X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/18864afa8aee710a5aa7fe65565711119ca7a663..f3ffbe167d15f44605ac192bbf87013a85965425:/settings/icu_tokenizer.yaml diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index f682bbcd..f30578a2 100644 --- a/settings/icu_tokenizer.yaml +++ b/settings/icu_tokenizer.yaml @@ -24,6 +24,7 @@ transliteration: - ":: lower ()" - "[^a-z0-9[:Space:]] >" - ":: NFC ()" + - "[:Space:]+ > ' '" sanitizers: - step: clean-housenumbers filter-kind: @@ -34,7 +35,8 @@ sanitizers: - (\A|.*,)[^\d,]{3,}(,.*|\Z) - step: clean-postcodes convert-to-address: yes - default-pattern: [A-Z0-9- ]{3,12} + default-pattern: "[A-Z0-9- ]{3,12}" + - step: clean-tiger-tags - step: split-name-list - step: strip-brace-terms - step: tag-analyzer-by-language @@ -46,6 +48,8 @@ token-analysis: - analyzer: generic - id: "@housenumber" analyzer: housenumbers + - id: "@postcode" + analyzer: postcodes - id: bg analyzer: generic mode: variant-only