Update app.py

app.py

@@ -2,13 +2,13 @@ import os
 import gradio as gr
 from transformers import pipeline
 import spacy
-import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
 import re
 import inflect
 
+# Initialize components
 try:
     nlp = spacy.load("en_core_web_sm")
 except OSError:
@@ -16,8 +16,6 @@ except OSError:
     spacy.cli.download("en_core_web_sm")
     nlp = spacy.load("en_core_web_sm")
 
-
-
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
 
@@ -31,9 +29,6 @@ inflect_engine = inflect.engine()
 nltk.download('wordnet')
 nltk.download('omw-1.4')
 
-# Load the SpaCy model
-nlp = spacy.load("en_core_web_sm")
-
 # Function to predict the label and score for English text (AI Detection)
 def predict_en(text):
     res = pipeline_en(text)[0]
@@ -172,22 +167,67 @@ def ensure_subject_verb_agreement(text):
         corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-# Function to correct spelling errors
-def correct_spelling(text):
+# Enhance the spell checker function
+def enhanced_spell_check(text):
     words = text.split()
     corrected_words = []
     for word in words:
-        corrected_word = spell.correction(word)
-        corrected_words.append(corrected_word if corrected_word else word)
+        if '_' in word:  # Handle cases like 'animate_being'
+            sub_words = word.split('_')
+            corrected_sub_words = [spell.correction(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)
+    return ' '.join(corrected_words)
+
+# Function to correct common semantic errors
+def correct_semantic_errors(text):
+    semantic_corrections = {
+        "animate_being": "animal",
+        "little": "smallest",
+        "big": "largest",
+        "mammalian": "mammals",
+        "universe": "world",
+        "manner": "ways",
+        "continue": "preserve",
+        "dirt": "soil",
+        "wellness": "health",
+        "modulate": "regulate",
+        "clime": "climate",
+        "function": "role",
+        "keeping": "maintaining",
+        "lend": "contribute",
+        "better": "improve",
+        "is": "s",
+        "wite": "write",
+        "alos": "also",
+        "ads": "as",
+        "dictuionatr": "dictionary",
+        "wors": "words"
+    }
+    
+    words = text.split()
+    corrected_words = [semantic_corrections.get(word.lower(), word) for word in words]
     return ' '.join(corrected_words)
 
-# Function to correct punctuation issues
-def correct_punctuation(text):
+# Enhance the punctuation correction function
+def enhance_punctuation(text):
+    # Remove extra spaces before punctuation
     text = re.sub(r'\s+([?.!,";:])', r'\1', text)
-    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)
+    
     return text
 
-# Function to ensure correct handling of possessive forms
+# Function to handle possessives
 def handle_possessives(text):
     text = re.sub(r"\b(\w+)'s\b", r"\1's", text)
     return text
@@ -231,53 +271,40 @@ def rephrase_with_synonyms(text):
 
     return ' '.join(rephrased_text)
 
-# 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 proper nouns
-    cleaned_text = capitalize_sentences_and_nouns(cleaned_text)
-
-    # Correct tense errors
-    cleaned_text = correct_tense_errors(cleaned_text)
-
-    # Correct singular/plural errors
-    cleaned_text = correct_singular_plural_errors(cleaned_text)
-
-    # Correct article errors
-    cleaned_text = correct_article_errors(cleaned_text)
-
-    # Correct spelling
-    cleaned_text = correct_spelling(cleaned_text)
-
-    # Correct punctuation issues
-    cleaned_text = correct_punctuation(cleaned_text)
-
-    # Handle possessives
-    cleaned_text = handle_possessives(cleaned_text)
-
-    # Replace words with synonyms
-    cleaned_text = rephrase_with_synonyms(cleaned_text)
-
-    # Correct double negatives
-    cleaned_text = correct_double_negatives(cleaned_text)
-
-    # Ensure subject-verb agreement
-    cleaned_text = ensure_subject_verb_agreement(cleaned_text)
-
-    return cleaned_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 = handle_possessives(text)
+    text = rephrase_with_synonyms(text)
+    text = correct_double_negatives(text)
+    text = ensure_subject_verb_agreement(text)
+    
+    return text
+
+# Gradio interface setup
 def gradio_interface(text):
     label, score = detect_ai(text)
     corrected_text = paraphrase_and_correct(text)
     return {label: score}, corrected_text
 
-# Modify the Gradio interface setup
+# Create Gradio interface
 iface = gr.Interface(
     fn=gradio_interface,
     inputs=gr.Textbox(lines=5, placeholder="Enter text here..."),
@@ -290,4 +317,4 @@ iface = gr.Interface(
 )
 
 # Launch the app
-iface.launch()
+iface.launch()