Spaces:
Running
Running
| from texts.models import TextDetector | |
| def extract_text_and_images(path: str): | |
| text_content = "" | |
| image_paths = "" | |
| return text_content, image_paths | |
| def process_document(document_path) -> list: | |
| """ | |
| Processes a given document, separating text and images, | |
| and then analyzes them. | |
| Args: | |
| document_path: Path to the document. | |
| Returns: | |
| A list containing the AI content percentage for text and images. | |
| """ | |
| # Extract text and images from the document | |
| text_content, image_paths = extract_text_and_images(document_path) | |
| # Analyze text content | |
| text_detector = TextDetector() | |
| text_ai_content_percentage = text_detector.analyze_text(text_content) | |
| # Analyze image content | |
| image_ai_content_percentages = [] | |
| for image_path in image_paths: | |
| # TODO: add image_detector class | |
| # image_ai_content = image_detector.analyze_image(image_path) | |
| image_ai_content = 100 | |
| image_ai_content_percentages.append(image_ai_content) | |
| return [text_ai_content_percentage, image_ai_content_percentages] | |
| def main(): | |
| document_path = "../data.pdf" # Replace with your document path | |
| text_ai_content_percentage, image_ai_content_percentages = ( | |
| process_document(document_path) | |
| ) | |
| print("Text AI Content Percentage:", text_ai_content_percentage) | |
| print("Combined AI Content Percentage:", image_ai_content_percentages) | |
| if __name__ == "__main__": | |
| main() | |