X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/02894ca4a40a73f715652cef062fd54e512039ed..815e3cccf6840d935e5a708588700cca23b976e9:/settings/icu_tokenizer.yaml diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index 50bb72d2..cd9c0d6d 100644 --- a/settings/icu_tokenizer.yaml +++ b/settings/icu_tokenizer.yaml @@ -8,8 +8,8 @@ normalization: - "ª > a" - "º > o" - "[[:Punctuation:][:Symbol:]\u02bc] > ' '" - - "ß > 'ss'" # German szet is unimbigiously equal to double ss - - "[^[:Letter:] [:Number:] [:Space:]] >" + - "ß > 'ss'" # German szet is unambiguously equal to double ss + - "[^[:alnum:] [:Canonical_Combining_Class=Virama:] [:Space:]] >" - "[:Lm:] >" - ":: [[:Number:]] Latin ()" - ":: [[:Number:]] Ascii ();" @@ -41,6 +41,8 @@ sanitizers: mode: append token-analysis: - analyzer: generic + - id: "@housenumber" + analyzer: housenumbers - id: bg analyzer: generic mode: variant-only