app.py

import gradio as gr
import numpy as np
import tensorflow as tf
from tokenizers import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

# Load trained tokenizer and model
tokenizer = Tokenizer.from_file("cr_tokenizer.json")
model = tf.keras.models.load_model("crv3.keras")

# Tokenization function
def tokenize_java_code(code: str, max_length=100):
    """Tokenizes and pads Java code for model input."""
    encoded = tokenizer.encode(code).ids
    padded_sequence = pad_sequences([encoded], maxlen=max_length, padding="post")[0]
    return np.array(padded_sequence).reshape(1, -1)  # Ensure correct shape for model

# Prediction function
def classify_code(input_text, input_file):
    """Classifies Java code readability based on user input."""
    # Load Java file if provided
    if input_file is not None:
        code = input_file.read().decode("utf-8")  # Read Java file as text
    else:
        code = input_text  # Use text input

    if not code.strip():  # Ensure input is not empty
        return "Please provide a Java code snippet."

    # Tokenize and predict
    tokenized_code = tokenize_java_code(code)
    prediction = model.predict(tokenized_code)[0][0]

    # Convert to readable/unreadable
    return "Readable" if prediction > 0.5 else "Unreadable"

# Create Gradio interface
gr.Interface(
    fn=classify_code,
    inputs=[
        gr.Textbox(lines=10, placeholder="Paste Java code here...", label="Java Code Snippet"),
        gr.File(type="binary", label="Upload Java File (.java)")
    ],
    outputs=gr.Text(label="Readability Prediction"),
    title="Java Code Readability Classifier",
    description="Upload a Java file or paste a Java code snippet to check if it's readable or unreadable.",
    allow_flagging="never"
).launch()