Final working bug fixer with fixed detection and suggestion

README.md

@@ -1,11 +1,10 @@
 ---
 title: Bug Fixer
-emoji: 🐞
+emoji: \ud83d\udc1e
 colorFrom: red
 colorTo: blue
 sdk: gradio
-sdk_version: 4.17.0
+sdk_version: 4.33.0
 app_file: app_ui.py
 pinned: false
----
-# Bug Fixer
+---

app_ui.py

@@ -2,20 +2,26 @@ import gradio as gr
 from bug_detector import detect_bug
 from fix_generator import generate_fix
 
-def process_code(code):
+def bug_fixer(code):
     bug_status = detect_bug(code)
-    if bug_status == "buggy":
-        fixed = generate_fix(code)
-        return fixed
-    return "Code looks correct!"
+    fixed_code = generate_fix(code)
+    return bug_status, fixed_code
 
-iface = gr.Interface(
-    fn=process_code,
-    inputs=gr.Textbox(lines=10, label="Enter Buggy Code"),
-    outputs=gr.Textbox(label="Suggested Fix"),
-    title="Bug Detection and Fixing Tool",
-    description="Enter your Python code to detect and fix simple bugs."
-)
+title = "\ud83d\udd27 Bug Detection and Fixing Tool"
 
-iface.launch()
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+        # \ud83d\udd27 Bug Detection and Fixing Tool
+        **Final Year Project - Guided by: Prof. Alakananda K P**  
+        **Team: Akanksha K P and Divyashree N**
+    """)
 
+    code_input = gr.Textbox(lines=8, label="Enter Buggy Code")
+    bug_output = gr.Textbox(label="Detected Bug")
+    fix_output = gr.Textbox(label="Suggested Fix")
+    btn = gr.Button("Detect and Fix")
+
+    btn.click(fn=bug_fixer, inputs=code_input, outputs=[bug_output, fix_output])
+
+demo.launch()
+#for the gradio user interface

bug_detector.py

@@ -1,11 +1,20 @@
 import torch
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
+# Load pre-trained CodeBERT model
 model = AutoModelForSequenceClassification.from_pretrained("microsoft/codebert-base", num_labels=2)
 tokenizer = AutoTokenizer.from_pretrained("microsoft/codebert-base")
 
 def detect_bug(code):
     inputs = tokenizer(code, return_tensors="pt", truncation=True, padding=True)
     outputs = model(**inputs)
-    probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
-    return "buggy" if probs[0][1] > probs[0][0] else "correct"
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    return "buggy" if probabilities[0][1] > probabilities[0][0] else "correct"
+
+# Optional test
+if __name__ == "__main__":
+    sample = "def multiply(a, b): return a + b"
+    print(detect_bug(sample))
+
+#detects if there's a bug in code
+

fix_generator.py

@@ -1,6 +1,19 @@
 def generate_fix(code):
-    # Dummy fix: add colon if missing, fix print
-    fixed_code = code.replace("print ", "print(")
-    if "print(" in fixed_code and not fixed_code.strip().endswith(")"):
-        fixed_code += ")"
-    return fixed_code
+    lines = code.split("\n")
+    fixed_lines = []
+    for line in lines:
+        line = line.strip()
+        if line.startswith("print ") and not line.startswith("print("):
+            content = line[6:].strip()
+            fixed_lines.append(f"print({content})")
+        else:
+            fixed_lines.append(line)
+    return "\n".join(fixed_lines)
+# Optional test
+if __name__ == "__main__":
+    buggy = "a = input()\nprint a"
+    print(generate_fix(buggy))
+
+
+
+#genrate the fixed version of code using an ML Model