Update app.py

app.py

@@ -5,6 +5,8 @@ import spacy
 import subprocess
 import nltk
 from nltk.corpus import wordnet
+from gingerit.gingerit import GingerIt
+from pattern.en import conjugate, lemma, pluralize, singularize
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -51,53 +53,47 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_text)
 
-# Improved Function to correct tense errors in a sentence (Tense Correction)
+# Function to correct tense errors using Pattern
 def correct_tense_errors(text):
     doc = nlp(text)
     corrected_text = []
+    
     for token in doc:
         if token.pos_ == "VERB":
-            lemma = wordnet.morphy(token.text, wordnet.VERB) or token.text
-            if token.tag_ in {"VB", "VBP"}:  # Present tense verb correction
-                corrected_text.append(lemma)
-            elif token.tag_ in {"VBD", "VBN"}:  # Past tense correction
-                corrected_text.append(lemma + "ed")
-            else:
-                corrected_text.append(token.text)
+            # Use conjugate from Pattern to adjust the tense of the verb
+            verb_form = conjugate(lemma(token.text), tense='past')  # Example: fix to past tense
+            corrected_text.append(verb_form)
         else:
             corrected_text.append(token.text)
+    
     return ' '.join(corrected_text)
 
-# Improved Function to correct singular/plural errors (Singular/Plural Correction)
+# Function to correct singular/plural errors using Pattern
 def correct_singular_plural_errors(text):
     doc = nlp(text)
     corrected_text = []
-    
+
     for token in doc:
         if token.pos_ == "NOUN":
-            if token.tag_ == "NN" and token.head.pos_ == "VERB" and token.head.tag_ == "VBZ":  # Singular noun with singular verb
-                corrected_text.append(token.text + 's')  # Make plural
-            elif token.tag_ == "NNS" and token.head.pos_ == "VERB" and token.head.tag_ == "VBP":  # Plural noun with plural verb
-                corrected_text.append(token.lemma_)  # Correct to singular
-            else:
-                corrected_text.append(token.text)
+            if token.tag_ == "NN":  # Singular noun
+                corrected_text.append(singularize(token.text))
+            elif token.tag_ == "NNS":  # Plural noun
+                corrected_text.append(pluralize(token.text))
         else:
             corrected_text.append(token.text)
-    
+
     return ' '.join(corrected_text)
 
-# Improved Function to check and correct article errors
+# Function to check and correct article errors
 def correct_article_errors(text):
     doc = nlp(text)
     corrected_text = []
-    vowels = "aeiou"
-    for i, token in enumerate(doc):
-        if token.text.lower() in ['a', 'an']:
+    for token in doc:
+        if token.text in ['a', 'an']:
             next_token = token.nbor(1)
-            next_word_lemma = next_token.lemma_ if next_token.lemma_ else next_token.text
-            if token.text == "a" and next_word_lemma[0].lower() in vowels:
+            if token.text == "a" and next_token.text[0].lower() in "aeiou":
                 corrected_text.append("an")
-            elif token.text == "an" and next_word_lemma[0].lower() not in vowels:
+            elif token.text == "an" and next_token.text[0].lower() not in "aeiou":
                 corrected_text.append("a")
             else:
                 corrected_text.append(token.text)
@@ -105,12 +101,19 @@ def correct_article_errors(text):
             corrected_text.append(token.text)
     return ' '.join(corrected_text)
 
-# Enhanced Paraphrasing function using SpaCy and NLTK (Humanifier)
+# Function to correct overall grammar using GingerIt
+def correct_grammar(text):
+    parser = GingerIt()
+    result = parser.parse(text)
+    return result['result']
+
+# Paraphrasing function using SpaCy and NLTK (Humanifier)
 def paraphrase_with_spacy_nltk(text):
     doc = nlp(text)
     paraphrased_words = []
     
     for token in doc:
+        # Map SpaCy POS tags to WordNet POS tags
         pos = None
         if token.pos_ in {"NOUN"}:
             pos = wordnet.NOUN
@@ -123,12 +126,13 @@ def paraphrase_with_spacy_nltk(text):
         
         synonyms = get_synonyms_nltk(token.text.lower(), pos) if pos else []
         
-        # Replace with a synonym only if it makes sense contextually
+        # Replace with a synonym only if it makes sense
         if synonyms and token.pos_ in {"NOUN", "VERB", "ADJ", "ADV"} and synonyms[0] != token.text.lower():
             paraphrased_words.append(synonyms[0])
         else:
             paraphrased_words.append(token.text)
     
+    # Join the words back into a sentence
     paraphrased_sentence = ' '.join(paraphrased_words)
     
     return paraphrased_sentence
@@ -143,8 +147,11 @@ def paraphrase_and_correct(text):
     corrected_text = capitalize_sentences_and_nouns(corrected_text)
     corrected_text = correct_singular_plural_errors(corrected_text)
     
-    # Step 3: Capitalize sentences and proper nouns (final correction step)
-    final_text = correct_tense_errors(corrected_text)
+    # Step 3: Correct tense errors
+    corrected_text = correct_tense_errors(corrected_text)
+    
+    # Step 4: Correct overall grammar using GingerIt
+    final_text = correct_grammar(corrected_text)
     
     return final_text
 
@@ -167,5 +174,5 @@ with gr.Blocks() as demo:
         # Connect the paraphrasing function to the button
         paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
 
-# Launch the app with the remaining functionalities
+# Launch the app
 demo.launch()