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/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