Update app.py

app.py

@@ -62,22 +62,28 @@ def generate_response(user_input):
         response = chat_session.send_message(user_input)
         return response.text
     except Exception as e:
-        return f"Error: {e}"
+        return f"Error in generating response: {str(e)}"
+
+def validate_and_fix_code(code):
+    lines = code.split('\n')
+    fixed_lines = []
+    for line in lines:
+        # Check for unterminated string literals
+        if line.count('"') % 2 != 0 and line.count("'") % 2 != 0:
+            line += '"'  # Add a closing quote if needed
+        fixed_lines.append(line)
+    return '\n'.join(fixed_lines)
 
 def optimize_code(code):
-    # Use abstract syntax tree for advanced code analysis
+    # Validate and fix the code first
+    fixed_code = validate_and_fix_code(code)
+    
     try:
-        tree = ast.parse(code)
-        analyzer = CodeAnalyzer()
-        analyzer.visit(tree)
-        
-        # Apply code transformations based on analysis
-        transformer = CodeTransformer(analyzer.get_optimizations())
-        optimized_tree = transformer.visit(tree)
-        
-        optimized_code = ast.unparse(optimized_tree)
+        tree = ast.parse(fixed_code)
+        # Placeholder for actual optimization logic
+        optimized_code = fixed_code
     except SyntaxError as e:
-        return code, f"SyntaxError: {str(e)}"
+        return fixed_code, f"SyntaxError: {str(e)}"
     
     # Run pylint for additional suggestions
     with open("temp_code.py", "w") as file:
@@ -94,19 +100,6 @@ def fetch_from_github(query):
         return response.json()['items'][:5]  # Return top 5 results
     return []
 
-def interact_with_api(api_url):
-    response = requests.get(api_url)
-    return response.json()
-
-def train_ml_model(code_data):
-    df = pd.DataFrame(code_data)
-    X = df.drop('target', axis=1)
-    y = df['target']
-    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
-    model = RandomForestClassifier(n_estimators=100, max_depth=10)
-    model.fit(X_train, y_train)
-    return model
-
 def analyze_code_quality(code):
     # Tokenize and encode the code
     inputs = tokenizer(code, return_tensors="pt", truncation=True, max_length=512, padding="max_length")
@@ -250,14 +243,15 @@ if st.button("Generate Advanced Code"):
     else:
         with st.spinner("Generating and analyzing code..."):
             completed_text = generate_response(prompt)
-            if "Error" in completed_text:
+            if "Error in generating response" in completed_text:
                 st.error(completed_text)
             else:
                 optimized_code, lint_results = optimize_code(completed_text)
                 
                 if "SyntaxError" in lint_results:
-                    st.warning(f"Syntax error detected: {lint_results}")
-                    st.code(completed_text)
+                    st.warning(f"Syntax error detected in the generated code. Attempting to fix...")
+                    st.code(optimized_code)
+                    st.info("Please review the code above. It may contain errors or be incomplete.")
                 else:
                     quality_score = analyze_code_quality(optimized_code)
                     st.success(f"Code generated and optimized successfully! Quality Score: {quality_score:.2f}")