postcodes: strip leading country codes

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index cd9c0d6dd56974888c9e12fdf834b51a5b55b22e..544bd81db01ee0dc17f13fce5ad859959b186812 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -32,6 +32,8 @@ sanitizers:
         - streetnumber
       convert-to-name:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
         - streetnumber
       convert-to-name:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)

+    - step: clean-postcodes
+      convert-to-address: yes

     - 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