From 2297ba8b4df219a07a24bb10c36bd6c32eb2cd6c Mon Sep 17 00:00:00 2001
From: User <user@example.com>
Date: Sat, 21 Feb 2026 22:38:44 +0800
Subject: [PATCH] fix: properly strip HTML tags and resolve entities in feed
 article summaries

Fixes #146

The parseTextFromHtml function was using document.textContent directly on
the parsed HTML document, which could leave raw HTML tags and unresolved
entities in feed article summaries.

Changes:
- Extract text from body element to avoid document wrapper artifacts
- Collapse multiple whitespace/newlines into single spaces for cleaner output
- Add early return for empty/whitespace-only input
- Use optional chaining for safer null handling
---
 lib/feed.ts | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/lib/feed.ts b/lib/feed.ts
index 77a2e3a..6a2f0b0 100644
--- a/lib/feed.ts
+++ b/lib/feed.ts
@@ -222,13 +222,19 @@ export async function getUrlInfo(url: string): Promise<{ title: string; htmlBody
 }
 
 export async function parseTextFromHtml(html: string): Promise<string> {
-  let text = '';
+  if (!html || !html.trim()) {
+    return '';
+  }
 
   await initParser();
 
   const document = new DOMParser().parseFromString(html, 'text/html');
 
-  text = document!.textContent;
+  // Extract text from body to avoid any artifacts from the document wrapper
+  const text = (document?.querySelector('body')?.textContent || document?.textContent || '')
+    // Collapse multiple whitespace/newlines into single spaces
+    .replace(/\s+/g, ' ')
+    .trim();
 
   return text;
 }