postcodes: introduce a default pattern for countries without postcodes

2022-05-24 18:25:37 +02:00
parent 5ba75df507
commit 18864afa8a
3 changed files with 28 additions and 7 deletions
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -34,6 +34,7 @@ sanitizers:
        - (\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