app.py

import os
import gradio as gr
from transformers import pipeline
import spacy
import nltk
from nltk.corpus import wordnet
from spellchecker import SpellChecker
import re
import inflect

# Initialize components
try:
    nlp = spacy.load("en_core_web_sm")
except OSError:
    print("Downloading spaCy model...")
    spacy.cli.download("en_core_web_sm")
    nlp = spacy.load("en_core_web_sm")

# 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()

# Initialize the inflect engine for pluralization
inflect_engine = inflect.engine()

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

# 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']

# 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]
    return []

# 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 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:  # 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)

# 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 correct singular/plural errors
def correct_singular_plural_errors(text):
    doc = nlp(text)
    corrected_text = []
    
    for token in doc:
        if token.pos_ == "NOUN":
            if token.tag_ == "NN":  # Singular noun
                if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
                    corrected_text.append(inflect_engine.plural(token.lemma_))
                else:
                    corrected_text.append(token.text)
            elif token.tag_ == "NNS":  # Plural noun
                if any(child.text.lower() in ['a', 'one'] for child in token.head.children):
                    corrected_text.append(inflect_engine.singular_noun(token.text) or token.text)
                else:
                    corrected_text.append(token.text)
        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 get the correct synonym while maintaining verb form
def replace_with_synonym(token):
    pos = None
    if token.pos_ == "VERB":
        pos = wordnet.VERB
    elif token.pos_ == "NOUN":
        pos = wordnet.NOUN
    elif token.pos_ == "ADJ":
        pos = wordnet.ADJ
    elif token.pos_ == "ADV":
        pos = wordnet.ADV
    
    synonyms = get_synonyms_nltk(token.lemma_, pos)
    
    if synonyms:
        synonym = synonyms[0]
        if token.tag_ == "VBG":  # Present participle (e.g., running)
            synonym = synonym + 'ing'
        elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
            synonym = synonym + 'ed'
        elif token.tag_ == "VBZ":  # Third-person singular present
            synonym = synonym + 's'
        return synonym
    return token.text

# Function to check for and avoid double negatives
def correct_double_negatives(text):
    doc = nlp(text)
    corrected_text = []
    for token in doc:
        if token.text.lower() == "not" and any(child.text.lower() == "never" for child in token.head.children):
            corrected_text.append("always")
        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":  # Singular noun, should use singular verb
                corrected_text.append(token.head.lemma_ + "s")
            elif token.tag_ == "NNS" and token.head.tag_ == "VBZ":  # Plural noun, should not use singular verb
                corrected_text.append(token.head.lemma_)
        corrected_text.append(token.text)
    return ' '.join(corrected_text)

# Enhance the spell checker function
def enhanced_spell_check(text):
    words = text.split()
    corrected_words = []
    for word in words:
        if '_' in word:  # Handle cases like 'animate_being'
            sub_words = word.split('_')
            corrected_sub_words = [spell.correction(w) for w in sub_words]
            corrected_words.append('_'.join(corrected_sub_words))
        else:
            corrected_word = spell.correction(word)
            corrected_words.append(corrected_word if corrected_word else word)
    return ' '.join(corrected_words)

# Function to correct common semantic errors
def correct_semantic_errors(text):
    semantic_corrections = {
        "animate_being": "animal",
        "little": "smallest",
        "big": "largest",
        "mammalian": "mammals",
        "universe": "world",
        "manner": "ways",
        "continue": "preserve",
        "dirt": "soil",
        "wellness": "health",
        "modulate": "regulate",
        "clime": "climate",
        "function": "role",
        "keeping": "maintaining",
        "lend": "contribute",
        "better": "improve",
        "is": "s",
        "wite": "write",
        "alos": "also",
        "ads": "as",
        "dictuionatr": "dictionary",
        "wors": "words"
    }
    
    words = text.split()
    corrected_words = [semantic_corrections.get(word.lower(), word) for word in words]
    return ' '.join(corrected_words)

# Enhance the punctuation correction function
def enhance_punctuation(text):
    # Remove extra spaces before punctuation
    text = re.sub(r'\s+([?.!,";:])', r'\1', text)
    
    # Add space after punctuation if it's missing
    text = re.sub(r'([?.!,";:])(\S)', r'\1 \2', text)
    
    # Correct spacing for quotes
    text = re.sub(r'\s*"\s*', '" ', text).strip()
    
    # Ensure proper capitalization after sentence-ending punctuation
    text = re.sub(r'([.!?])\s*([a-z])', lambda m: m.group(1) + ' ' + m.group(2).upper(), text)
    
    return text

# Function to handle possessives
def handle_possessives(text):
    text = re.sub(r"\b(\w+)'s\b", r"\1's", text)
    return text

# Function to rephrase text and replace words with their synonyms while maintaining form
def rephrase_with_synonyms(text):
    doc = nlp(text)
    rephrased_text = []

    for token in doc:
        if token.pos_ == "NOUN" and token.text.lower() == "earth":
            rephrased_text.append("Earth")
            continue
        
        pos_tag = None
        if token.pos_ == "NOUN":
            pos_tag = wordnet.NOUN
        elif token.pos_ == "VERB":
            pos_tag = wordnet.VERB
        elif token.pos_ == "ADJ":
            pos_tag = wordnet.ADJ
        elif token.pos_ == "ADV":
            pos_tag = wordnet.ADV
        
        if pos_tag:
            synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
            if synonyms:
                synonym = synonyms[0]  # Just using the first synonym for simplicity
                if token.pos_ == "VERB":
                    if token.tag_ == "VBG":  # Present participle (e.g., running)
                        synonym = synonym + 'ing'
                    elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
                        synonym = synonym + 'ed'
                    elif token.tag_ == "VBZ":  # Third-person singular present
                        synonym = synonym + 's'
                rephrased_text.append(synonym)
            else:
                rephrased_text.append(token.text)
        else:
            rephrased_text.append(token.text)

    return ' '.join(rephrased_text)

# Function to detect AI-generated content
def detect_ai(text):
    label, score = predict_en(text)
    return label, score

# Enhance the paraphrase_and_correct function
def paraphrase_and_correct(text):
    # Apply enhanced spell checking
    text = enhanced_spell_check(text)
    
    # Correct semantic errors
    text = correct_semantic_errors(text)
    
    # Apply existing corrections
    text = remove_redundant_words(text)
    text = capitalize_sentences_and_nouns(text)
    text = correct_tense_errors(text)
    text = correct_singular_plural_errors(text)
    text = correct_article_errors(text)
    text = enhance_punctuation(text)
    text = handle_possessives(text)
    text = rephrase_with_synonyms(text)
    text = correct_double_negatives(text)
    text = ensure_subject_verb_agreement(text)
    
    return text

# Gradio interface setup
def gradio_interface(text):
    label, score = detect_ai(text)
    corrected_text = paraphrase_and_correct(text)
    return {label: score}, corrected_text

# Create Gradio interface
iface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
    outputs=[
        gr.Label(num_top_classes=1),
        gr.Textbox(label="Corrected Text")
    ],
    title="AI Detection and Grammar Correction",
    description="Detect AI-generated content and correct grammar issues."
)

# Launch the app
iface.launch()