Add working crate parser and filesystem scanner

serato_doctor/cli.py

@@ -1,9 +1,9 @@
 from pathlib import Path
 import argparse
+import csv
 
 from serato_doctor.crate_parser import parse_crates
 from serato_doctor.scanner import scan_audio
-from serato_doctor.report import write_csv, write_missing_report
 
 
 def main():
@@ -11,13 +11,11 @@ def main():
     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"))
-    parser.add_argument("--report", default=str(Path.home() / "Desktop/serato_doctor_missing_report.txt"))
     args = parser.parse_args()
 
     serato = Path(args.serato)
     music = Path(args.music)
     out = Path(args.out)
-    report = Path(args.report)
 
     refs = parse_crates(serato / "Subcrates")
     disk = scan_audio(music)
@@ -33,16 +31,15 @@ def main():
             "exists_by_filename": ref.filename in disk_names,
         })
 
-    missing_count = sum(1 for r in rows if not r["exists_by_filename"])
+    with out.open("w", newline="", encoding="utf-8") as f:
-
+        writer = csv.DictWriter(f, fieldnames=["crate", "serato_path", "filename", "exists_by_filename"])
-    write_csv(rows, out)
+        writer.writeheader()
-    write_missing_report(rows, report)
+        writer.writerows(rows)
 
     print(f"Crate references: {len(refs)}")
     print(f"Disk tracks: {len(disk)}")
-    print(f"Missing by filename: {missing_count}")
+    print(f"Missing by filename: {sum(1 for r in rows if not r['exists_by_filename'])}")
-    print(f"CSV: {out}")
+    print(f"Wrote: {out}")
-    print(f"Report: {report}")
 
 
 if __name__ == "__main__":

serato_doctor/crate_parser.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+import re
+
+from serato_doctor.models import TrackReference
+
+AUDIO_EXTS = "mp3|m4a|wav|aif|aiff|flac|MP3|M4A|WAV|AIF|AIFF|FLAC"
+
+
+def read_crate_text(crate_path: Path) -> str:
+    raw = crate_path.read_bytes()
+    for enc in ("utf-16-be", "utf-16-le", "utf-8", "latin1"):
+        text = raw.decode(enc, errors="ignore")
+        if "Users" in text or "Jukebox" in text:
+            return text
+    return raw.decode("latin1", errors="ignore")
+
+
+def parse_crate(crate_path: Path) -> list[TrackReference]:
+    text = read_crate_text(crate_path)
+
+    # Serato crate files often decode with weird spacing/null-ish characters.
+    # This finds paths from /Users/... through the audio extension without
+    # greedily scanning the entire file.
+    pattern = rf"/?Users/[^\r\n]+?\.(?:{AUDIO_EXTS})"
+
+    refs = []
+    for match in re.finditer(pattern, text):
+        raw_path = "/" + match.group(0).lstrip("/")
+        raw_path = raw_path.replace("\x00", "")
+        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/report.py

@@ -1,42 +0,0 @@
-from collections import Counter, defaultdict
-from pathlib import Path
-import csv
-
-
-def write_missing_report(rows: list[dict], out: Path) -> None:
-    missing = [r for r in rows if not r["exists_by_filename"]]
-
-    crate_counts = Counter(r["crate"] for r in missing)
-    filename_counts = Counter(r["filename"] for r in missing)
-
-    with out.open("w", encoding="utf-8") as f:
-        f.write("# Serato Doctor Missing Report\n\n")
-        f.write(f"Total missing references: {len(missing)}\n\n")
-
-        f.write("## Missing by crate\n\n")
-        for crate, count in crate_counts.most_common():
-            f.write(f"{count:5}  {crate}\n")
-
-        f.write("\n## Most common missing filenames\n\n")
-        for filename, count in filename_counts.most_common(100):
-            f.write(f"{count:5}  {filename}\n")
-
-        f.write("\n## Detail\n\n")
-        by_crate = defaultdict(list)
-        for r in missing:
-            by_crate[r["crate"]].append(r["filename"])
-
-        for crate, names in sorted(by_crate.items()):
-            f.write(f"\n### {crate}\n")
-            for name in sorted(set(names)):
-                f.write(f"- {name}\n")
-
-
-def write_csv(rows: list[dict], out: Path) -> None:
-    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)

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