import easyocr
import numpy as np
import cv2
import re

reader = easyocr.Reader(['en'], gpu=False)

def extract_weight_from_image(pil_img):
    try:
        img = np.array(pil_img)

        # Resize and convert to grayscale
        img = cv2.resize(img, None, fx=2.5, fy=2.5, interpolation=cv2.INTER_LINEAR)
        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

        # Apply Gaussian blur to remove noise
        blurred = cv2.GaussianBlur(gray, (5, 5), 0)

        # Apply adaptive threshold
        thresh = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
                                       cv2.THRESH_BINARY_INV, 15, 6)

        # OCR
        results = reader.readtext(thresh)

        # Debug: Print all detected text
        print("OCR Results:", results)

        weight_candidates = []
        for _, text, conf in results:
            text = text.lower().replace('kg', '').replace('kgs', '').strip()
            if re.match(r'^\d{2,4}(\.\d{1,2})?$', text):
                weight_candidates.append((text, conf))

        if not weight_candidates:
            return "Not detected", 0.0

        # Return the one with highest confidence
        weight, confidence = sorted(weight_candidates, key=lambda x: -x[1])[0]
        return weight, round(confidence * 100, 2)

    except Exception as e:
        return f"Error: {str(e)}", 0.0