"""Check what non-sneaker items might be slipping through the bol import"""
import gzip, csv
from collections import defaultdict

TARGET_BRANDS = {
    'nike', 'adidas', 'adidas originals', 'new balance', 'puma', 'asics',
    'jordan', 'vans', 'converse', 'reebok', 'skechers', 'hoka', 'on running',
    'on', 'salomon', 'diadora', 'karhu', 'filling pieces', 'autry',
    'common projects', 'saucony', 'hummel', 'geox', 'floris van bommel',
    'nubikk', 'cruyff', 'fila', 'lacoste', 'tommy hilfiger', 'reebok classic',
}

# Words that indicate NOT a sneaker
EXCLUDE_KEYWORDS = [
    'sandaal', 'sandal', 'slipper', 'slide', 'flip flop', 'muil', 'clog',
    'laars', 'boot', 'pump', 'ballerina', 'espadrille', 'loafer', 'mocassin',
    'pantoffel', 'wandelschoen', 'hiking', 'voetbal', 'football', 'rugby',
    'tennis ', 'indoor', 'zaal', 'badschoen', 'waterschoen', 'aqua',
    'sokken', 'veters', 'inlegzool', 'schoenlepel', 'tas ', 'rugzak',
    'badslippers', 'teenslippers', 'klompen',
]

suspicious = defaultdict(list)
clean_count = 0
dirty_count = 0

with gzip.open(r'D:\bol-footwear-feed.csv.gz', 'rt', encoding='utf-8', errors='replace') as f:
    reader = csv.DictReader(f, delimiter='|', quotechar='"')
    for row in reader:
        subgroup = row.get('Category.subgroup', '').lower()
        if 'sneaker' not in subgroup:
            continue
        if row.get('OfferNL.isDeliverable') != 'Y' or row.get('OfferNL.condition') != 'new':
            continue
        brand = row.get('brand', '').strip()
        if brand.lower() not in TARGET_BRANDS:
            continue

        title = row.get('title', '').lower()
        brick = row.get('Gpc.brickName', '').lower()
        subsub = row.get('Category.subssubgroup', '').lower()
        
        found = False
        for kw in EXCLUDE_KEYWORDS:
            if kw in title or kw in brick:
                suspicious[kw].append(title[:80])
                dirty_count += 1
                found = True
                break
        if not found:
            clean_count += 1

print(f"Clean sneakers: {clean_count}")
print(f"Suspicious items: {dirty_count}")
print()
for kw, items in sorted(suspicious.items(), key=lambda x: -len(x[1])):
    print(f"  '{kw}': {len(items)} items")
    for t in items[:3]:
        print(f"    - {t}")