/**
 * Sanitizer - HTML 净化器
 * 基于白名单策略，防御 XSS 攻击
 */

export const SAFE_URI_SCHEMES = new Set(['http:', 'https:', 'mailto:', 'tel:', 'ftp:', 'ftps:', 'xmpp:']);
export const SAFE_DATA_TYPES = new Set(['image/png', 'image/jpeg', 'image/gif', 'image/webp', 'image/svg+xml']);

const ALLOWED_TAGS = new Set([
    'a', 'abbr', 'b', 'blockquote', 'br', 'code', 'del', 'details', 'div',
    'dl', 'dt', 'dd', 'em', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr',
    'i', 'img', 'ins', 'kbd', 'li', 'ol', 'p', 'pre', 'q', 'rp', 'rt',
    'ruby', 's', 'samp', 'small', 'span', 'strike', 'strong', 'sub',
    'summary', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead',
    'tr', 'u', 'ul', 'var', 'input',
]);

const ALLOWED_ATTRS = new Set([
    'href', 'src', 'alt', 'title', 'width', 'height', 'align',
    'target', 'rel', 'class', 'id', 'type', 'checked', 'disabled',
    'start', 'value', 'scope', 'rowspan', 'colspan', 'lang',
]);

const DANGEROUS_PREFIXES = ['on', 'xlink:href', 'xmlns:'];

/**
 * 净化 HTML 字符串，移除危险标签和属性
 * @param {string} html - 原始 HTML
 * @returns {string} 净化后的 HTML
 */
export function sanitize(html) {
    try {
        const template = document.createElement('template');
        template.innerHTML = html;
        const root = template.content;

        // 删除注释节点
        const walker = document.createTreeWalker(root, NodeFilter.SHOW_COMMENT);
        const comments = [];
        while (walker.nextNode()) comments.push(walker.currentNode);
        comments.forEach(c => c.remove());

        // 遍历所有元素（先收集再处理，避免动态集合问题）
        const elements = [...root.querySelectorAll('*')];
        for (const el of elements) {
            if (!el.parentNode) continue;

            const tag = el.tagName.toLowerCase();

            if (!ALLOWED_TAGS.has(tag)) {
                while (el.firstChild) el.parentNode.insertBefore(el.firstChild, el);
                el.remove();
                continue;
            }

            // 清理属性
            for (const attr of [...el.attributes]) {
                const name = attr.name.toLowerCase();

                if (DANGEROUS_PREFIXES.some(p => name.startsWith(p))) {
                    el.removeAttribute(attr.name);
                    continue;
                }

                if (!ALLOWED_ATTRS.has(name)) {
                    el.removeAttribute(attr.name);
                    continue;
                }

                // URI 协议检查
                if ((name === 'href' || name === 'src' || name === 'action') && attr.value) {
                    const val = attr.value.trim().toLowerCase();
                    if (/^(javascript|vbscript|data|file):/i.test(val)) {
                        const mimeMatch = val.match(/^data:([^;,]+)/i);
                        if (!mimeMatch || !SAFE_DATA_TYPES.has(mimeMatch[1].toLowerCase())) {
                            el.removeAttribute(attr.name);
                        }
                    }
                }
            }
        }

        return root.innerHTML;
    } catch (e) {
        console.warn('[Sanitizer] 净化失败，返回原始文本:', e);
        return html;
    }
}