add japanese phrase preprocessing

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 1fa467befebfa4c5977103d6731064dd760791ff..6cf30d59e55b961d32ae7fc1b9a08bf9118d1c62 100644 (file)
--- 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 ()"
@@ -45,6 +49,7 @@ sanitizers:
       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"