X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/610f2cc254cf442c895351907be6405f03026903..18864afa8aee710a5aa7fe65565711119ca7a663:/settings/icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 50bb72d2..f682bbcd 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -8,8 +8,8 @@ normalization:
     - "ª > a"
     - "º > o"
     - "[[:Punctuation:][:Symbol:]\u02bc]  > ' '"
-    - "ß > 'ss'" # German szet is unimbigiously equal to double ss
-    - "[^[:Letter:] [:Number:] [:Space:]] >"
+    - "ß > 'ss'" # German szet is unambiguously equal to double ss
+    - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:]] >"
     - "[:Lm:] >"
     - ":: [[:Number:]] Latin ()"
     - ":: [[:Number:]] Ascii ();"
@@ -32,6 +32,9 @@ sanitizers:
         - 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
@@ -41,6 +44,8 @@ sanitizers:
       mode: append
 token-analysis:
     - analyzer: generic
+    - id: "@housenumber"
+      analyzer: housenumbers
     - id: bg
       analyzer: generic
       mode: variant-only