X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/37e5f07d83f04664b05b35eb05abcf304897e9f2..eeb3d5dd0affdd3317ff62177905b5474ad2fd34:/settings/icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index cd9c0d6d..530df1a6 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -1,3 +1,5 @@
+query-preprocessing:
+    - step: normalize
 normalization:
     - ":: lower ()"
     - ":: Hans-Hant"
@@ -24,6 +26,7 @@ transliteration:
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
+    - "[:Space:]+ > ' '"
 sanitizers:
     - step: clean-housenumbers
       filter-kind:
@@ -32,17 +35,25 @@ sanitizers:
         - streetnumber
       convert-to-name:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
+    - step: clean-postcodes
+      convert-to-address: yes
+      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"
       analyzer: housenumbers
+    - id: "@postcode"
+      analyzer: postcodes
     - id: bg
       analyzer: generic
       mode: variant-only