Update app.py

app.py

@@ -26,15 +26,13 @@ spell = SpellChecker()
 inflect_engine = inflect.engine()
 
 # Ensure necessary NLTK data is downloaded
-nltk.download('wordnet')
-nltk.download('omw-1.4')
+nltk.download('wordnet', quiet=True)
+nltk.download('omw-1.4', quiet=True)
 
-# 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:
@@ -42,14 +40,12 @@ def get_synonyms_nltk(word, pos):
         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 = []
@@ -57,9 +53,7 @@ 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
-                sentence.append(token.text.capitalize())
-            elif token.pos_ == "PROPN":  # Proper noun
+            if token.i == sent.start or token.pos_ == "PROPN":
                 sentence.append(token.text.capitalize())
             else:
                 sentence.append(token.text)
@@ -67,7 +61,6 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-# Function to correct tense errors in a sentence
 def correct_tense_errors(text):
     doc = nlp(text)
     corrected_text = []
@@ -79,109 +72,75 @@ 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(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)
+            if token.tag_ == "NN" and any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
+                corrected_text.append(inflect_engine.plural(token.lemma_))
+            elif token.tag_ == "NNS" and 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":
+    for i, token in enumerate(doc):
+        if token.text.lower() in ['a', 'an']:
+            next_token = doc[i + 1] if i + 1 < len(doc) else None
+            if next_token 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)
+                corrected_text.append("a")
         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")
+        if token.dep_ == "neg" and any(child.dep_ == "neg" for child in token.head.children):
+            continue
         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)
+            else:
+                corrected_text.append(token.head.text)
+        else:
+            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'
+        if '_' in word:
             sub_words = word.split('_')
-            corrected_sub_words = [spell.correction(w) for w in sub_words]
+            corrected_sub_words = [spell.correction(w) or 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)
+            corrected_word = spell.correction(word) or word
+            corrected_words.append(corrected_word)
     return ' '.join(corrected_words)
 
-# Function to correct common semantic errors
 def correct_semantic_errors(text):
     semantic_corrections = {
         "animate_being": "animal",
@@ -199,69 +158,99 @@ def correct_semantic_errors(text):
         "keeping": "maintaining",
         "lend": "contribute",
         "better": "improve",
-        "is": "s",
-        "wite": "write",
-        "alos": "also",
-        "ads": "as",
-        "dictuionatr": "dictionary",
-        "wors": "words"
+        "cardinal": "key",
+        "expeditiously": "efficiently",
+        "marauder": "predator",
+        "quarry": "prey",
+        "forestalling": "preventing",
+        "bend": "turn",
+        "works": "plant",
+        "croping": "grazing",
+        "flora": "vegetation",
+        "dynamical": "dynamic",
+        "alteration": "change",
+        "add-on": "addition",
+        "indispensable": "essential",
+        "nutrient": "food",
+        "harvest": "crops",
+        "pollenateing": "pollinating",
+        "divers": "diverse",
+        "beginning": "source",
+        "homo": "humans",
+        "fall_in": "collapse",
+        "takeing": "leading",
+        "coinage": "species",
+        "trust": "rely",
+        "angleworm": "earthworm",
+        "interrupt": "break",
+        "affair": "matter",
+        "air_out": "aerate",
+        "alimentary": "nutrient",
+        "distributeed": "spread",
+        "country": "areas",
+        "reconstruct": "restore",
+        "debauched": "degraded",
+        "giant": "whales",
+        "organic_structure": "bodies",
+        "decease": "die",
+        "carcase": "carcasses",
+        "pin_downing": "trapping",
+        "cut_downs": "reduces",
+        "ambiance": "atmosphere",
+        "extenuateing": "mitigating",
+        "decision": "conclusion",
+        "doing": "making",
+        "prolongs": "sustains",
+        "home_ground": "habitats",
+        "continueing": "preserving",
+        "populateing": "living",
+        "beingness": "beings"
     }
     
     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)
-    
+    text = re.sub(r'([a-z])\s+([A-Z])', r'\1. \2', text)
+    return text
+
+def correct_apostrophes(text):
+    text = re.sub(r"\b(\w+)s\b(?<!\'s)", r"\1's", text)
+    text = re.sub(r"\b(\w+)s'\b", r"\1s'", 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":
+        if 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 token.pos_ in ["NOUN", "VERB", "ADJ", "ADV"]:
+            pos_tag = getattr(wordnet, token.pos_)
         
         if pos_tag:
             synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
             if synonyms:
-                synonym = synonyms[0]  # Just using the first synonym for simplicity
+                synonym = synonyms[0]
                 if token.pos_ == "VERB":
-                    if token.tag_ == "VBG":  # Present participle (e.g., running)
+                    if token.tag_ == "VBG":
                         synonym = synonym + 'ing'
-                    elif token.tag_ == "VBD" or token.tag_ == "VBN":  # Past tense or past participle
+                    elif token.tag_ in ["VBD", "VBN"]:
                         synonym = synonym + 'ed'
-                    elif token.tag_ == "VBZ":  # Third-person singular present
+                    elif token.tag_ == "VBZ":
                         synonym = synonym + 's'
                 rephrased_text.append(synonym)
             else:
@@ -271,40 +260,32 @@ def rephrase_with_synonyms(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 = correct_apostrophes(text)
     text = handle_possessives(text)
     text = rephrase_with_synonyms(text)
     text = correct_double_negatives(text)
     text = ensure_subject_verb_agreement(text)
-    
+    text = ' '.join(word.capitalize() if word.lower() in ['i', 'earth'] else word for word in text.split())
     return text
 
-# Gradio interface setup
+def detect_ai(text):
+    label, score = predict_en(text)
+    return label, score
+
 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..."),
@@ -316,5 +297,5 @@ iface = gr.Interface(
     description="Detect AI-generated content and correct grammar issues."
 )
 
-# Launch the app
-iface.launch()
+if __name__ == "__main__":
+    iface.launch()