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)

        # STEP 1: Resize and convert to grayscale
        img = cv2.resize(img, None, fx=4, fy=4, interpolation=cv2.INTER_CUBIC)
        gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

        # STEP 2: Denoise + Threshold
        blur = cv2.GaussianBlur(gray, (5, 5), 0)
        _, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

        # Invert to get black text on white background
        inverted = cv2.bitwise_not(thresh)

        # STEP 3: OCR
        results = reader.readtext(inverted)

        # Debug print
        print("OCR Results:", results)

        # STEP 4: Extract weight values using regex
        weight_candidates = []
        for _, text, conf in results:
            text = text.replace("kg", "").replace("KG", "").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

        # STEP 5: 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