Update app.py

app.py

@@ -25,58 +25,15 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# 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()
-
-            # 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
-
-    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)
-    rephrased_text = []
-
-    for token in doc:
-        # Get the correct POS tag for WordNet
-        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:
-            synonym = get_synonym(token.text, pos_tag, token)
-            rephrased_text.append(synonym)
-        else:
-            rephrased_text.append(token.text)
-
-    return ' '.join(rephrased_text)
+# Function to get synonyms using NLTK WordNet (Humanifier)
+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]
+    return []
+
+# Function to capitalize the first letter of sentences and proper nouns (Humanifier)
 def capitalize_sentences_and_nouns(text):
     doc = nlp(text)
     corrected_text = []
@@ -94,6 +51,88 @@ def capitalize_sentences_and_nouns(text):
 
     return ' '.join(corrected_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)
+
+# 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]
+        # Ensure the correct grammatical form is maintained
+        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 paraphrase and correct grammar
 def paraphrase_and_correct(text):
     paraphrased_text = capitalize_sentences_and_nouns(text)  # Capitalize first to ensure proper noun capitalization
@@ -102,11 +141,17 @@ def paraphrase_and_correct(text):
     paraphrased_text = correct_article_errors(paraphrased_text)
     paraphrased_text = correct_singular_plural_errors(paraphrased_text)
     paraphrased_text = correct_tense_errors(paraphrased_text)
+
+    # Replace words with synonyms while maintaining verb form
+    doc = nlp(paraphrased_text)
+    final_text = []
+    for token in doc:
+        if token.pos_ in {"VERB", "NOUN", "ADJ", "ADV"}:
+            final_text.append(replace_with_synonym(token))
+        else:
+            final_text.append(token.text)
     
-    # Rephrase with synonyms while maintaining grammatical forms
-    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
-    
-    return paraphrased_text
+    return ' '.join(final_text)
 
 # Gradio app setup with two tabs
 with gr.Blocks() as demo:
@@ -128,4 +173,4 @@ with gr.Blocks() as demo:
         paraphrase_button.click(paraphrase_and_correct, inputs=text_input, outputs=output_text)
 
 # Launch the app with the remaining functionalities
-demo.launch(share=True)
+demo.launch()