Philip Guzman
48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
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
|