Update app.py

app.py

@@ -6,7 +6,6 @@ import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
-import random
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -134,17 +133,66 @@ def correct_article_errors(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-# Function to dynamically choose synonyms with more options
-def dynamic_synonyms(token, pos):
+# 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)
-    # Choose a random synonym to increase variety
+    
     if synonyms:
-        random_synonym = random.choice(synonyms)
-        return random_synonym
+        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 rephrase text and replace words with more versatile synonyms
-def versatile_rephrase(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)
+
+# 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)
+    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 = []
 
@@ -158,25 +206,30 @@ def versatile_rephrase(text):
             pos_tag = wordnet.ADJ
         elif token.pos_ == "ADV":
             pos_tag = wordnet.ADV
-
+        
         if pos_tag:
-            synonym = dynamic_synonyms(token, pos_tag)
-            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 ends with 's' else ""
-            rephrased_text.append(synonym)
+            synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
+            if synonyms:
+                # Use a more dynamic approach for synonyms
+                synonym = max(synonyms, key=lambda s: wordnet.synsets(s, pos=pos_tag))  # Select based on the number of synsets
+                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)
         else:
             rephrased_text.append(token.text)
 
     return ' '.join(rephrased_text)
 
-# Function to retain the structure of the input text (headings, paragraphs, line breaks)
+# Retain the structure of the input text (headings, paragraphs, line breaks)
 def retain_structure(text):
     lines = text.split("\n")
     formatted_lines = []
@@ -190,24 +243,35 @@ def retain_structure(text):
     return "\n".join(formatted_lines)
 
 # Function to paraphrase and correct grammar with enhanced accuracy and retain structure
-def paraphrase_and_correct_with_structure(text):
+def paraphrase_and_correct(text):
+    # Retain the structure (headings, paragraphs, line breaks)
     structured_text = retain_structure(text)
     
-    # Rephrase with more versatile synonyms while maintaining grammatical forms
-    paraphrased_text = versatile_rephrase(structured_text)
+    # Remove meaningless or redundant words first
+    cleaned_text = remove_redundant_words(structured_text)
+    
+    # Capitalize sentences and nouns
+    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
     
-    # Apply grammatical corrections on the rephrased text
-    paraphrased_text = remove_redundant_words(paraphrased_text)
-    paraphrased_text = capitalize_sentences_and_nouns(paraphrased_text)
+    # Ensure first letter of each sentence is capitalized
     paraphrased_text = force_first_letter_capital(paraphrased_text)
+    
+    # Handle possessives properly
     paraphrased_text = handle_possessives(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
@@ -227,6 +291,6 @@ with gr.Blocks() as demo:
         result2 = gr.Textbox(lines=5, label='Corrected Text')
 
         # Connect the paraphrasing and correction function to the button
-        button2.click(fn=paraphrase_and_correct_with_structure, inputs=t2, outputs=result2)
+        button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
 
-demo.launch(share=True)
+demo.launch(share=True)  # Share=True to create a public link