import os
import gradio as gr
from transformers import pipeline
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet
from spellchecker import SpellChecker
import re
from inflect import engine  # For pluralization

# Initialize the English text classification pipeline for AI detection
pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")

# Initialize the spell checker and inflect engine
spell = SpellChecker()
inflect_engine = engine()

# Ensure necessary NLTK data is downloaded
nltk.download('wordnet')
nltk.download('omw-1.4')

# 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")

# Function to predict AI detection
def predict_en(text):
    res = pipeline_en(text)[0]
    return res['label'], res['score']

# 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 if lemma.name() != word]  # Avoid original word
    return []

# Function to remove redundant words
def remove_redundant_words(text):
    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
    return ' '.join(word for word in text.split() if word.lower() not in meaningless_words)

# Function to correct spelling errors
def correct_spelling(text):
    words = text.split()
    corrected_words = [spell.correction(word) for word in words]
    return ' '.join(corrected_words)

# Function to rephrase text with synonyms
def rephrase_with_synonyms(text):
    doc = nlp(text)
    rephrased_text = []

    for token in doc:
        pos_tag = {
            "NOUN": wordnet.NOUN,
            "VERB": wordnet.VERB,
            "ADJ": wordnet.ADJ,
            "ADV": wordnet.ADV
        }.get(token.pos_, None)
        
        if pos_tag:
            synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
            synonym = synonyms[0] if synonyms else token.text
            rephrased_text.append(synonym)
        else:
            rephrased_text.append(token.text)

    return ' '.join(rephrased_text)

# Function to paraphrase and correct grammar
def paraphrase_and_correct(text):
    cleaned_text = remove_redundant_words(text)
    cleaned_text = correct_spelling(cleaned_text)
    return rephrase_with_synonyms(cleaned_text)

# Function to handle user input
def process_text(input_text):
    ai_label, ai_score = predict_en(input_text)

    if ai_label == "HUMAN":
        corrected_text = paraphrase_and_correct(input_text)
        return corrected_text
    else:
        return "The text seems to be AI-generated; no correction applied."

# Gradio interface
iface = gr.Interface(
    fn=process_text,
    inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."),
    outputs=gr.Textbox(label="Corrected Text"),
    title="Text Correction and Rephrasing",
    description="This app corrects and rephrases text while detecting AI-generated content."
)

# Launch the interface
iface.launch()