python_analyzer.py

"""

PYTHON CODE ANALYZER & IMPROVER

Analyzes Python code, learns patterns, generates better Python code

"""

import ast
import re
import logging
from typing import Dict, List, Optional, Tuple, Any
import json
import os

logger = logging.getLogger(__name__)

class PythonAnalyzer:
    """Analyzes and learns from Python code"""
    
    def __init__(self):
        self.learned_patterns = {}
        self.code_quality_metrics = {}
        self.best_practices = self._initialize_best_practices()
        self.load_learned_patterns()
    
    def _initialize_best_practices(self) -> Dict:
        """Initialize Python best practices database"""
        return {
            'naming_conventions': {
                'functions': r'^[a-z_][a-z0-9_]*$',
                'classes': r'^[A-Z][a-zA-Z0-9]*$',
                'constants': r'^[A-Z_][A-Z0-9_]*$',
                'variables': r'^[a-z_][a-z0-9_]*$',
            },
            'anti_patterns': [
                {'pattern': r'import \*', 'message': 'Avoid wildcard imports'},
                {'pattern': r'except:', 'message': 'Avoid bare except clauses'},
                {'pattern': r'== True', 'message': 'Use "if value:" instead of "== True"'},
                {'pattern': r'== False', 'message': 'Use "if not value:" instead of "== False"'},
                {'pattern': r'== None', 'message': 'Use "if value is None:" instead'},
            ],
            'style_checks': [
                'Use 4 spaces for indentation',
                'Use list comprehensions instead of loops',
                'Use context managers (with statements)',
                'Add docstrings to all functions',
                'Use type hints for function parameters',
            ]
        }
    
    def analyze_python_code(self, code: str) -> Dict:
        """Comprehensive analysis of Python code"""
        
        analysis = {
            'syntax_valid': False,
            'structure': {},
            'quality_score': 0.0,
            'issues': [],
            'suggestions': [],
            'complexity': 0,
        }
        
        try:
            tree = ast.parse(code)
            analysis['syntax_valid'] = True
            
            # Extract structure
            analysis['structure'] = self._extract_structure(tree)
            
            # Check for issues
            analysis['issues'] = self._check_code_issues(code)
            
            # Generate suggestions
            analysis['suggestions'] = self._generate_suggestions(code, tree)
            
            # Calculate complexity
            analysis['complexity'] = self._calculate_complexity(tree)
            
            # Quality score
            analysis['quality_score'] = self._calculate_quality_score(analysis)
            
            # Learn from this code
            self._learn_from_code(code, analysis)
            
        except SyntaxError as e:
            analysis['syntax_valid'] = False
            analysis['issues'].append(f"Syntax Error: {str(e)}")
        except Exception as e:
            analysis['issues'].append(f"Analysis Error: {str(e)}")
        
        return analysis
    
    def _extract_structure(self, tree: ast.AST) -> Dict:
        """Extract code structure"""
        structure = {
            'functions': [],
            'classes': [],
            'imports': [],
            'global_vars': []
        }
        
        for node in ast.walk(tree):
            if isinstance(node, ast.FunctionDef):
                structure['functions'].append({
                    'name': node.name,
                    'args': len(node.args.args),
                    'lines': node.end_lineno - node.lineno if node.end_lineno else 0,
                    'docstring': ast.get_docstring(node) is not None
                })
            elif isinstance(node, ast.ClassDef):
                structure['classes'].append({
                    'name': node.name,
                    'methods': len([n for n in node.body if isinstance(n, ast.FunctionDef)]),
                    'has_init': any(isinstance(n, ast.FunctionDef) and n.name == '__init__' for n in node.body)
                })
            elif isinstance(node, ast.Import) or isinstance(node, ast.ImportFrom):
                structure['imports'].append(self._extract_import(node))
        
        return structure
    
    def _extract_import(self, node) -> str:
        """Extract import statement"""
        if isinstance(node, ast.Import):
            return ', '.join(alias.name for alias in node.names)
        elif isinstance(node, ast.ImportFrom):
            module = node.module or ''
            names = ', '.join(alias.name for alias in node.names)
            return f"from {module} import {names}"
        return ""
    
    def _check_code_issues(self, code: str) -> List[str]:
        """Check for code issues"""
        issues = []
        
        # Check anti-patterns
        for anti_pattern in self.best_practices['anti_patterns']:
            if re.search(anti_pattern['pattern'], code):
                issues.append(anti_pattern['message'])
        
        # Check naming conventions
        functions = re.findall(r'def\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*\(', code)
        for func_name in functions:
            if not re.match(self.best_practices['naming_conventions']['functions'], func_name):
                issues.append(f"Function '{func_name}' doesn't follow naming convention")
        
        # Check for missing docstrings
        if 'def ' in code and '"""' not in code and "'''" not in code:
            issues.append("Missing docstrings in functions")
        
        return issues
    
    def _generate_suggestions(self, code: str, tree: ast.AST) -> List[str]:
        """Generate improvement suggestions"""
        suggestions = []
        
        # Check for loop patterns that could be list comprehensions
        for node in ast.walk(tree):
            if isinstance(node, ast.For):
                suggestions.append("Consider using list comprehension instead of for loop")
        
        # Check for proper exception handling
        for node in ast.walk(tree):
            if isinstance(node, ast.ExceptHandler) and node.type is None:
                suggestions.append("Specify exception type instead of bare except")
        
        # Check for type hints (Python 3.5+)
        for node in ast.walk(tree):
            if isinstance(node, ast.FunctionDef) and not node.returns:
                suggestions.append(f"Add return type hint to function '{node.name}'")
        
        return suggestions
    
    def _calculate_complexity(self, tree: ast.AST) -> int:
        """Calculate cyclomatic complexity"""
        complexity = 1
        for node in ast.walk(tree):
            if isinstance(node, (ast.If, ast.While, ast.For, ast.ExceptHandler)):
                complexity += 1
        return complexity
    
    def _calculate_quality_score(self, analysis: Dict) -> float:
        """Calculate overall code quality score (0-100)"""
        score = 100.0
        
        # Subtract points for issues
        score -= len(analysis['issues']) * 10
        
        # Subtract points for complexity
        if analysis['complexity'] > 5:
            score -= (analysis['complexity'] - 5) * 2
        
        # Add bonus for structure
        structure = analysis['structure']
        if structure['functions']:
            score += min(5, len(structure['functions']))
        if structure['classes']:
            score += min(5, len(structure['classes']))
        
        return max(0, min(100, score))
    
    def _learn_from_code(self, code: str, analysis: Dict):
        """Learn patterns from Python code"""
        
        # Store patterns for future reference
        key = f"pattern_{hash(code) % 10000}"
        self.learned_patterns[key] = {
            'code_snippet': code[:500],
            'quality': analysis['quality_score'],
            'complexity': analysis['complexity'],
            'structure': analysis['structure'],
            'issues': analysis['issues']
        }
    
    def improve_python_code(self, code: str) -> Dict:
        """Generate improved version of Python code"""
        
        analysis = self.analyze_python_code(code)
        
        if not analysis['syntax_valid']:
            return {
                'success': False,
                'error': 'Code has syntax errors',
                'original': code
            }
        
        improved = code
        improvements = []
        
        # Apply improvements based on analysis
        
        # 1. Fix common patterns
        if 'Avoid bare except clauses' in analysis['issues']:
            improved = improved.replace('except:', 'except Exception:')
            improvements.append('Fixed bare except clause')
        
        # 2. Add docstrings if missing
        if 'Missing docstrings in functions' in analysis['issues']:
            improved = self._add_docstrings(improved)
            improvements.append('Added docstrings')
        
        # 3. Suggest list comprehensions
        if any('list comprehension' in s for s in analysis['suggestions']):
            improved = self._suggest_list_comprehensions(improved)
            improvements.append('Suggested list comprehensions')
        
        # 4. Add type hints
        improved = self._add_type_hints(improved)
        improvements.append('Added type hints')
        
        return {
            'success': True,
            'original': code,
            'improved': improved,
            'analysis': analysis,
            'improvements': improvements,
            'quality_before': 0,
            'quality_after': analysis['quality_score']
        }
    
    def _add_docstrings(self, code: str) -> str:
        """Add docstrings to functions"""
        improved = code
        functions = re.findall(r'def\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*\((.*?)\):', code)
        
        for func_name, args in functions:
            if '"""' not in code:
                docstring = f'\n    """{func_name}.\n    \n    Args:\n        {args}\n    """\n    '
                improved = improved.replace(
                    f'def {func_name}({args}):',
                    f'def {func_name}({args}):{docstring}'
                )
        
        return improved
    
    def _add_type_hints(self, code: str) -> str:
        """Add type hints to functions"""
        improved = code
        
        # Simple type hint addition (can be enhanced)
        improved = re.sub(
            r'def\s+(\w+)\s*\(([^)]*)\)\s*:',
            r'def \1(\2) -> Any:',
            improved
        )
        
        return improved
    
    def _suggest_list_comprehensions(self, code: str) -> str:
        """Suggest list comprehensions instead of loops"""
        # This would require more complex parsing
        return code
    
    def generate_python_from_requirement(self, requirement: str) -> Dict:
        """Generate Python code from natural language requirement"""
        
        templates = {
            'function': '''def {name}({args}):

    """{description}"""

    # TODO: Implement function

    pass''',
            
            'class': '''class {name}:

    """Class for {description}"""

    

    def __init__(self):

        """Initialize {name}"""

        pass

    

    def method(self):

        """Class method"""

        pass''',
            
            'loop': '''for item in items:

    # Process item

    print(item)''',
            
            'request': '''import requests



def fetch_data(url):

    """Fetch data from URL"""

    try:

        response = requests.get(url)

        response.raise_for_status()

        return response.json()

    except requests.RequestException as e:

        print(f"Error: {e}")

        return None''',
            
            'file_operation': '''def read_file(filepath):

    """Read file safely"""

    try:

        with open(filepath, 'r', encoding='utf-8') as f:

            return f.read()

    except FileNotFoundError:

        print(f"File not found: {filepath}")

        return None''',
        }
        
        # Select appropriate template
        requirement_lower = requirement.lower()
        
        selected_template = 'function'  # Default
        
        if 'class' in requirement_lower:
            selected_template = 'class'
        elif 'loop' in requirement_lower or 'iterate' in requirement_lower:
            selected_template = 'loop'
        elif 'request' in requirement_lower or 'fetch' in requirement_lower or 'api' in requirement_lower:
            selected_template = 'request'
        elif 'file' in requirement_lower or 'read' in requirement_lower or 'write' in requirement_lower:
            selected_template = 'file_operation'
        
        code_template = templates[selected_template]
        
        return {
            'success': True,
            'code': code_template,
            'template_used': selected_template,
            'requirement': requirement,
            'quality': 'template',
            'needs_customization': True
        }
    
    def load_learned_patterns(self):
        """Load previously learned patterns"""
        try:
            pattern_file = 'noahski_data/python_patterns.json'
            if os.path.exists(pattern_file):
                with open(pattern_file, 'r', encoding='utf-8') as f:
                    self.learned_patterns = json.load(f)
                logger.info(f"Loaded {len(self.learned_patterns)} Python patterns")
        except Exception as e:
            logger.error(f"Error loading patterns: {e}")
    
    def save_learned_patterns(self):
        """Save learned patterns for future use"""
        try:
            os.makedirs('noahski_data', exist_ok=True)
            pattern_file = 'noahski_data/python_patterns.json'
            with open(pattern_file, 'w', encoding='utf-8') as f:
                json.dump(self.learned_patterns, f, indent=2)
            logger.info(f"Saved {len(self.learned_patterns)} Python patterns")
        except Exception as e:
            logger.error(f"Error saving patterns: {e}")


# Global instance
_python_analyzer = None

def get_python_analyzer() -> PythonAnalyzer:
    """Get or create global Python analyzer"""
    global _python_analyzer
    if _python_analyzer is None:
        _python_analyzer = PythonAnalyzer()
    return _python_analyzer