import cv2
import pytesseract
import numpy as np
from PIL import Image

def preprocess_image(pil_image):
    image = np.array(pil_image.convert("RGB"))
    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
    blurred = cv2.GaussianBlur(gray, (3, 3), 0)
    _, thresh = cv2.threshold(blurred, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
    return thresh

def extract_weight(pil_image):
    try:
        processed_img = preprocess_image(pil_image)
        config = "--psm 7 -c tessedit_char_whitelist=0123456789."
        text = pytesseract.image_to_string(processed_img, config=config)
        print("OCR Raw:", text)

        numbers = ''.join(filter(lambda x: x in "0123456789.", text))
        if not numbers:
            return "No valid weight detected"

        weight_val = float(numbers)
        unit = "kg" if weight_val >= 20 else "grams"
        return f"{weight_val} {unit}"
    except Exception as e:
        return f"Error: {str(e)}"