package com.ruoyi.cms.util;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.safety.Safelist;

/**
 * 富文本 HTML 白名单清理。
 *
 * <p>保留新闻正文所需的常见排版、链接、图片和表格标签，移除脚本、事件属性、
 * iframe 以及 javascript/data 等危险协议。</p>
 */
public final class RichTextSanitizer {

    private static final Safelist NEWS_CONTENT_SAFELIST = Safelist.relaxed()
            .addTags("figure", "figcaption", "s")
            .addAttributes("a", "target", "rel")
            .addAttributes("img", "loading")
            .addAttributes("table", "border", "cellpadding", "cellspacing")
            .addProtocols("a", "href", "http", "https", "mailto")
            .addProtocols("img", "src", "http", "https");

    private static final Document.OutputSettings OUTPUT_SETTINGS = new Document.OutputSettings()
            .prettyPrint(false);

    private RichTextSanitizer() {
    }

    /**
     * 清理并规范化富文本 HTML。
     */
    public static String clean(String html) {
        if (html == null) {
            return null;
        }
        return Jsoup.clean(html, "", NEWS_CONTENT_SAFELIST, OUTPUT_SETTINGS).trim();
    }

    /**
     * 判断清理后的正文是否包含文字或图片内容。
     */
    public static boolean hasContent(String cleanedHtml) {
        if (cleanedHtml == null || cleanedHtml.trim().isEmpty()) {
            return false;
        }
        Document document = Jsoup.parseBodyFragment(cleanedHtml);
        return !document.text().trim().isEmpty() || !document.select("img").isEmpty();
    }
}