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: