import easyocr
import cv2
import os


def extract_text_from_image(image_path, language='en'):
  """
  Extracts text from an image using EasyOCR.

  Args:
      image_path (str): Path to the image file.
      language (str, optional): Language(s) to be recognized. Defaults to 'en' (English).

  Returns:
      list: List of recognized text strings.
  """

  reader = easyocr.Reader([language])
  reader.detector = reader.initDetector('best\BEST.pth')

  image = cv2.imread(image_path)
  result = reader.readtext(image, detail=0)  # Extract only recognized texts

  return result


if __name__ == '__main__':
  # Define the folder path containing images
  folder_path = "inference_results\Anil Maheshwari - Data analytics-McGraw-Hill Education (2017)"

  # Create an empty string to store all concatenated text
  all_extracted_text = ""

  # Loop through all files in the folder
  for filename in os.listdir(folder_path):
    if filename.endswith(".jpg") or filename.endswith(".png"):
      image_path = os.path.join(folder_path, filename)

      # Extract text for current image
      extracted_text = extract_text_from_image(image_path)

      # Concatenate extracted text with a newline character
      all_extracted_text += "\n".join(extracted_text) + "\n\n"  # Add double newlines for separation