Files
beets-setup/scripts/unsorted/audit/find_duplicates.py
2026-05-18 14:25:54 -04:00

48 lines
1.5 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#1/usr/bin/env python3
import sys
import re
import unicodedata
from collections import defaultdict
def norm(s: str) -> str:
s = unicodedata.normalize("NFKC", s)
s = s.replace("", "'").replace("", "'").replace("`", "'").replace("´", "'")
s = s.replace("", "-").replace("-", "-").replace("", "-").replace("", "-").replace("", "-")
s = s.replace("", '"').replace("", '"')
s = re.sub(r"\s+", " ", s).strip()
return s.casefold()
groups = defaultdict(list)
for line in sys.stdin:
line = line.rstrip("\n")
if not line:
continue
parts = line.split("\t")
if len(parts) != 9:
print(f"BAD LINE: {line!r}", file=sys.stderr)
continue
album_id, albumartist, album, year, albumtype, albumtotal, mb_albumid, mb_releasegroupid, path = parts
key = (norm(albumartist), norm(album))
groups[key].append(parts)
for key, rows in sorted(groups.items()):
if len(rows) <= 1:
continue
print("=" * 100)
print(f"NORMALIZED DUPLICATE: {key[0]} / {key[1]}")
for row in rows:
album_id, albumartist, album, year, albumtype, albumtotal, mb_albumid, mb_releasegroupid, path = row
print(f"id={album_id}")
print(f" albumartist: {albumartist}")
print(f" album: {album}")
print(f" year/type: {year} / {albumtype}")
print(f" tracks: {albumtotal}")
print(f" mb_albumid: {mb_albumid}")
print(f" rgid: {mb_releasegroupid}")
print(f" path: {path}")