app.py

import os
import gradio as gr
from transformers import pipeline
import spacy
import subprocess
import nltk
from nltk.corpus import wordnet

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

# Function to predict the label and score for English text (AI Detection)
def predict_en(text):
    res = pipeline_en(text)[0]
    return res['label'], res['score']

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


# Ensure the SpaCy model is installed for Humanifier
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")

# Grammar, Tense, and Singular/Plural Correction Functions

# Correct article errors (e.g., "a apple" -> "an apple")
def check_article_error(text):
    tokens = nltk.pos_tag(nltk.word_tokenize(text))
    corrected_tokens = []
    
    for i, token in enumerate(tokens):
        word, pos = token
        if word.lower() == 'a' and i < len(tokens) - 1 and tokens[i + 1][1] == 'NN':
            corrected_tokens.append('an' if tokens[i + 1][0][0] in 'aeiou' else 'a')
        else:
            corrected_tokens.append(word)
    
    return ' '.join(corrected_tokens)

# Correct tense errors (e.g., "She has go out" -> "She has gone out")
def check_tense_error(text):
    tokens = nltk.pos_tag(nltk.word_tokenize(text))
    corrected_tokens = []
    
    for word, pos in tokens:
        if word == "go" and pos == "VB":
            corrected_tokens.append("gone")
        elif word == "know" and pos == "VB":
            corrected_tokens.append("known")
        else:
            corrected_tokens.append(word)
    
    return ' '.join(corrected_tokens)

# Correct singular/plural errors (e.g., "There are many chocolate" -> "There are many chocolates")
def check_pluralization_error(text):
    tokens = nltk.pos_tag(nltk.word_tokenize(text))
    corrected_tokens = []
    
    for word, pos in tokens:
        if word == "chocolate" and pos == "NN":
            corrected_tokens.append("chocolates")
        elif word == "kids" and pos == "NNS":
            corrected_tokens.append("kid")
        else:
            corrected_tokens.append(word)
    
    return ' '.join(corrected_tokens)

# Combined function to correct grammar, tense, and singular/plural errors
def correct_grammar_tense_plural(text):
    text = check_article_error(text)
    text = check_tense_error(text)
    text = check_pluralization_error(text)
    return text

# Function to get synonyms using NLTK WordNet (Humanifier)
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 []

# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
def capitalize_sentences_and_nouns(text):
    doc = nlp(text)
    corrected_text = []

    for sent in doc.sents:
        sentence = []
        for token in sent:
            if token.i == sent.start:  # First word of the sentence
                sentence.append(token.text.capitalize())
            elif token.pos_ == "PROPN":  # Proper noun
                sentence.append(token.text.capitalize())
            else:
                sentence.append(token.text)
        corrected_text.append(' '.join(sentence))

    return ' '.join(corrected_text)

# Paraphrasing function using SpaCy and NLTK (Humanifier)
def paraphrase_with_spacy_nltk(text):
    doc = nlp(text)
    paraphrased_words = []
    
    for token in doc:
        # Map SpaCy POS tags to WordNet POS tags
        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 []
        
        # Replace with a synonym only if it makes sense
        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)
    
    # Join the words back into a sentence
    paraphrased_sentence = ' '.join(paraphrased_words)
    
    # Capitalize sentences and proper nouns
    corrected_text = capitalize_sentences_and_nouns(paraphrased_sentence)
    
    return corrected_text

# Combined function: Paraphrase -> Capitalization -> Grammar Correction
def paraphrase_and_correct(text):
    # Step 1: Paraphrase the text
    paraphrased_text = paraphrase_with_spacy_nltk(text)
    
    # Step 2: Capitalize sentences and proper nouns
    capitalized_text = capitalize_sentences_and_nouns(paraphrased_text)

    # Step 3: Correct grammar, tense, and pluralization
    final_text = correct_grammar_tense_plural(capitalized_text)
    
    return final_text

# Gradio app setup with three tabs
with gr.Blocks() as demo:
    with gr.Tab("AI Detection"):
        t1 = gr.Textbox(lines=5, label='Text')
        button1 = gr.Button("🤖 Predict!")
        label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
        score1 = gr.Textbox(lines=1, label='Prob')

        # Connect the prediction function to the button
        button1.click(predict_en, inputs=[t1], outputs=[label1, score1], api_name='predict_en')
    
    with gr.Tab("Humanifier"):
        text_input = gr.Textbox(lines=5, label="Input Text")
        paraphrase_button = gr.Button("Paraphrase & Correct")
        output_text = gr.Textbox(label="Paraphrased Text")

        # Connect the paraphrasing function to the button
        paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
    
    with gr.Tab("Grammar Correction"):
        grammar_input = gr.Textbox(lines=5, label="Input Text")
        grammar_button = gr.Button("Correct Grammar")
        grammar_output = gr.Textbox(label="Corrected Text")

        # Connect the custom grammar, tense, and plural correction function to the button
        grammar_button.click(correct_grammar_tense_plural, inputs=grammar_input, outputs=grammar_output)

# Launch the app with all functionalities
demo.launch(share=True)  # Enables public link sharing and could bypass local threading issues