Update app.py

app.py

@@ -7,14 +7,16 @@ import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
 import re
-from inflect import engine  # For pluralization
+import inflect
 
 # 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 and inflect engine
+# Initialize the spell checker
 spell = SpellChecker()
-inflect_engine = engine()
+
+# Initialize the inflect engine for pluralization
+inflect_engine = inflect.engine()
 
 # Ensure necessary NLTK data is downloaded
 nltk.download('wordnet')
@@ -27,7 +29,7 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Function to predict AI detection
+# 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']
@@ -37,66 +39,247 @@ 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 if lemma.name() != word]  # Avoid original word
+        return [lemma.name() for lemma in lemmas if lemma.name() != word]
     return []
 
-# Function to remove redundant words
+# Function to remove redundant and meaningless words
 def remove_redundant_words(text):
+    doc = nlp(text)
     meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
-    return ' '.join(word for word in text.split() if word.lower() not in meaningless_words)
+    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 = []
+
+    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
+                sentence.append(token.text.capitalize())
+            else:
+                sentence.append(token.text)
+        corrected_text.append(' '.join(sentence))
+
+    return ' '.join(corrected_text)
+
+# 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 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)
+        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 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
+                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 = [spell.correction(word) for word in words]
+    corrected_words = []
+    for word in words:
+        corrected_word = spell.correction(word)
+        corrected_words.append(corrected_word if corrected_word else word)  # Keep original if correction is None
     return ' '.join(corrected_words)
 
-# Function to rephrase text with synonyms
+# Function to correct punctuation issues
+def correct_punctuation(text):
+    text = re.sub(r'\s+([?.!,";:])', r'\1', text)  # Remove space before punctuation
+    text = re.sub(r'([?.!,";:])\s+', r'\1 ', text)  # Ensure a single space after punctuation
+    return text
+
+# Function to ensure correct handling of possessive forms
+def handle_possessives(text):
+    text = re.sub(r"\b(\w+)'s\b", r"\1's", text)  # Preserve possessive forms
+    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:
-        pos_tag = {
-            "NOUN": wordnet.NOUN,
-            "VERB": wordnet.VERB,
-            "ADJ": wordnet.ADJ,
-            "ADV": wordnet.ADV
-        }.get(token.pos_, None)
+        if token.pos_ == "NOUN" and 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 pos_tag:
             synonyms = get_synonyms_nltk(token.lemma_, pos_tag)
-            synonym = synonyms[0] if synonyms else token.text
-            rephrased_text.append(synonym)
+            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'
+                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
+# 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)
-    cleaned_text = correct_spelling(cleaned_text)
-    return rephrase_with_synonyms(cleaned_text)
-
-# Function to handle user input
-def process_text(input_text):
-    ai_label, ai_score = predict_en(input_text)
-
-    if ai_label == "HUMAN":
-        corrected_text = paraphrase_and_correct(input_text)
-        return corrected_text
-    else:
-        return "The text seems to be AI-generated; no correction applied."
-
-# Gradio interface
-iface = gr.Interface(
-    fn=process_text,
-    inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."),
-    outputs=gr.Textbox(label="Corrected Text"),
-    title="Text Correction and Rephrasing",
-    description="This app corrects and rephrases text while detecting AI-generated content."
-)
-
-# Launch the interface
+    
+    # Capitalize sentences and nouns
+    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
+    
+    # Correct tense errors
+    paraphrased_text = correct_tense_errors(paraphrased_text)
+    
+    # Correct singular/plural errors
+    paraphrased_text = correct_singular_plural_errors(paraphrased_text)
+    
+    # Correct article errors
+    paraphrased_text = correct_article_errors(paraphrased_text)
+    
+    # Correct spelling
+    paraphrased_text = correct_spelling(paraphrased_text)
+    
+    # Correct punctuation issues
+    paraphrased_text = correct_punctuation(paraphrased_text)
+    
+    # Handle possessives
+    paraphrased_text = handle_possessives(paraphrased_text)
+    
+    # Replace words with synonyms
+    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
+
+    # Correct double negatives
+    paraphrased_text = correct_double_negatives(paraphrased_text)
+
+    # Ensure subject-verb agreement
+    paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
+
+    return paraphrased_text
+
+# Function to detect AI-generated content
+def detect_ai(text):
+    label, score = predict_en(text)
+    return label, score
+
+# Gradio interface setup
+def gradio_interface(text):
+    ai_result = detect_ai(text)
+    corrected_text = paraphrase_and_correct(text)
+    return ai_result, corrected_text
+
+# Create Gradio interface
+iface = gr.Interface(fn=gradio_interface,
+                     inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
+                     outputs=[gr.outputs.Label(num_top_classes=2), gr.outputs.Textbox()],
+                     title="AI Detection and Grammar Correction",
+                     description="Detect AI-generated content and correct grammar issues.")
+
+# Launch the app
 iface.launch()