Update app.py

app.py

@@ -6,13 +6,6 @@ import subprocess
 import nltk
 from nltk.corpus import wordnet
 from spellchecker import SpellChecker
-from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel
-import uvicorn
-import uuid  # To generate unique link IDs
-
-# Initialize FastAPI app
-api_app = FastAPI()
 
 # Initialize the English text classification pipeline for AI detection
 pipeline_en = pipeline(task="text-classification", model="Hello-SimpleAI/chatgpt-detector-roberta")
@@ -31,73 +24,239 @@ except OSError:
     subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
     nlp = spacy.load("en_core_web_sm")
 
-# Generate temporary link storage (could be database or in-memory store)
-temporary_links = {}
-
-# Define request models for FastAPI
-class TextRequest(BaseModel):
-    text: str
-
 # 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']
 
+# Function to get synonyms using NLTK WordNet
+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 remove redundant and meaningless words
+def remove_redundant_words(text):
+    doc = nlp(text)
+    meaningless_words = {"actually", "basically", "literally", "really", "very", "just"}
+    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 '\n'.join(corrected_text)  # Preserve paragraphs by joining sentences with newline
+
+# Function to force capitalization of the first letter of every sentence
+def force_first_letter_capital(text):
+    sentences = text.split(". ")  # Split by period to get each sentence
+    capitalized_sentences = [sentence[0].capitalize() + sentence[1:] if sentence else "" for sentence in sentences]
+    return ". ".join(capitalized_sentences)
+
+# 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(token.lemma_ + 's')
+                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(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]
+        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 = []
+    for word in words:
+        corrected_word = spell.correction(word)
+        corrected_words.append(corrected_word)
+    return ' '.join(corrected_words)
+
+# 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 = 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.text, pos_tag)
+            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'
+                elif token.pos_ == "NOUN" and token.tag_ == "NNS":  # Plural nouns
+                    synonym += 's' if not synonym.endswith('s') else ""
+                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 with enhanced accuracy
 def paraphrase_and_correct(text):
-    # Here should go all the paraphrasing and grammar correction logic.
-    return text  # For now just return the input
-
-# API Endpoint to create a new temporary link for Gradio interface
-@api_app.post("/generate-link/")
-async def generate_temporary_link(task: str):
-    # Check if the task is either 'ai-detection' or 'paraphrase'
-    if task not in ["ai-detection", "paraphrase"]:
-        raise HTTPException(status_code=400, detail="Invalid task type.")
-
-    # Create a unique link using UUID
-    link_id = str(uuid.uuid4())
-
-    # Set up Gradio interface based on task
-    if task == "ai-detection":
-        with gr.Blocks() as demo:
-            t1 = gr.Textbox(lines=5, label='Text')
-            button1 = gr.Button("🤖 Predict!")
-            label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
-            score1 = gr.Textbox(lines=1, label='Prob')
-
-            # Connect the prediction function to the button
-            button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
-
-    elif task == "paraphrase":
-        with gr.Blocks() as demo:
-            t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction')
-            button2 = gr.Button("🔄 Paraphrase and Correct")
-            result2 = gr.Textbox(lines=10, label='Corrected Text', placeholder="The corrected text will appear here...")
-
-            # Connect the paraphrasing and correction function to the button
-            button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
-
-    # Launch Gradio and get the link
-    demo_url = demo.launch(share=True, prevent_thread_lock=True)
-
-    # Save the generated link in memory (temporary)
-    temporary_links[link_id] = {"task": task, "url": demo_url}
-
-    # Return the link to the user
-    return {"link_id": link_id, "url": demo_url}
-
-# API Endpoint to get the status or result via the generated link
-@api_app.get("/get-link/{link_id}")
-async def get_temporary_link(link_id: str):
-    # Check if the link exists
-    if link_id not in temporary_links:
-        raise HTTPException(status_code=404, detail="Link not found.")
-
-    # Retrieve the link details
-    link_details = temporary_links[link_id]
-    return {"link": link_details["url"]}
-
-# Run the FastAPI app
-if __name__ == "__main__":
-    uvicorn.run(api_app, host="0.0.0.0", port=8000)
+    # Remove meaningless or redundant words first
+    cleaned_text = remove_redundant_words(text)
+    
+    # Capitalize sentences and nouns
+    paraphrased_text = capitalize_sentences_and_nouns(cleaned_text)
+    
+    # Ensure first letter of each sentence is capitalized
+    paraphrased_text = force_first_letter_capital(paraphrased_text)
+    
+    # Apply grammatical corrections
+    paraphrased_text = correct_article_errors(paraphrased_text)
+    paraphrased_text = correct_singular_plural_errors(paraphrased_text)
+    paraphrased_text = correct_tense_errors(paraphrased_text)
+    paraphrased_text = correct_double_negatives(paraphrased_text)
+    paraphrased_text = ensure_subject_verb_agreement(paraphrased_text)
+    
+    # Rephrase with synonyms while maintaining grammatical forms
+    paraphrased_text = rephrase_with_synonyms(paraphrased_text)
+    
+    # Correct spelling errors
+    paraphrased_text = correct_spelling(paraphrased_text)
+    
+    return paraphrased_text
+
+# Gradio app setup with two tabs
+with gr.Blocks() as demo:
+    with gr.Tab("AI Detection"):
+        t1 = gr.Textbox(lines=5, label='Text')
+        button1 = gr.Button("🤖 Predict!")
+        label1 = gr.Textbox(lines=1, label='Predicted Label 🎃')
+        score1 = gr.Textbox(lines=1, label='Prob')
+
+        # Connect the prediction function to the button
+        button1.click(fn=predict_en, inputs=t1, outputs=[label1, score1])
+
+    with gr.Tab("Paraphrasing & Grammar Correction"):
+        t2 = gr.Textbox(lines=5, label='Enter text for paraphrasing and grammar correction')
+        button2 = gr.Button("🔄 Paraphrase and Correct")
+        result2 = gr.Textbox(lines=10, label='Corrected Text', placeholder="The corrected text will appear here...")
+
+        # Connect the paraphrasing and correction function to the button
+        button2.click(fn=paraphrase_and_correct, inputs=t2, outputs=result2)
+
+demo.launch(share=True)  # Share=True to create a public link