Update app.py

app.py

@@ -6,6 +6,7 @@ import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
+import re
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -29,14 +30,6 @@ 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)
@@ -44,15 +37,20 @@ def remove_redundant_words(text):
     filtered_text = [token.text for token in doc if token.text.lower() not in meaningless_words]
     return ' '.join(filtered_text)
 
-# Function to fix spacing around punctuation
+# Function to fix spacing before punctuation
 def fix_punctuation_spacing(text):
-    text = ' '.join(part.strip() for part in text.splitlines())
-    text = text.replace(' ,', ',').replace(' .', '.').replace(' ;', ';')
+    # Remove spaces before commas, periods, question marks, etc.
+    text = re.sub(r'\s+([,.\'!?:])', r'\1', text)
+    return text
+
+# Function to fix possessives like "Earth's"
+def fix_possessives(text):
+    # Simple rule to catch possessives and correct spacing
+    text = re.sub(r'(\w)\s\'\s?s', r"\1's", text)
     return text
 
-# Updated function to capitalize sentences and proper nouns
+# Function to capitalize the first letter of sentences and proper nouns
 def capitalize_sentences_and_nouns(text):
-    text = fix_punctuation_spacing(text)
     doc = nlp(text)
     corrected_text = []
 
@@ -69,18 +67,11 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-# Function to handle possessive forms
-def correct_possessives(text):
-    doc = nlp(text)
-    corrected_text = []
-    
-    for token in doc:
-        if token.dep_ == 'poss' and token.head.pos_ == 'NOUN':
-            corrected_text.append(f"{token.text}'s")
-        else:
-            corrected_text.append(token.text)
-    
-    return ' '.join(corrected_text)
+# Function to force capitalization of the first letter of every sentence
+def force_first_letter_capital(text):
+    sentences = text.split(". ")
+    capitalized_sentences = [sentence[0].capitalize() + sentence[1:] if sentence else "" for sentence in sentences]
+    return ". ".join(capitalized_sentences)
 
 # Function to correct tense errors in a sentence
 def correct_tense_errors(text):
@@ -94,28 +85,6 @@ 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)
@@ -133,42 +102,6 @@ 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 += 'ing'
-        elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
-            synonym += 'ed'
-        elif token.tag_ == "VBZ":  # Third-person singular present
-            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)
@@ -194,44 +127,7 @@ def correct_spelling(text):
             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 += 'ing'
-                    elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
-                        synonym += 'ed'
-                    elif token.tag_ == "VBZ":  # Third-person singular present
-                        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)
-        else:
-            rephrased_text.append(token.text)
-
-    return ' '.join(rephrased_text)
-
-# Function to paraphrase and correct grammar with enhanced accuracy
+# Main function for paraphrasing and grammar correction
 def paraphrase_and_correct(text):
     # Remove meaningless or redundant words first
     cleaned_text = remove_redundant_words(text)
@@ -239,25 +135,24 @@ def paraphrase_and_correct(text):
     # Capitalize sentences and nouns
     paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
     
-    # Ensure first letter of each sentence is capitalized and fix possessives
-    paraphrased_text = correct_possessives(paraphrased_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)
+    # Fix punctuation spacing and possessives
+    paraphrased_text = fix_punctuation_spacing(paraphrased_text)
+    paraphrased_text = fix_possessives(paraphrased_text)
     
     # Correct spelling errors
     paraphrased_text = correct_spelling(paraphrased_text)
     
     return paraphrased_text
 
-# Gradio app setup with two tabs
+# Gradio app setup
 with gr.Blocks() as demo:
     with gr.Tab("AI Detection"):
         t1 = gr.Textbox(lines=5, label='Text')
@@ -265,7 +160,6 @@ 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"):
@@ -273,7 +167,6 @@ 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)