Refactor markdown processing in posts API; replace unified with marked and DOMPurify for improved HTML sanitization and performance.

src/app/api/posts/route.ts

@@ -2,13 +2,9 @@ import { NextResponse } from 'next/server';
 import fs from 'fs';
 import path from 'path';
 import matter from 'gray-matter';
-
-import { unified } from 'unified';
-import remarkParse from 'remark-parse';
-import remarkGfm from 'remark-gfm';
-import remarkRehype from 'remark-rehype';
-import rehypeRaw from 'rehype-raw';
-import rehypeStringify from 'rehype-stringify';
+import { marked } from 'marked';
+import DOMPurify from 'dompurify';
+import { JSDOM } from 'jsdom';
 
 const postsDirectory = path.join(process.cwd(), 'posts');
 
@@ -35,17 +31,35 @@ async function getPostByPath(filePath: string, relPath: string) {
 
   let processedContent = '';
   try {
-    const file = await unified()
-      .use(remarkParse as any)
-      .use(remarkGfm)
-      .use(remarkRehype, { allowDangerousHtml: true })
-      .use(rehypeRaw)
-      .use(rehypeStringify)
-      .process(content);
-
-    processedContent = file.toString();
+    marked.setOptions({
+      gfm: true,
+      breaks: true
+    });
+    const rawHtml = marked.parse(content);
+    const window = new JSDOM('').window;
+    const purify = DOMPurify(window);
+    processedContent = purify.sanitize(rawHtml as string, {
+      ALLOWED_TAGS: [
+        'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
+        'p', 'a', 'ul', 'ol', 'li', 'blockquote',
+        'pre', 'code', 'em', 'strong', 'del',
+        'hr', 'br', 'img', 'table', 'thead', 'tbody',
+        'tr', 'th', 'td', 'div', 'span', 'iframe'
+      ],
+      ALLOWED_ATTR: [
+        'class', 'id', 'style',
+        'href', 'target', 'rel',
+        'src', 'alt', 'title', 'width', 'height',
+        'frameborder', 'allowfullscreen'
+      ],
+      ALLOWED_URI_REGEXP: /^(?:(?:(?:f|ht)tps?|mailto|tel|callto|cid|xmpp):|[^a-z]|[a-z+.\-]+(?:[^a-z+.\-:]|$))/i
+    });
   } catch (err) {
     console.error(`Error processing markdown for ${relPath}:`, err);
+    processedContent = `<div class="error-message">
+      <p>Error processing markdown content. Please check the console for details.</p>
+      <pre>${err instanceof Error ? err.message : 'Unknown error'}</pre>
+    </div>`;
   }
 
   return {