X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/639630d5fe91b38d39123f002ef77c70c3b1b520..13db4c9731072c8e8af5f3eccbefb8723233f51c:/settings/icu_tokenizer.yaml?ds=sidebyside

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 530df1a6..bb81f80b 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -1,4 +1,5 @@
 query-preprocessing:
+    - step: split_japanese_phrases
     - step: normalize
 normalization:
     - ":: lower ()"
@@ -9,16 +10,17 @@ 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 ()"
@@ -44,7 +46,7 @@ sanitizers:
     - 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]
+      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
@@ -156,7 +158,7 @@ token-analysis:
       mode: variant-only
       variants:
           - !include icu-rules/variants-nl.yaml
-    - id: no
+    - id: "no"
       analyzer: generic
       mode: variant-only
       variants: