import sys,os,json,pickle,csv,unicodedata,numpy as np,cv2,glob
sys.path.insert(0,'code'); from ocr import VisionOcr
S=os.path.dirname(__file__)
def norm(s):
    s=unicodedata.normalize('NFKC',s).upper()
    tr=str.maketrans('ッャュョァィゥェォヮヵヶユ','ツヤユヨアイウエオワカケユ'); s=s.translate(tr)
    s=s.replace('キユーピー','キユピ').replace('キューピー','キユピ')
    return ''.join(ch for ch in s if ch.isalnum() or ch=='%')
def grams(s): return {s[i:i+2] for i in range(len(s)-1)}
def sim(a,b):
    A,B=grams(norm(a)),grams(norm(b))
    return len(A&B)/max(1,len(A)) if A else 0.0   # share of OCR bigrams explained by signature
# leak-free signatures: catalog names (all SKUs) + OCR of enrolled packshots
names={r['SKU_ID']:r['product_name'] for r in csv.DictReader(open('stock-lopia/stock.csv'))}
if __name__=='__main__':
  o=VisionOcr(languages=['ja-JP','en-US']); sig={}
  for k,n in names.items():
    sig[k]=n
    p=f'stock-lopia-clean/{k}.jpg'
    if os.path.exists(p): sig[k]+=' '+' '.join(l.text for l in o.read(cv2.imread(p)).lines)
  for k,v in sig.items(): print(k, v[:90])
  pickle.dump(sig,open(f'{S}/sig.pkl','wb'))