#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Detector A1 — albumartist hijacked from a random ROOT file of the folder.

Rule (Alex): a track's albumartist = its OWN artist, unless the album is a genuine
compilation. A value taken from one stray file in the root must NOT be propagated.

Finds folders where the folder-level albumartist equals the `artist` of a MINORITY
file, but is neither the top artist nor the folder name.

Benign hits to review manually (NOT corruption):
  - eponymous compilation        (ДДТ/2008 L'Echoppe — files are a duet credit)
  - letter sub-folder of a set   (Сборка Песни для детей/L)
  - category root                (z Другое, Enigma, Ленинград)
  - any folder the user explicitly decided (Re Sfaction, S Is Here)

Usage:
    python3 find_aa_hijack.py [путь_к_APPLY-PLAN.csv]
"""
import sys

import csv
import collections
import os

P = sys.argv[1] if len(sys.argv) > 1 else '/Users/admin/Downloads/music-tags/APPLY-PLAN.csv'
rows = list(csv.DictReader(open(P, encoding='utf-8-sig', newline='')))


def s(v):
    return (v or '').strip()


by_folder = collections.defaultdict(list)
for r in rows:
    by_folder[r['folder']].append(r)

suspects = []
for folder, rs in sorted(by_folder.items()):
    aa_vals = collections.Counter(s(r['new_albumartist']) for r in rs if s(r['new_albumartist']))
    if len(aa_vals) != 1:
        continue  # mixed folder — separate case
    aa = next(iter(aa_vals))
    art = collections.Counter(s(r['new_artist']) for r in rs if s(r['new_artist']))
    if not art:
        continue
    top_artist, top_n = art.most_common(1)[0]
    folder_name = os.path.basename(folder)
    # albumartist matches a MINORITY artist, not the top one, not the folder name
    if aa != top_artist and aa != folder_name and aa in art:
        minority = art[aa]
        if minority < top_n:
            suspects.append((folder, aa, top_artist, top_n, minority, len(rs)))

print(f"ПОДОЗРЕВАЕМЫХ ПАПОК: {len(suspects)}")
print()
for folder, aa, top, tn, mn, tot in suspects:
    print(f"  albumartist={aa!r}  (у {mn} из {tot})")
    print(f"     должен быть {top!r} (у {tn})")
    print(f"     {folder}")