"""URL validation utilities (backed by net_security.SSRFValidator)."""

import os

from yuxi.utils.net_security import SSRFPolicy, SSRFValidator

YUXI_URL_WHITELIST_ENV = "YUXI_URL_WHITELIST"


def _get_policy_from_env() -> SSRFPolicy:
    """从环境变量构建策略（兼容 YUXI_URL_WHITELIST）。"""
    whitelist = [d.strip() for d in os.environ.get(YUXI_URL_WHITELIST_ENV, "").split(",") if d.strip()]
    return SSRFPolicy(allowed_domains=whitelist)


def validate_url(url: str) -> tuple[bool, str]:
    """Validate if a URL is allowed (sync wrapper).

    Args:
        url: The URL to validate.

    Returns:
        A tuple of (is_valid, error_message).
        If is_valid is True, error_message will be empty.
    """
    if not url:
        return False, "URL cannot be empty"

    # 白名单为空时，URL 抓取功能禁用（保持原有行为）
    if not is_url_parsing_enabled():
        return False, "URL parsing feature is disabled"

    validator = SSRFValidator(_get_policy_from_env())
    allowed, reason = validator.validate_url_sync(url)
    if not allowed:
        return False, reason
    return True, ""


def is_url_parsing_enabled() -> bool:
    """Check if URL parsing is enabled (whitelist is configured)."""
    return bool(os.environ.get(YUXI_URL_WHITELIST_ENV, "").strip())


def get_whitelist_info() -> dict:
    """Get information about the current whitelist configuration."""
    whitelist = [d.strip() for d in os.environ.get(YUXI_URL_WHITELIST_ENV, "").split(",") if d.strip()]
    return {
        "enabled": len(whitelist) > 0,
        "domains": whitelist,
        "count": len(whitelist),
    }