Philip Guzman
66 lines
1.9 KiB
Python
66 lines
1.9 KiB
Python
from pathlib import Path
|
|
|
|
from serato_doctor.models.crate import Crate
|
|
from serato_doctor.models.reference 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 load_crate(crate_path: Path) -> Crate:
|
|
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 Crate(path=crate_path, references=tuple(refs))
|
|
|
|
|
|
def parse_crate(crate_path: Path) -> list[TrackReference]:
|
|
"""Parse references from one crate, preserving the prototype API."""
|
|
|
|
return list(load_crate(crate_path).references)
|
|
|
|
|
|
def parse_crates(root: Path) -> list[TrackReference]:
|
|
refs = []
|
|
for crate in root.rglob("*.crate"):
|
|
refs.extend(parse_crate(crate))
|
|
return refs
|