X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c35b3ea5c7125dc874557d121cb3e97b84a498b2..baee6f3de09226c3dc41cb2314a0ac348e865561:/settings/icu_tokenizer.yaml diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index bebd49e9..544bd81d 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 ();" @@ -32,6 +32,8 @@ sanitizers: - streetnumber convert-to-name: - (\A|.*,)[^\d,]{3,}(,.*|\Z) + - step: clean-postcodes + convert-to-address: yes - step: split-name-list - step: strip-brace-terms - step: tag-analyzer-by-language