Update app.py

app.py

@@ -25,40 +25,34 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
-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 get synonyms using NLTK WordNet and keep the same grammatical form
-def get_synonym(word, pos_tag):
+# Function to get synonyms using NLTK WordNet and maintain original verb form
+def get_synonym(word, pos_tag, original_token):
     synsets = wordnet.synsets(word)
     if not synsets:
         return word
-    
+
     for synset in synsets:
         if synset.pos() == pos_tag:  # Match the part of speech
-            synonym = synset.lemmas()[0].name()  # Get the first lemma
-            # Check if the original word and synonym are in the same form (singular/plural, tense, etc.)
-            if word.islower():
-                return synonym.lower()
+            synonym = synset.lemmas()[0].name()
+
+            # Preserve the original verb form
+            if original_token.tag_ in ["VBG", "VBN"]:  # Present or past participle
+                return spacy_token_form(synonym, original_token.tag_)
+            elif original_token.tag_ in ["VBZ"]:  # 3rd person singular
+                return synonym + "s"
             else:
-                return synonym.capitalize()
+                return synonym
+
     return word
 
+# Function to conjugate the synonym to the correct form based on the original token's tag
+def spacy_token_form(synonym, tag):
+    if tag == "VBG":  # Gerund or present participle
+        return synonym + "ing" if not synonym.endswith("ing") else synonym
+    elif tag == "VBN":  # Past participle
+        return synonym + "ed" if not synonym.endswith("ed") else synonym
+    return synonym
+
 # Function to rephrase text and replace words with their synonyms while maintaining form
 def rephrase_with_synonyms(text):
     doc = nlp(text)
@@ -77,12 +71,7 @@ def rephrase_with_synonyms(text):
             pos_tag = wordnet.ADV
         
         if pos_tag:
-            synonym = get_synonym(token.text, pos_tag)
-            # Ensure that the verb/noun/plural/singular is kept intact
-            if token.pos_ == "VERB":
-                synonym = token.lemma_ if token.morph.get("Tense") == "Past" else synonym
-            elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
-                synonym += 's' if not synonym.endswith('s') else ""
+            synonym = get_synonym(token.text, pos_tag, token)
             rephrased_text.append(synonym)
         else:
             rephrased_text.append(token.text)
@@ -103,62 +92,6 @@ def paraphrase_and_correct(text):
     
     return paraphrased_text
 
-# Function to correct tense errors in a sentence (Tense Correction)
-def correct_tense_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    for token in doc:
-        # Check for tense correction based on modal verbs
-        if token.pos_ == "VERB" and token.dep_ in {"aux", "auxpass"}:
-            # Replace with appropriate verb form
-            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 (Singular/Plural Correction)
-def correct_singular_plural_errors(text):
-    doc = nlp(text)
-    corrected_text = []
-    
-    for token in doc:
-        if token.pos_ == "NOUN":
-            # Check if the noun is singular or plural
-            if token.tag_ == "NN":  # Singular noun
-                # Look for determiners like "many", "several", "few" to correct to plural
-                if any(child.text.lower() in ['many', 'several', 'few'] for child in token.head.children):
-                    corrected_text.append(token.lemma_ + 's')
-                else:
-                    corrected_text.append(token.text)
-            elif token.tag_ == "NNS":  # Plural noun
-                # Look for determiners like "a", "one" to correct to singular
-                if any(child.text.lower() in ['a', 'one'] for child in token.head.children):
-                    corrected_text.append(token.lemma_)
-                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)
-
 # Gradio app setup with two tabs
 with gr.Blocks() as demo:
     with gr.Tab("AI Detection"):