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 bebd49e924bcf08fa3da5cbb04c5cf4d3c486533..1fa467befebfa4c5977103d6731064dd760791ff 100644 (file)
--- 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 ();"
@@ -24,6 +24,7 @@ transliteration:
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
+    - "[:Space:]+ > ' '"
 sanitizers:
     - step: clean-housenumbers
       filter-kind:
@@ -32,7 +33,12 @@ sanitizers:
         - streetnumber
       convert-to-name:
         - (\A|.*,)[^\d,]{3,}(,.*|\Z)
+    - step: clean-postcodes
+      convert-to-address: yes
+      default-pattern: "[A-Z0-9- ]{3,12}"
+    - step: clean-tiger-tags
     - step: split-name-list
+      delimiters: ;
     - step: strip-brace-terms
     - step: tag-analyzer-by-language
       filter-kind: [".*name.*"]
@@ -43,6 +49,8 @@ token-analysis:
     - analyzer: generic
     - id: "@housenumber"
       analyzer: housenumbers
+    - id: "@postcode"
+      analyzer: postcodes
     - id: bg
       analyzer: generic
       mode: variant-only