Update app.py

app.py

@@ -5,7 +5,28 @@ import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
 from spellchecker import SpellChecker
+import re
+import string
+import random
+
+# Download necessary NLTK data
+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')
+
+# Initialize stopwords
+stop_words = set(stopwords.words("english"))
+
+# Words 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")
@@ -13,10 +34,6 @@ pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt
 # Initialize the spell checker
 spell = SpellChecker()
 
-# 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")
@@ -24,27 +41,74 @@ 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 plagiarism_removal(text):
+    def plagiarism_remover(word):
+        if word.lower() in stop_words or word.lower() in exclude_words or word in string.punctuation:
+            return word
+        
+        # Find synonyms
+        synonyms = set()
+        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
+
+    para_split = word_tokenize(text)
+    final_text = [plagiarism_remover(word) for word in para_split]
+    
+    corrected_text = []
+    for i in range(len(final_text)):
+        if final_text[i] in string.punctuation and i > 0:
+            corrected_text[-1] += final_text[i]  
+        else:
+            corrected_text.append(final_text[i])
+
+    return " ".join(corrected_text)
+
 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]
-    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 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(' :', ':')
+
+def fix_possessives(text):
+    text = re.sub(r'(\w)\s\'\s?s', r"\1's", text)
+    return text
+
 def capitalize_sentences_and_nouns(text):
     doc = nlp(text)
     corrected_text = []
@@ -52,9 +116,9 @@ def capitalize_sentences_and_nouns(text):
     for sent in doc.sents:
         sentence = []
         for token in sent:
-            if token.i == sent.start:  # First word of the sentence
+            if token.i == sent.start:
                 sentence.append(token.text.capitalize())
-            elif token.pos_ == "PROPN":  # Proper noun
+            elif token.pos_ == "PROPN":
                 sentence.append(token.text.capitalize())
             else:
                 sentence.append(token.text)
@@ -62,13 +126,19 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-# Function to force capitalization of the first letter of every sentence (NEW)
 def force_first_letter_capital(text):
-    sentences = text.split(". ")  # Split by period to get each sentence
-    capitalized_sentences = [sentence[0].capitalize() + sentence[1:] if sentence else "" for sentence in sentences]
-    return ". ".join(capitalized_sentences)
+    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 = []
@@ -80,29 +150,6 @@ def correct_tense_errors(text):
             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(token.lemma_ + 's')
-                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(token.lemma_)
-                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 = []
@@ -119,131 +166,52 @@ def correct_article_errors(text):
             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
+            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":  # Plural noun, should not use singular verb
+            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()
+    words = word_tokenize(text)
     corrected_words = []
-    for word in words:
-        corrected_word = spell.correction(word)
-        if corrected_word is not None:
-            corrected_words.append(corrected_word)
-        else:
-            corrected_words.append(word)  # Keep the original word if correction is None
-    return ' '.join(corrected_words)
-
-# 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:
-        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.text, 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'
-                elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
-                    synonym += 's' if not synonym.endswith('s') else ""
-                rephrased_text.append(synonym)
-            else:
-                rephrased_text.append(token.text)
+    for word in words:
+        corrected_word = spell.candidates(word)
+        if corrected_word:
+            corrected_words.append(spell.candidates(word).pop())  # Choose the first candidate as the correction
         else:
-            rephrased_text.append(token.text)
+            corrected_words.append(word)  # If it's not misspelled, keep the original word
 
-    return ' '.join(rephrased_text)
+    return ' '.join(corrected_words)
 
-# Function to paraphrase and correct grammar with enhanced accuracy
 def paraphrase_and_correct(text):
-    # Remove meaningless or redundant words first
-    cleaned_text = remove_redundant_words(text)
-    
-    # Capitalize sentences and nouns
-    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
-    
-    # Ensure first letter of each sentence is capitalized
-    paraphrased_text = force_first_letter_capital(paraphrased_text)
-    
-    # Apply grammatical corrections
-    paraphrased_text = correct_article_errors(paraphrased_text)
-    paraphrased_text = correct_singular_plural_errors(paraphrased_text)
-    paraphrased_text = correct_tense_errors(paraphrased_text)
-    paraphrased_text = correct_double_negatives(paraphrased_text)
-    paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
-    
-    # Rephrase with synonyms while maintaining grammatical forms
-    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
-    
-    # Correct spelling errors
-    paraphrased_text = correct_spelling(paraphrased_text)
-    
-    return paraphrased_text
-
-# Gradio app setup with two tabs
+    paragraphs = text.split("\n\n")  # Split by paragraphs
+
+    # Process each paragraph separately
+    processed_paragraphs = []
+    for paragraph in paragraphs:
+        cleaned_text = remove_redundant_words(paragraph)
+        plag_removed = plagiarism_removal(cleaned_text)
+        paraphrased_text = capitalize_sentences_and_nouns(plag_removed)
+        paraphrased_text = force_first_letter_capital(paraphrased_text)
+        paraphrased_text = correct_article_errors(paraphrased_text)
+        paraphrased_text = correct_tense_errors(paraphrased_text)
+        paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
+        paraphrased_text = fix_possessives(paraphrased_text)
+        paraphrased_text = correct_spelling(paraphrased_text)  # Spelling correction
+        paraphrased_text = fix_punctuation_spacing(paraphrased_text)
+        processed_paragraphs.append(paraphrased_text)
+
+    return "\n\n".join(processed_paragraphs)  # Reassemble the text with paragraphs
+
+# Gradio app setup
 with gr.Blocks() as demo:
     with gr.Tab("AI Detection"):
         t1 = gr.Textbox(lines=5, label='Text')
@@ -251,7 +219,6 @@ with gr.Blocks() as demo:
         label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
         score1 = gr.Textbox(lines=1, label='Prob')
 
-        # Connect the prediction function to the button
         button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
 
     with gr.Tab("Paraphrasing & Grammar Correction"):
@@ -259,7 +226,6 @@ with gr.Blocks() as demo:
         button2 = gr.Button("🔄 Paraphrase and Correct")
         result2 = gr.Textbox(lines=5, label='Corrected Text')
 
-        # Connect the paraphrasing and correction function to the button
         button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
 
-demo.launch(share=True)  # Share=True to create a public link
+demo.launch(share=True)