Merge improved parser into missing report branch

.gitignore

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

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():
@@ -11,11 +11,13 @@ 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)
@@ -31,15 +33,16 @@ def main():
             "exists_by_filename": ref.filename in disk_names,
         })
 
-    with out.open("w", newline="", encoding="utf-8") as f:
+    missing_count = sum(1 for r in rows if not r["exists_by_filename"])
-        writer = csv.DictWriter(f, fieldnames=["crate", "serato_path", "filename", "exists_by_filename"])
+
-        writer.writeheader()
+    write_csv(rows, out)
-        writer.writerows(rows)
+    write_missing_report(rows, report)
 
     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"Missing by filename: {missing_count}")
-    print(f"Wrote: {out}")
+    print(f"CSV: {out}")
+    print(f"Report: {report}")
 
 
 if __name__ == "__main__":

serato_doctor/crate_parser.py

@@ -1,34 +1,45 @@
 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()
+    return crate_path.read_bytes().decode("utf-16-le", errors="ignore").replace("\x00", "")
-    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:
+def clean_path(raw: str) -> str:
-            return text
+    # Common Serato decode artifacts where final extension char gets merged.
-    return raw.decode("latin1", errors="ignore")
+    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)
-
-    # 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)
 
+    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,

serato_doctor/report.py

@@ -0,0 +1,42 @@
+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)