Resolved merge conflicts from Hugging Face

Dockerfile

@@ -0,0 +1,17 @@
+# Use Python as the base image
+FROM python:3.9
+
+# Set working directory
+WORKDIR /app
+
+# Copy project files
+COPY . /app
+
+# Install dependencies
+RUN pip install flask torch transformers
+
+# Expose the API port
+EXPOSE 5000
+
+# Start Flask server
+CMD ["python", "app.py"]

README.md

@@ -1,3 +1,14 @@
 # Bug Fixer
-
 Bug Fixer is a Gradio-based web tool that uses the CodeT5+ model to automatically detect and fix bugs in Python code. Built using Hugging Face Transformers and deployable via Hugging Face Spaces.
+---
+title: Bug Fixer - CodeT5
+emoji: 🧠
+colorFrom: pink
+colorTo: purple
+sdk: gradio
+sdk_version: 4.33.0
+app_file: app_ui.py
+pinned: false
+---
+
+

app.py

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 import gradio as gr
 from bug_detector import fix_code
 
@@ -10,3 +11,44 @@ gr.Interface(
     outputs=gr.Textbox(label="Suggested Fixed Code"),
     title="Code Fixer using CodeT5+"
 ).launch()
+=======
+from flask import Flask, request, jsonify
+from flask_cors import CORS  # Fix CORS issue
+import torch
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+
+app = Flask(__name__)
+CORS(app)  # Enable CORS
+
+# Load CodeBERT model
+tokenizer = RobertaTokenizer.from_pretrained("microsoft/codebert-base")
+model = RobertaForSequenceClassification.from_pretrained("microsoft/codebert-base")
+
+@app.route("/")
+def home():
+    return "Bug Detection and Fixing API is running!"
+
+@app.route("/detect", methods=["POST"])
+def detect_bug():
+    try:
+        data = request.get_json()
+        code = data.get("code", "")
+
+        if not code:
+            return jsonify({"error": "No code provided"}), 400
+
+        # Tokenize and classify
+        inputs = tokenizer(code, return_tensors="pt", truncation=True, padding=True)
+        outputs = model(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"])
+        prediction = torch.argmax(outputs.logits, dim=1).item()
+
+        bug_status = "buggy" if prediction == 1 else "clean"
+
+        return jsonify({"status": bug_status})
+    
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500  # Handle errors properly
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5000)  # Ensure compatibility with Docker
+>>>>>>> 22b22edd4386cff48f5ad4c4325e1f8524238b52

app_ui.py

@@ -0,0 +1,18 @@
+import gradio as gr
+from full_code_fixer import fix_code
+
+def fix_script(code):
+    fixed = fix_code(code)
+    return "Analyzed", fixed
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🛠️ Bug Detection and Fixing Tool - Full Script Version")
+    code_input = gr.Textbox(lines=20, label="Paste Your Python Code Here")
+    bug_status = gr.Textbox(label="Status")
+    fixed_code = gr.Textbox(lines=20, label="Suggested Fix")
+
+    gr.Button("Detect and Fix").click(fix_script, inputs=code_input, outputs=[bug_status, fixed_code])
+
+demo.launch()
+
+#for the gradio user interface

bug-fixer

@@ -0,0 +1 @@
+Subproject commit 0469b937d3a712bd7bcdcf362bed99e60ad7e37b

bug_detector.py

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import torch
 
@@ -12,3 +13,24 @@ def fix_code(code):
     output = model.generate(inputs["input_ids"], max_length=256)
     fixed_code = tokenizer.decode(output[0], skip_special_tokens=True)
     return fixed_code.strip()
+=======
+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)
+    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
+
+>>>>>>> 22b22edd4386cff48f5ad4c4325e1f8524238b52

fix_generator.py

@@ -0,0 +1,16 @@
+def generate_fix(code):
+    lines = code.split('\n')
+    fixed_lines = []
+    for line in lines:
+        stripped = line.strip()
+        # Fix print statements missing parentheses
+        if stripped.startswith("print ") and "(" not in stripped:
+            expression = stripped[6:]
+            fixed_line = f"print({expression})"
+            fixed_lines.append(fixed_line)
+        else:
+            fixed_lines.append(line)
+    return "\n".join(fixed_lines)
+
+
+#genrate the fixed version of code using an ML Model

full_code_fixer.py

@@ -0,0 +1,18 @@
+# full_code_fixer.py
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_name = "Salesforce/codet5-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+def fix_code(code):
+    input_text = f"fix Python: {code}"
+    inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)
+    outputs = model.generate(**inputs, max_length=512, num_beams=4, early_stopping=True)
+    fixed_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return fixed_code
+
+# Optional test
+if __name__ == "__main__":
+    buggy_code = "def add(a,b):\n return a*b"  # wrong logic
+    print(fix_code(buggy_code))

requirements.txt

@@ -0,0 +1,5 @@
+flask
+flask-cors
+torch
+transformers
+gradio