app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet
from gensim import downloader as api
import language_tool_python

# Install Java
def install_java():
    subprocess.run(["apt-get", "update"])
    subprocess.run(["apt-get", "install", "-y", "openjdk-11-jre"])

install_java()

# Ensure necessary NLTK data is downloaded
nltk.download('wordnet')
nltk.download('omw-1.4')
nltk.download('punkt')  # Download the Punkt tokenizer for sentence tokenization

# Ensure the spaCy model is installed
try:
    nlp = spacy.load("en_core_web_sm")
except OSError:
    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
    nlp = spacy.load("en_core_web_sm")

# Load a smaller Word2Vec model from Gensim's pre-trained models
word_vectors = api.load("glove-wiki-gigaword-50")

# Check for GPU and set the device accordingly
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Load AI Detector model and tokenizer from Hugging Face (DistilBERT)
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english").to(device)

# Function to correct grammar using LanguageTool
def correct_grammar_with_languagetool(text):
    tool = language_tool_python.LanguageTool('en-US')
    matches = tool.check(text)
    corrected_text = language_tool_python.utils.correct(text, matches)
    return corrected_text

# Function to get synonyms using NLTK WordNet
def get_synonyms_nltk(word, pos):
    synsets = wordnet.synsets(word, pos=pos)
    if synsets:
        lemmas = synsets[0].lemmas()
        return [lemma.name() for lemma in lemmas]
    return []

# Paraphrasing function using spaCy and NLTK
def paraphrase_with_spacy_nltk(text):
    doc = nlp(text)
    paraphrased_words = []
    
    for token in doc:
        pos = None
        if token.pos_ in {"NOUN"}:
            pos = wordnet.NOUN
        elif token.pos_ in {"VERB"}:
            pos = wordnet.VERB
        elif token.pos_ in {"ADJ"}:
            pos = wordnet.ADJ
        elif token.pos_ in {"ADV"}:
            pos = wordnet.ADV
        
        synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
        
        if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
            paraphrased_words.append(synonyms[0])
        else:
            paraphrased_words.append(token.text)
    
    paraphrased_sentence = ' '.join(paraphrased_words)
    return paraphrased_sentence

# Sentence structuring using NLTK
def structure_sentences(text):
    sentences = nltk.sent_tokenize(text)  # Tokenize text into sentences
    structured_sentences = []
    
    for sentence in sentences:
        # Here you can apply any structuring rules or logic you need.
        structured_sentences.append(sentence)
    
    structured_text = ' '.join(structured_sentences)
    return structured_text

# Combined function: Paraphrase -> Structure -> Grammar Check
def humanize_text(text):
    # Step 1: Paraphrase
    paraphrased_text = paraphrase_with_spacy_nltk(text)
    
    # Step 2: Structure sentences
    structured_text = structure_sentences(paraphrased_text)
    
    # Step 3: Apply grammar correction
    final_text = correct_grammar_with_languagetool(structured_text)
    
    return final_text

# Gradio interface definition
with gr.Blocks() as interface:
    with gr.Row():
        with gr.Column():
            text_input = gr.Textbox(lines=5, label="Input Text")
            detect_button = gr.Button("AI Detection")
            humanize_button = gr.Button("Humanize Text")
        with gr.Column():
            output_text = gr.Textbox(label="Output")

    detect_button.click(detect_ai_generated, inputs=text_input, outputs=output_text)
    humanize_button.click(humanize_text, inputs=text_input, outputs=output_text)

# Launch the Gradio app
interface.launch(debug=False)