use canonical url for nominatim.org

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index cd9c0d6dd56974888c9e12fdf834b51a5b55b22e..f30578a2322859ce287915a4049092f50eb3057a 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -24,6 +24,7 @@ transliteration:
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"

+    - "[:Space:]+ > ' '"

 sanitizers:
     - step: clean-housenumbers
       filter-kind:
 sanitizers:
     - step: clean-housenumbers
       filter-kind:


@@ -32,6 +33,10 @@ sanitizers:
         - streetnumber
       convert-to-name:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
         - 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
     - step: strip-brace-terms
     - step: tag-analyzer-by-language
     - step: split-name-list
     - step: strip-brace-terms
     - step: tag-analyzer-by-language


@@ -43,6 +48,8 @@ token-analysis:
     - analyzer: generic
     - id: "@housenumber"
       analyzer: housenumbers
     - analyzer: generic
     - id: "@housenumber"
       analyzer: housenumbers

+    - id: "@postcode"
+      analyzer: postcodes

     - id: bg
       analyzer: generic
       mode: variant-only
     - id: bg
       analyzer: generic
       mode: variant-only