X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/13dbeb75c77ae88984cfe2730a4c9a1561304564..HEAD:/settings/icu_tokenizer.yaml?ds=sidebyside

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 16339970..c5a809c6 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:
@@ -37,12 +38,14 @@ sanitizers:
       default-pattern: "[A-Z0-9- ]{3,12}"
     - step: clean-tiger-tags
     - step: split-name-list
+      delimiters: ;
     - 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]
       use-defaults: all
       mode: append
+    - step: tag-japanese
 token-analysis:
     - analyzer: generic
     - id: "@housenumber"