X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/3bf3b894eaddd4f17f7e92353af6b2aa6200ab20..69ce42b22cc676f0fa4a5ae408008369b9e9cb7e:/settings/icu_tokenizer.yaml diff --git a/settings/icu_tokenizer.yaml b/settings/icu_tokenizer.yaml index 212fdcb9..1fa467be 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: @@ -35,7 +36,9 @@ sanitizers: - step: clean-postcodes convert-to-address: yes default-pattern: "[A-Z0-9- ]{3,12}" + - step: clean-tiger-tags - step: split-name-list + delimiters: ; - step: strip-brace-terms - step: tag-analyzer-by-language filter-kind: [".*name.*"]