From fd8d462d6efe1fa5a55634e5e79f2875fd6cbb08 Mon Sep 17 00:00:00 2001
From: Richard R <me@richardr.dev>
Date: Wed, 10 Jun 2026 09:38:41 -0600
Subject: [PATCH] test(nlp): add case to ensure Catalan middle dot is preserved
 in audio text normalization

Add unit test verifying that U+00B7 middle dot is not stripped from Catalan
words during audio text preprocessing, reflecting multilingual requirements.
---
 tests/unit/nlp.vitest.spec.ts | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tests/unit/nlp.vitest.spec.ts b/tests/unit/nlp.vitest.spec.ts
index 5088594..a9374ec 100644
--- a/tests/unit/nlp.vitest.spec.ts
+++ b/tests/unit/nlp.vitest.spec.ts
@@ -41,6 +41,12 @@ describe('preprocessSentenceForAudio', () => {
         input: '• Bullet ‣ marker ◦ list',
         expected: 'Bullet marker list',
       },
+      {
+        // U+00B7 middle dot is a real letter in Catalan ("col·legi") and must
+        // NOT be stripped like decorative bullets, since OpenReader is multilingual.
+        input: 'Col·legi de l·l',
+        expected: 'Col·legi de l·l',
+      },
       {
         input: 'Multiple    spaces',
         expected: 'Multiple spaces',