From b9e0689359f347edc47487a8043c9004ead0770a Mon Sep 17 00:00:00 2001
From: Vyr Cossont <VyrCossont@users.noreply.github.com>
Date: Fri, 31 Jan 2025 02:42:55 -0800
Subject: [bugfix] Extend parser to handle more non-Latin hashtags (#3700)

* Allow marks after NFC normalization

Includes regression test for the Tamil example from #3618

* Disallow just numbers + marks + underscore as hashtag
---
 internal/text/goldmark_parsers.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'internal/text/goldmark_parsers.go')

diff --git a/internal/text/goldmark_parsers.go b/internal/text/goldmark_parsers.go
index b7cf4f9e9..e2c87e057 100644
--- a/internal/text/goldmark_parsers.go
+++ b/internal/text/goldmark_parsers.go
@@ -177,7 +177,7 @@ func (p *hashtagParser) Parse(
 			// Ignore initial '#'.
 			continue
 
-		case !isPlausiblyInHashtag(r) &&
+		case !isPermittedInHashtag(r) &&
 			!isHashtagBoundary(r):
 			// Weird non-boundary character
 			// in the hashtag. Don't trust it.
-- 
cgit v1.2.3