Merge pull request #2954 from lonvia/remove-comma-as-separator

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index f682bbcdf8ad4c38a4e891e55f5360e70a7a28d0..1fa467befebfa4c5977103d6731064dd760791ff 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:


@@ -34,8 +35,10 @@ sanitizers:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
     - step: clean-postcodes
       convert-to-address: yes
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
     - step: clean-postcodes
       convert-to-address: yes

-      default-pattern: [A-Z0-9- ]{3,12}
+      default-pattern: "[A-Z0-9- ]{3,12}"
+    - step: clean-tiger-tags

     - step: split-name-list
     - step: split-name-list

+      delimiters: ;

     - step: strip-brace-terms
     - step: tag-analyzer-by-language
       filter-kind: [".*name.*"]
     - step: strip-brace-terms
     - step: tag-analyzer-by-language
       filter-kind: [".*name.*"]


@@ -46,6 +49,8 @@ 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