from __future__ import annotations

import ast
import importlib.util
import re
from pathlib import Path


def _load_agent_module():
    agent_path = Path(__file__).resolve().parents[1] / "agent.py"
    spec = importlib.util.spec_from_file_location("agent", agent_path)
    assert spec is not None and spec.loader is not None
    module = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(module)
    return module


def _render_script() -> str:
    module = _load_agent_module()
    return module._render_scraper_script(
        {
            "url": "https://example.com/",
            "selectors": {"title": "title"},
            "max_pages": 1,
            "wait_seconds": 0,
            "output_format": "json",
            "headless": True,
            "user_agent": "SmokeTest",
            "respect_robots": True,
            "rate_limit_seconds": 0,
            "screenshot": False,
            "output_dir": "/workspace/outputs/seleniumbase-website-scraper",
        }
    )


def test_render_scraper_script_parses_as_python_35() -> None:
    script = _render_script()
    ast.parse(script, feature_version=(3, 5))


def test_render_scraper_script_has_no_forbidden_modern_syntax_markers() -> None:
    script = _render_script()

    numeric_underscore_literal = re.compile(r"(?<![A-Za-z0-9_])\d+(?:_\d+)+(?![A-Za-z0-9_])")
    f_string_prefix = re.compile(r"(?<![A-Za-z0-9_])(?:[fF]|[rR][fF]|[fF][rR])(['\"])")

    assert numeric_underscore_literal.findall(script) == []
    assert f_string_prefix.findall(script) == []
    assert "2_000_000" not in script
    assert "response.read(2000000)" in script
    assert ":=" not in script
    assert "pathlib" not in script


if __name__ == "__main__":
    test_render_scraper_script_parses_as_python_35()
    test_render_scraper_script_has_no_forbidden_modern_syntax_markers()
    print("smoke ok: rendered scraper script parses as Python 3.5 and contains no forbidden markers")