Improve Serato crate parser for UTF-16 LE path records

.gitignore

@@ -11,3 +11,6 @@ reports/
 # Never commit personal Serato data
 database V2
 *.crate
+
+# macOS
+.DS_Store

serato_doctor/cli.py

@@ -0,0 +1,46 @@
+from pathlib import Path
+import argparse
+import csv
+
+from serato_doctor.crate_parser import parse_crates
+from serato_doctor.scanner import scan_audio
+
+
+def main():
+    parser = argparse.ArgumentParser(prog="serato-doctor")
+    parser.add_argument("--serato", default=str(Path.home() / "Music/_Serato_"))
+    parser.add_argument("--music", default=str(Path.home() / "Library/CloudStorage/OneDrive-Personal/Jukebox"))
+    parser.add_argument("--out", default=str(Path.home() / "Desktop/serato_doctor_scan.csv"))
+    args = parser.parse_args()
+
+    serato = Path(args.serato)
+    music = Path(args.music)
+    out = Path(args.out)
+
+    refs = parse_crates(serato / "Subcrates")
+    disk = scan_audio(music)
+
+    disk_names = {t.filename for t in disk}
+
+    rows = []
+    for ref in refs:
+        rows.append({
+            "crate": str(ref.source),
+            "serato_path": str(ref.path),
+            "filename": ref.filename,
+            "exists_by_filename": ref.filename in disk_names,
+        })
+
+    with out.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=["crate", "serato_path", "filename", "exists_by_filename"])
+        writer.writeheader()
+        writer.writerows(rows)
+
+    print(f"Crate references: {len(refs)}")
+    print(f"Disk tracks: {len(disk)}")
+    print(f"Missing by filename: {sum(1 for r in rows if not r['exists_by_filename'])}")
+    print(f"Wrote: {out}")
+
+
+if __name__ == "__main__":
+    main()

serato_doctor/crate_parser.py

@@ -0,0 +1,58 @@
+from pathlib import Path
+
+from serato_doctor.models import TrackReference
+
+
+def read_crate_text(crate_path: Path) -> str:
+    return crate_path.read_bytes().decode("utf-16-le", errors="ignore").replace("\x00", "")
+
+
+def clean_path(raw: str) -> str:
+    # Common Serato decode artifacts where final extension char gets merged.
+    raw = raw.replace(".mp漳", ".mp3")
+    raw = raw.replace(".MP漳", ".MP3")
+    raw = raw.replace(".m4愠", ".m4a")
+    raw = raw.replace(".M4愠", ".M4A")
+    raw = raw.replace(".wa瘠", ".wav")
+    raw = raw.replace(".WA瘠", ".WAV")
+    raw = raw.replace(".ai映", ".aif")
+    raw = raw.replace(".AI映", ".AIF")
+    return raw.strip()
+
+
+def parse_crate(crate_path: Path) -> list[TrackReference]:
+    text = read_crate_text(crate_path)
+    refs = []
+
+    marker = "Users/djsplice/OneDrive/Jukebox/"
+
+    # Serato record markers seen after paths in UTF-16-LE decoded crate data.
+    stop_markers = ["牴k", "otrk", "ptrk", "tvcn", "ovct"]
+
+    for part in text.split(marker)[1:]:
+        candidate = marker + part
+
+        stops = [candidate.find(m) for m in stop_markers if candidate.find(m) != -1]
+        if not stops:
+            continue
+
+        raw_path = "/" + candidate[: min(stops)]
+        raw_path = clean_path(raw_path)
+
+        path = Path(raw_path)
+        refs.append(
+            TrackReference(
+                source=crate_path,
+                path=path,
+                filename=path.name,
+            )
+        )
+
+    return refs
+
+
+def parse_crates(root: Path) -> list[TrackReference]:
+    refs = []
+    for crate in root.rglob("*.crate"):
+        refs.extend(parse_crate(crate))
+    return refs

serato_doctor/models.py

@@ -0,0 +1,17 @@
+from dataclasses import dataclass
+from pathlib import Path
+
+
+@dataclass(frozen=True)
+class TrackReference:
+    source: Path
+    path: Path
+    filename: str
+
+
+@dataclass(frozen=True)
+class DiskTrack:
+    path: Path
+    filename: str
+    size: int
+    suffix: str

serato_doctor/scanner.py

@@ -0,0 +1,31 @@
+from pathlib import Path
+
+from serato_doctor.models import DiskTrack
+
+AUDIO_SUFFIXES = {".mp3", ".m4a", ".wav", ".aif", ".aiff", ".flac"}
+
+
+def scan_audio(folder: Path) -> list[DiskTrack]:
+    tracks = []
+
+    for path in folder.rglob("*"):
+        if not path.is_file():
+            continue
+        if path.suffix.lower() not in AUDIO_SUFFIXES:
+            continue
+
+        try:
+            stat = path.stat()
+        except OSError:
+            continue
+
+        tracks.append(
+            DiskTrack(
+                path=path,
+                filename=path.name,
+                size=stat.st_size,
+                suffix=path.suffix.lower(),
+            )
+        )
+
+    return tracks