keep break indicators [:-] during normalisation

[nominatim.git] / settings / icu_tokenizer.yaml

diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml
index 530df1a63397e423355ec7a75dc36178e2c2418e..437319fab801d53fbd5b2cb5581e1dd88a0ff79a 100644 (file)
--- a/settings/icu_tokenizer.yaml
+++ b/settings/icu_tokenizer.yaml
@@ -9,16 +9,17 @@ normalization:
     - "'nº' > 'no'"
     - "ª > a"
     - "º > o"
     - "'nº' > 'no'"
     - "ª > a"
     - "º > o"

-    - "[[:Punctuation:][:Symbol:]\u02bc]  > ' '"
+    - "[[:Punctuation:][:Symbol:][\u02bc] - [-:]]+  > '-'"

     - "ß > 'ss'" # German szet is unambiguously equal to double ss
     - "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:]] >;"
     - "[:Lm:] >"
     - ":: [[:Number:]] Latin ()"
     - ":: [[:Number:]] Ascii ();"
     - ":: [[:Number:]] NFD ();"
     - "[[:Nonspacing Mark:] [:Cf:]] >;"

-    - "[:Space:]+ > ' '"
+    - "[-:]?[:Space:]+[-:]? > ' '"

 transliteration:
 transliteration:

+    - "[-:]  > ' '"

     - ":: Latin ()"
     - !include icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"
     - ":: Latin ()"
     - !include icu-rules/extended-unicode-to-asccii.yaml
     - ":: Ascii ()"