = parse_crates(
+        tmp_path, (root for root in [Path("/Archive/Jukebox")])
+    )
+
+    assert {reference.filename for reference in references} == {
+        "First.mp3",
+        "Second.mp3",
+    }