keep break indicators [:-] during normalisation

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index f682bbcdf8ad4c38a4e891e55f5360e70a7a28d0..437319fab801d53fbd5b2cb5581e1dd88a0ff79a 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -1,3 +1,5 @@
+query-preprocessing:
+    - step: normalize
 normalization:
     - ":: lower ()"
     - ":: Hans-Hant"
@@ -7,16 +9,17 @@ normalization:
     - "'nº' > 'no'"
     - "ª > a"
     - "º > o"
-    - "[[:Punctuation:][:Symbol:]\u02bc]  > ' '"
+    - "[[:Punctuation:][:Symbol:][\u02bc] - [-:]]+  > '-'"
     - "ß > 'ss'" # German szet is unambiguously equal to double ss
-    - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:]] >"
+    - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:] [-:]] >"
     - "[:Lm:] >"
     - ":: [[:Number:]] Latin ()"
     - ":: [[:Number:]] Ascii ();"
     - ":: [[:Number:]] NFD ();"
     - "[[:Nonspacing Mark:] [:Cf:]] >;"
-    - "[:Space:]+ > ' '"
+    - "[-:]?[:Space:]+[-:]? > ' '"
 transliteration:
+    - "[-:]  > ' '"
     - ":: Latin ()"
     - !include icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"
@@ -24,6 +27,7 @@ transliteration:
     - ":: lower ()"
     - "[^a-z0-9[:Space:]] >"
     - ":: NFC ()"
+    - "[:Space:]+ > ' '"
 sanitizers:
     - step: clean-housenumbers
       filter-kind:
@@ -34,18 +38,23 @@ sanitizers:
         - (\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
+      delimiters: ;
     - step: strip-brace-terms
     - step: tag-analyzer-by-language
       filter-kind: [".*name.*"]
       whitelist: [bg,ca,cs,da,de,el,en,es,et,eu,fi,fr,gl,hu,it,ja,mg,ms,nl,no,pl,pt,ro,ru,sk,sl,sv,tr,uk,vi]
       use-defaults: all
       mode: append
+    - step: tag-japanese
 token-analysis:
     - analyzer: generic
     - id: "@housenumber"
       analyzer: housenumbers
+    - id: "@postcode"
+      analyzer: postcodes
     - id: bg
       analyzer: generic
       mode: variant-only