X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/a7e048484b0f9066d1c6ba422087c2fd2c635b16..27f7c7fd88e588c48c006b459d9912c23b4e13c0:/settings/icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index c6601faf..bebd49e9 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -25,6 +25,13 @@ transliteration:
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
 sanitizers:
+    - step: clean-housenumbers
+      filter-kind:
+        - housenumber
+        - conscriptionnumber
+        - streetnumber
+      convert-to-name:
+        - (\A|.*,)[^\d,]{3,}(,.*|\Z)
     - step: split-name-list
     - step: strip-brace-terms
     - step: tag-analyzer-by-language
@@ -34,6 +41,8 @@ sanitizers:
       mode: append
 token-analysis:
     - analyzer: generic
+    - id: "@housenumber"
+      analyzer: housenumbers
     - id: bg
       analyzer: generic
       mode: variant-only