File size: 2,303 Bytes
f7601c8 9ac8247 98ba9be f7601c8 9ac8247 f7601c8 98ba9be 9ac8247 dd4f105 9ac8247 98ba9be 9ac8247 98ba9be 9ac8247 4c6b685 ac03c7a 9ac8247 98ba9be 9ac8247 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
import gradio as gr
import numpy as np
import tensorflow as tf
from tokenizers import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
import re
# Load trained tokenizer and model
tokenizer = Tokenizer.from_file("cr_tokenizer.json")
model = tf.keras.models.load_model("crv3.keras")
def replace_java_comments(code: str) -> str:
"""Replaces Java comments with placeholders."""
code = re.sub(r"//.*", " SINGLE_LINE_COMMENT ", code) # Replace single-line comments
code = re.sub(r"/\*[\s\S]*?\*/", " MULTI_LINE_COMMENT ", code) # Replace multi-line comments
return code.strip() # Keep indentation
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
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.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."
# Replace comments before tokenization
cleaned_code = replace_java_comments(code)
# Tokenize and predict
tokenized_code = tokenize_java_code(cleaned_code)
prediction = model.predict(tokenized_code)[0][0]
threshold = 0.52 # Increase the threshold for "Readable"
prediction = (prediction > threshold).astype(int) # Convert probabilities to binary
# Convert to readable/unreadable
return "Readable" if prediction > 0.5 else "Unreadable"
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 Classification"),
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() |