# app/model/model.py
import pickle
import re
from pathlib import Path
from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(max_features=1500)
__version__ = '01'

BASE_DIR = Path(__file__).resolve(strict=True).parent

with open(f"{BASE_DIR}/filename.pkl", "rb") as f:
    data = pickle.load(f)
    model = data['model']
    vocab = data['vocab']

classes = ['Arabic', 'Danish', 'Dutch', 'English', 'French', 'German',
           'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',
           'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish']

dict_por = {'Arabic': 'Árabe', 'Danish': 'Dinamarquês', 'Dutch': 'Holandês', 'English': 'Inglês', 'French': 'Francês', 'German': 'Alemão',
         'Greek': 'Grego', 'Hindi': 'Hindi', 'Italian': 'Italiano', 'Kannada': 'Kannada', 'Malayalam': 'Malaiala', 'Portugeese': 'Português',
            'Russian': 'Russo', 'Spanish': 'Espanhol', 'Sweedish': 'Sueco', 'Tamil': 'Tâmil', 'Turkish': 'Turco'}

def predict_language(text):
    text = re.sub(r'[!@#$(),\n"%^*?\:;~`0-9]', ' ', text)
    text = re.sub(r'[\[\]]', ' ', text)
    text = text.lower()
    text = vocab.transform([text]).toarray() 
    pred = model.predict(text)
    return dict_por[classes[pred[0]]]