app/utils/validators.py

"""Validation utilities for generated code."""

import ast
import os
from pathlib import Path
from typing import List, Optional


def validate_python_syntax(file_path: Path) -> tuple[bool, Optional[str]]:
    """Check if a Python file has valid syntax."""
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            content = f.read()
        ast.parse(content)
        return True, None
    except SyntaxError as e:
        return False, f"Syntax error at line {e.lineno}: {e.msg}"
    except Exception as e:
        return False, str(e)


def validate_required_files_exist(repo_dir: Path, required_files: List[str]) -> List[str]:
    """Check that required files exist in the repository."""
    missing = []
    for file in required_files:
        if not (repo_dir / file).exists():
            missing.append(file)
    return missing


def validate_imports(file_path: Path) -> List[str]:
    """Check for likely missing imports (basic heuristic)."""
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            content = f.read()
        tree = ast.parse(content)

        defined_names = set()
        used_names = set()

        for node in ast.walk(tree):
            if isinstance(node, ast.FunctionDef):
                defined_names.add(node.name)
            elif isinstance(node, ast.Name) and isinstance(node.ctx, ast.Load):
                used_names.add(node.id)
            elif isinstance(node, ast.Attribute):
                # Capture attribute access like os.path
                if isinstance(node.value, ast.Name):
                    used_names.add(f"{node.value.id}.{node.attr}")

        undefined = used_names - defined_names - set(__builtins__.keys())
        # Filter out likely imports from standard library and common packages
        common_imports = {
            "os",
            "sys",
            "json",
            "logging",
            "typing",
            "Path",
            "Optional",
            "List",
            "Dict",
            "Any",
            "Union",
            "Callable",
            "subprocess",
            "requests",
            "fastapi",
            "gradio",
            "uvicorn",
        }
        possibly_undefined = [n for n in undefined if n not in common_imports]

        return possibly_undefined
    except Exception:
        return []


def validate_file_not_empty(file_path: Path) -> bool:
    """Check that a file has non-empty content."""
    return file_path.exists() and file_path.stat().st_size > 10


def validate_has_main_block(file_path: Path) -> bool:
    """Check if Python file has a main execution block."""
    try:
        with open(file_path, "r", encoding="utf-8") as f:
            content = f.read()
        tree = ast.parse(content)
        for node in ast.walk(tree):
            if isinstance(node, ast.If):
                if (
                    isinstance(node.test, ast.Compare)
                    and any(isinstance(op, ast.Eq) for op in node.test.ops)
                    and any(
                        isinstance(comp, ast.Name) and comp.id == "__name__"
                        for comp in node.test.comparators
                    )
                ):
                    return True
        return False
    except Exception:
        return False