app.py

import nltk
from nltk.corpus import wordnet
import streamlit as st

# Download required NLTK resources if you haven't already
nltk.download('punkt')
nltk.download('wordnet')
nltk.download('averaged_perceptron_tagger')

def rewrite_content(text):
    # Tokenize the text
    tokens = nltk.word_tokenize(text)

    # Tag the tokens with their part-of-speech
    tagged_tokens = nltk.pos_tag(tokens)

    # Iterate over the tagged tokens and replace words with synonyms
    rewritten_text = []
    for token, tag in tagged_tokens:
        # Fetch synonyms for the word
        synonyms = wordnet.synsets(token)
        if synonyms:
            # Choose the first synonym
            synonym = synonyms[0].lemmas()[0].name()
            # Ensure the synonym is not the same as the original word
            if synonym != token:
                rewritten_text.append(synonym)
            else:
                rewritten_text.append(token)
        else:
            rewritten_text.append(token)

    # Join the rewritten tokens back into a string
    rewritten_content = ' '.join(rewritten_text)

    # Maintain paragraph structure
    paragraphs = text.split('\n')
    rewritten_paragraphs = []
    token_index = 0

    for paragraph in paragraphs:
        paragraph_tokens = nltk.word_tokenize(paragraph)
        rewritten_paragraph = ' '.join(rewritten_text[token_index:token_index + len(paragraph_tokens)])
        rewritten_paragraphs.append(rewritten_paragraph)
        token_index += len(paragraph_tokens)

    return '\n'.join(rewritten_paragraphs)

# Streamlit interface
st.title("Content Rewriter using NLTK")

# Text input for the content to be rewritten
input_text = st.text_area("Enter text to rewrite", height=200)

# Button to trigger content rewriting
if st.button("Rewrite"):
    if input_text:
        # Display rewritten content
        rewritten_text = rewrite_content(input_text)
        st.text_area("Rewritten text", rewritten_text, height=200)
    else:
        st.warning("Please enter some text to rewrite.")