postcodes: introduce a default pattern for countries without postcodes

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index cd9c0d6dd56974888c9e12fdf834b51a5b55b22e..f682bbcdf8ad4c38a4e891e55f5360e70a7a28d0 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -32,6 +32,9 @@ 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: 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