From d669ed4783ad07a78483c89d51551f29cc1e0edc Mon Sep 17 00:00:00 2001
From: rainbow napkin <ourforest@tuta.io>
Date: Fri, 26 Dec 2025 12:54:41 -0500
Subject: [PATCH] Prevented accented letters splitting words in client-side
 chatPostprocessor

---
 www/js/channel/chatPostprocessor.js | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/www/js/channel/chatPostprocessor.js b/www/js/channel/chatPostprocessor.js
index a9d1370..a1b7e43 100644
--- a/www/js/channel/chatPostprocessor.js
+++ b/www/js/channel/chatPostprocessor.js
@@ -140,10 +140,11 @@ class chatPostprocessor{
         this.messageArray = [];
 
         //Unescape any sanatized char codes as we use .textContent for double-safety, and to prevent splitting of char codes
-        //Split string by word-boundries on words and non-word boundries around whitespace, with negative lookaheads to exclude file seperators so we don't split link placeholders, and dashes so we dont split usernames and other things
+        //Split string by word-boundries on words and non-word boundries around whitespace, 
+        //with negative lookaheads to exclude file seperators so we don't split link placeholders, dashes so we dont split usernames and other things, and accented characters to keep those from splitting boundries too 
         //Also split by any invisble whitespace as a crutch to handle mushed links/emotes
         //If we can one day figure out how to split non-repeating special chars instead of special chars with whitespace, that would be perf, unfortunately my brain hasn't rotted enough to understand regex like that just yet.
-        const splitString = utils.unescapeEntities(this.rawData.msg).split(/(?<!-)(?<!␜)(?=\w)\b|(?!-)(?<=\w)\b|(?=\s)\B|(?<=\s)\B|ㅤ/g);
+        const splitString = utils.unescapeEntities(this.rawData.msg).split(/(?<!-)(?<!␜)(?=\w)\b|(?!-|[\u00C0-\u017F])(?<=\w)\b|(?=\s)\B|(?<=\s)\B|ㅤ/g);
 
         //for each word in the splitstring
         splitString.forEach((string) => {