X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/63dc4b39bc6bc0bf5a95d0c1a8298f5349637a9e..ded2c5bf684bb034f593d8a7f5a7111b49578fe2:/settings/icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index cd9c0d6d..1fa467be 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:
@@ -32,7 +33,12 @@ 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.*"]
@@ -43,6 +49,8 @@ token-analysis:
     - analyzer: generic
     - id: "@housenumber"
       analyzer: housenumbers
+    - id: "@postcode"
+      analyzer: postcodes
     - id: bg
       analyzer: generic
       mode: variant-only