import os import gradio as gr from transformers import pipeline import spacy import subprocess import json import nltk from nltk.corpus import wordnet, stopwords from spellchecker import SpellChecker import re import random import string # Ensure necessary NLTK data is downloaded def download_nltk_resources(): try: nltk.download('punkt') nltk.download('stopwords') nltk.download('averaged_perceptron_tagger') nltk.download('averaged_perceptron_tagger_eng') nltk.download('wordnet') nltk.download('omw-1.4') nltk.download('punkt_tab') except Exception as e: print(f"Error downloading NLTK resources: {e}") # Call the download function download_nltk_resources() top_words = set(stopwords.words("english")) # 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: 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}" # Function to remove plagiarism 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()