From 7a3bfc50e78da32daa5aadd468d687d87c358b6a Mon Sep 17 00:00:00 2001
From: User <user@example.com>
Date: Mon, 23 Feb 2026 04:39:14 +0800
Subject: [PATCH] fix: preserve single line breaks, only collapse 2+
 consecutive whitespace

Address review feedback: the previous \s+ regex was too aggressive and
broke text-only summaries with legitimate line breaks.

Now:
- Collapse runs of 2+ non-newline whitespace into a single space
- Collapse 3+ consecutive newlines into double newline (paragraph break)
- Single line breaks are preserved
---
 lib/feed.ts | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/feed.ts b/lib/feed.ts
index 6a2f0b0..79e6545 100644
--- a/lib/feed.ts
+++ b/lib/feed.ts
@@ -232,8 +232,9 @@ export async function parseTextFromHtml(html: string): Promise<string> {
 
   // 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, ' ')
+    // Collapse runs of 2+ whitespace/newline characters, preserving single line breaks
+    .replace(/[^\S\n]{2,}/g, ' ')
+    .replace(/\n{3,}/g, '\n\n')
     .trim();
 
   return text;