code_analyzer.py

"""
PyPilot Code Analyzer - Advanced static analysis and quality metrics
"""
import ast
import astor
import radon
from radon import metrics, complexity
from radon.visitors import ComplexityVisitor
import lizard
import tempfile
import subprocess
import os

class PyPilotCodeAnalyzer:
    def __init__(self):
        self.analysis_results = {}
        
    def comprehensive_analysis(self, code_string):
        """Perform comprehensive code analysis"""
        analysis = {}
        
        try:
            # Parse AST
            tree = ast.parse(code_string)
            analysis['ast_info'] = self.analyze_ast(tree)
            
            # Code metrics
            analysis['metrics'] = self.calculate_metrics(code_string)
            
            # Complexity analysis
            analysis['complexity'] = self.analyze_complexity(code_string)
            
            # Security checks
            analysis['security'] = self.security_scan(code_string)
            
            # Code quality
            analysis['quality'] = self.quality_assessment(code_string)
            
        except Exception as e:
            analysis['error'] = str(e)
            
        return analysis
    
    def analyze_ast(self, tree):
        """Analyze Abstract Syntax Tree"""
        ast_info = {
            'imports': [],
            'functions': [],
            'classes': [],
            'variables': [],
            'structure': {}
        }
        
        for node in ast.walk(tree):
            if isinstance(node, ast.Import):
                for alias in node.names:
                    ast_info['imports'].append(alias.name)
            elif isinstance(node, ast.ImportFrom):
                ast_info['imports'].append(f"from {node.module}")
            elif isinstance(node, ast.FunctionDef):
                ast_info['functions'].append({
                    'name': node.name,
                    'args': [arg.arg for arg in node.args.args],
                    'lineno': node.lineno
                })
            elif isinstance(node, ast.ClassDef):
                ast_info['classes'].append({
                    'name': node.name,
                    'bases': [base.id for base in node.bases if hasattr(base, 'id')],
                    'lineno': node.lineno
                })
            elif isinstance(node, ast.Assign):
                for target in node.targets:
                    if hasattr(target, 'id'):
                        ast_info['variables'].append(target.id)
        
        return ast_info
    
    def calculate_metrics(self, code_string):
        """Calculate comprehensive code metrics"""
        with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
            f.write(code_string)
            temp_file = f.name
        
        try:
            # Use lizard for advanced metrics
            analysis = lizard.analyze_file(temp_file)
            
            metrics = {
                'lines_of_code': analysis.nloc,
                'token_count': analysis.token_count,
                'function_count': len(analysis.function_list),
                'average_complexity': analysis.average_cyclomatic_complexity,
                'maintainability_index': analysis.maintainability_index,
            }
            
            # Function-level metrics
            functions_metrics = []
            for func in analysis.function_list:
                functions_metrics.append({
                    'name': func.name,
                    'complexity': func.cyclomatic_complexity,
                    'lines': func.length,
                    'parameters': func.parameter_count
                })
            
            metrics['functions'] = functions_metrics
            
        finally:
            os.unlink(temp_file)
            
        return metrics
    
    def analyze_complexity(self, code_string):
        """Analyze code complexity using radon"""
        try:
            cc = complexity.cc_visit(code_string)
            complexity_data = []
            
            for block in cc:
                complexity_data.append({
                    'name': block.name,
                    'complexity': block.complexity,
                    'type': block.type,
                    'lineno': block.lineno
                })
            
            mi = metrics.mi_visit(code_string, True)
            
            return {
                'cyclomatic_complexity': complexity_data,
                'maintainability_index': mi,
                'halstead_metrics': metrics.h_visit(code_string)
            }
        except Exception as e:
            return {'error': str(e)}
    
    def security_scan(self, code_string):
        """Basic security vulnerability scan"""
        vulnerabilities = []
        
        security_patterns = [
            ('eval', 'Use of eval() function'),
            ('exec', 'Use of exec() function'),
            ('pickle.loads', 'Unsafe deserialization'),
            ('os.system', 'Potential command injection'),
            ('subprocess.call', 'Potential command injection'),
        ]
        
        for pattern, description in security_patterns:
            if pattern in code_string:
                vulnerabilities.append({
                    'type': 'security',
                    'description': description,
                    'severity': 'high'
                })
        
        return vulnerabilities
    
    def quality_assessment(self, code_string):
        """Assess code quality"""
        quality_score = 100
        
        # Check for common issues
        issues = []
        
        if len(code_string) > 1000:
            issues.append("File is too long")
            quality_score -= 10
            
        if code_string.count('\n') > 50:
            issues.append("Too many lines")
            quality_score -= 5
            
        # Check for commented code
        if code_string.count('#') > code_string.count('\n') * 0.3:
            issues.append("Too many comments")
            quality_score -= 5
            
        return {
            'quality_score': max(quality_score, 0),
            'issues': issues,
            'recommendations': self.generate_recommendations(issues)
        }
    
    def generate_recommendations(self, issues):
        """Generate improvement recommendations"""
        recommendations = []
        
        issue_solutions = {
            "File is too long": "Consider breaking into smaller functions or modules",
            "Too many lines": "Refactor into smaller, focused functions",
            "Too many comments": "Ensure comments are meaningful and not redundant"
        }
        
        for issue in issues:
            if issue in issue_solutions:
                recommendations.append(issue_solutions[issue])
                
        return recommendations

if __name__ == "__main__":
    analyzer = PyPilotCodeAnalyzer()
    
    # Test with sample code
    sample_code = """
def calculate_factorial(n):
    if n == 0:
        return 1
    else:
        return n * calculate_factorial(n-1)

def main():
    print(calculate_factorial(5))
    
if __name__ == "__main__":
    main()
    """
    
    results = analyzer.comprehensive_analysis(sample_code)
    print("🔍 Code Analysis Results:")
    print(f"Functions: {results['ast_info']['functions']}")
    print(f"Metrics: {results['metrics']}")
    print(f"Quality Score: {results['quality']['quality_score']}")