X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/0722495434e039b7b716206974d0076db8813ca6..efc09a5cfcfa85663db7d2a4deb86808a0a72de6:/settings/icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index c5a809c6..6cf30d59 100644
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -1,3 +1,6 @@
+query-preprocessing:
+    - step: split_japanese_phrases
+    - step: normalize
 normalization:
     - ":: lower ()"
     - ":: Hans-Hant"
@@ -7,16 +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 ()"