import gradio as gr
import spacy
import os
import re
os.system("python -m spacy download en_core_web_sm")
nlp = spacy.load("en_core_web_sm")

def detect_ai_content(text):
    # Count the number of words in the text
    word_count = len(text.split())

    # Analyze the text using Spacy
    doc = nlp(text)

    # Count the number of tokens that are not in Spacy's default stop word list
    non_stopword_tokens = [token for token in doc if not token.is_stop]
    non_stopword_count = len(non_stopword_tokens)

    # Calculate the percentage of non-stopword tokens
    percentage_ai = (1 - non_stopword_count / word_count) * 100

    # Clean the text by removing extra spaces, line breaks and special characters
    cleaned_text = re.sub(r'\s+', ' ', text).strip()
    cleaned_text = re.sub(r'[^\w\s]', '', cleaned_text)

    # Return a dictionary with the percentage of AI-generated content and the cleaned text
    return {
        "text": cleaned_text,
        "percentage": f"{percentage_ai:.2f}% AI-generated content"
    }

gr.Interface(detect_ai_content, "text", "json").launch()