From 3313369a395b9bd6bc57e0fe81a86a82f644d881 Mon Sep 17 00:00:00 2001
From: Sarah Hoffmann <lonvia@denofr.de>
Date: Fri, 2 Dec 2022 10:15:02 +0100
Subject: [PATCH] contract duplicate spaces in transliteration string

There are some pathological cases where an isolated letter may
be deleted because it is in itself meaningless. If this happens in
the middle of a sentence, then the transliteration contains two
consecutive spaces. Add a final rule to fix this.

See #2909.
---
 settings/icu_tokenizer.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 16339970..f30578a2 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -24,6 +24,7 @@ transliteration:
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
+    - "[:Space:]+ > ' '"
 sanitizers:
     - step: clean-housenumbers
       filter-kind:
-- 
2.39.5