X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/86588419fb1c3fffe131c0e8d99ecea3c77d67c5..baf1b955fb27e9b4e4c7c1146b87627e13be6ac1:/settings/icu_tokenizer.yaml diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index bf51f563..50bb72d2 100644 --- a/settings/icu_tokenizer.yaml +++ b/settings/icu_tokenizer.yaml @@ -25,13 +25,15 @@ transliteration: - "[^a-z0-9[:Space:]] >" - ":: NFC ()" sanitizers: - - step: split-name-list - - step: strip-brace-terms - step: clean-housenumbers filter-kind: - housenumber - conscriptionnumber - streetnumber + convert-to-name: + - (\A|.*,)[^\d,]{3,}(,.*|\Z) + - step: split-name-list + - step: strip-brace-terms - step: tag-analyzer-by-language filter-kind: [".*name.*"] whitelist: [bg,ca,cs,da,de,el,en,es,et,eu,fi,fr,gl,hu,it,ja,mg,ms,nl,no,pl,pt,ro,ru,sk,sl,sv,tr,uk,vi]