app.py

import os
import gradio as gr
from transformers import pipeline
import spacy
import subprocess
import json
import nltk
from nltk.corpus import wordnet, stopwords  # Import stopwords here
from spellchecker import SpellChecker
import re
import random
import string

# Ensure necessary NLTK data is downloaded
def download_nltk_resources():
    try:
        nltk.download('punkt')  # Tokenizer for English text
        nltk.download('stopwords')  # Stop words
        nltk.download('averaged_perceptron_tagger')  # POS tagger
        nltk.download('wordnet')  # WordNet
        nltk.download('omw-1.4')  # Open Multilingual Wordnet
    except Exception as e:
        print(f"Error downloading NLTK resources: {e}")

# Call the download function
download_nltk_resources()

top_words = set(stopwords.words("english"))  # More efficient as a set

# Path to the thesaurus file
thesaurus_file_path = 'en_thesaurus.jsonl'  # Ensure the file path is correct

# Function to load the thesaurus into a dictionary
def load_thesaurus(file_path):
    thesaurus_dict = {}
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            for line in file:
                # Parse each line as a JSON object
                entry = json.loads(line.strip())
                word = entry.get("word")
                synonyms = entry.get("synonyms", [])
                if word:
                    thesaurus_dict[word] = synonyms
    except Exception as e:
        print(f"Error loading thesaurus: {e}")
    
    return thesaurus_dict

# Load the thesaurus
synonym_dict = load_thesaurus(thesaurus_file_path)

# Words and POS tags we don't want to replace
exclude_tags = {'PRP', 'PRP$', 'MD', 'VBZ', 'VBP', 'VBD', 'VBG', 'VBN', 'TO', 'IN', 'DT', 'CC'}
exclude_words = {'is', 'am', 'are', 'was', 'were', 'have', 'has', 'do', 'does', 'did', 'will', 'shall', 'should', 'would', 'could', 'can', 'may', 'might'}

# 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
spell = SpellChecker()

# 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 the label and score for English text (AI Detection)
def predict_en(text):
    try:
        res = pipeline_en(text)[0]
        return res['label'], res['score']
    except Exception as e:
        return f"Error during AI detection: {e}"

# Modified plagiarism_remover function to use the loaded thesaurus
def plagiarism_remover(word):
    if word.lower() in top_words or word.lower() in exclude_words or word in string.punctuation:
        return word
    
    # Check for synonyms in the custom thesaurus
    synonyms = synonym_dict.get(word.lower(), set())
    
    # If no synonyms found in the custom thesaurus, use WordNet
    if not synonyms:
        for syn in wordnet.synsets(word):
            for lemma in syn.lemmas():
                if "_" not in lemma.name() and lemma.name().isalpha() and lemma.name().lower() != word.lower():
                    synonyms.add(lemma.name())

    pos_tag_word = nltk.pos_tag([word])[0]
    
    if pos_tag_word[1] in exclude_tags:
        return word
    
    filtered_synonyms = [syn for syn in synonyms if nltk.pos_tag([syn])[0][1] == pos_tag_word[1]]

    if not filtered_synonyms:
        return word

    synonym_choice = random.choice(filtered_synonyms)

    if word.istitle():
        return synonym_choice.title()
    return synonym_choice

# Function to remove redundant and meaningless words
def remove_redundant_words(text):
    doc = nlp(text)
    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
    filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
    return ' '.join(filtered_text)

# Function to fix spacing before punctuation
def fix_punctuation_spacing(text):
    words = text.split(' ')
    cleaned_words = []
    punctuation_marks = {',', '.', "'", '!', '?', ':'}

    for word in words:
        if cleaned_words and word and word[0] in punctuation_marks:
            cleaned_words[-1] += word
        else:
            cleaned_words.append(word)

    return ' '.join(cleaned_words).replace(' ,', ',').replace(' .', '.').replace(" '", "'") \
                                    .replace(' !', '!').replace(' ?', '?').replace(' :', ':')

# Function to fix possessives like "Earth's"
def fix_possessives(text):
    return re.sub(r'(\w)\s\'\s?s', r"\1's", text)

# Function to capitalize the first letter of sentences and proper nouns
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:
                sentence.append(token.text.capitalize())
            elif token.pos_ == "PROPN":
                sentence.append(token.text.capitalize())
            else:
                sentence.append(token.text)
        corrected_text.append(' '.join(sentence))

    return ' '.join(corrected_text)

# Function to force capitalization of the first letter of every sentence and ensure full stops
def force_first_letter_capital(text):
    sentences = re.split(r'(?<=\w[.!?])\s+', text)
    capitalized_sentences = []
    
    for sentence in sentences:
        if sentence:
            capitalized_sentence = sentence[0].capitalize() + sentence[1:]
            if not re.search(r'[.!?]$', capitalized_sentence):
                capitalized_sentence += '.'
            capitalized_sentences.append(capitalized_sentence)
    
    return " ".join(capitalized_sentences)

# Function to correct tense errors in a sentence
def correct_tense_errors(text):
    doc = nlp(text)
    corrected_text = []
    for token in doc:
        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
            corrected_text.append(lemma)
        else:
            corrected_text.append(token.text)
    return ' '.join(corrected_text)

# Function to check and correct article errors
def correct_article_errors(text):
    doc = nlp(text)
    corrected_text = []
    for token in doc:
        if token.text in ['a', 'an']:
            next_token = token.nbor(1)
            if token.text == "a" and next_token.text[0].lower() in "aeiou":
                corrected_text.append("an")
            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
                corrected_text.append("a")
            else:
                corrected_text.append(token.text)
        else:
            corrected_text.append(token.text)
    return ' '.join(corrected_text)

# Function to ensure subject-verb agreement
def ensure_subject_verb_agreement(text):
    doc = nlp(text)
    corrected_text = []
    for token in doc:
        if token.dep_ == "nsubj" and token.head.pos_ == "VERB":
            if token.tag_ == "NN" and token.head.tag_ != "VBZ":
                corrected_text.append(token.head.lemma_ + "s")
            elif token.tag_ == "NNS" and token.head.tag_ == "VBZ":
                corrected_text.append(token.head.lemma_)
        corrected_text.append(token.text)
    return ' '.join(corrected_text)

# Function to correct spelling errors
def correct_spelling(text):
    words = text.split()
    corrected_words = []
    for word in words:
        corrected_word = spell.correction(word)
        corrected_words.append(corrected_word if corrected_word is not None else word)
    return ' '.join(corrected_words)

# Main processing function for paraphrasing and grammar correction
def paraphrase_and_correct(text):
    cleaned_text = remove_redundant_words(text)
    cleaned_text = fix_punctuation_spacing(cleaned_text)
    cleaned_text = fix_possessives(cleaned_text)
    cleaned_text = capitalize_sentences_and_nouns(cleaned_text)
    cleaned_text = force_first_letter_capital(cleaned_text)
    cleaned_text = correct_tense_errors(cleaned_text)
    cleaned_text = correct_article_errors(cleaned_text)
    cleaned_text = ensure_subject_verb_agreement(cleaned_text)
    cleaned_text = correct_spelling(cleaned_text)
    plag_removed = plagiarism_remover(cleaned_text)
    return plag_removed

# Create the Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# AI Text Processor")
    with gr.Tab("AI Detection"):
        t1 = gr.Textbox(lines=5, label='Input Text')
        btn1 = gr.Button("Detect AI")
        out1 = gr.Textbox(label='Prediction', interactive=False)
        out2 = gr.Textbox(label='Confidence', interactive=False)
        btn1.click(fn=predict_en, inputs=t1, outputs=[out1, out2])

    with gr.Tab("Paraphrasing and Grammar Correction"):
        t2 = gr.Textbox(lines=5, label='Input Text')
        btn2 = gr.Button("Process Text")
        out3 = gr.Textbox(label='Processed Text', interactive=False)
        btn2.click(fn=paraphrase_and_correct, inputs=t2, outputs=out3)

demo.launch()