import cv2
import numpy as np
from PIL import Image

def preprocess_image(image, target_size=(1000, 1000)):
    """
    Preprocess image for document analysis.
    
    Args:
        image: PIL Image object
        target_size: Tuple of (width, height) to resize to
        
    Returns:
        Preprocessed image as numpy array
    """
    # Convert PIL Image to numpy array if needed
    if isinstance(image, Image.Image):
        img_array = np.array(image)
    else:
        img_array = image
    
    # Convert to RGB if grayscale
    if len(img_array.shape) == 2:
        img_array = cv2.cvtColor(img_array, cv2.COLOR_GRAY2RGB)
    elif img_array.shape[2] == 4:
        img_array = cv2.cvtColor(img_array, cv2.COLOR_RGBA2RGB)
    
    # Resize image
    img_array = cv2.resize(img_array, target_size)
    
    # Enhance contrast
    lab = cv2.cvtColor(img_array, cv2.COLOR_RGB2LAB)
    l, a, b = cv2.split(lab)
    clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8))
    cl = clahe.apply(l)
    enhanced_lab = cv2.merge((cl, a, b))
    enhanced_img = cv2.cvtColor(enhanced_lab, cv2.COLOR_LAB2RGB)
    
    return enhanced_img