Nominatim/settings/icu_tokenizer.yaml
Sarah Hoffmann b7d4ff3201 icu: normalise simplified to traditional chinese
The conversion is unambigious in most cases, so that the
information loss is minimal.
2021-08-31 11:18:34 +02:00

58 lines
2.0 KiB
YAML

normalization:
- ":: lower ()"
- ":: Hans-Hant"
- !include icu-rules/unicode-digits-to-decimal.yaml
- "'№' > 'no'"
- "'n°' > 'no'"
- "'nº' > 'no'"
- "ª > a"
- "º > o"
- "[[:Punctuation:][:Symbol:]] > ' '"
- "ß > 'ss'" # German szet is unimbigiously equal to double ss
- "[^[:Letter:] [:Number:] [:Space:]] >"
- "[:Lm:] >"
- ":: [[:Number:]] Latin ()"
- ":: [[:Number:]] Ascii ();"
- ":: [[:Number:]] NFD ();"
- "[[:Nonspacing Mark:] [:Cf:]] >;"
- "[:Space:]+ > ' '"
transliteration:
- ":: Latin ()"
- !include icu-rules/extended-unicode-to-asccii.yaml
- ":: Ascii ()"
- ":: NFD ()"
- "[^[:Ascii:]] >"
- ":: lower ()"
- ":: NFC ()"
variants:
- !include icu-rules/variants-bg.yaml
- !include icu-rules/variants-ca.yaml
- !include icu-rules/variants-cs.yaml
- !include icu-rules/variants-da.yaml
- !include icu-rules/variants-de.yaml
- !include icu-rules/variants-el.yaml
- !include icu-rules/variants-en.yaml
- !include icu-rules/variants-es.yaml
- !include icu-rules/variants-et.yaml
- !include icu-rules/variants-eu.yaml
- !include icu-rules/variants-fi.yaml
- !include icu-rules/variants-fr.yaml
- !include icu-rules/variants-gl.yaml
- !include icu-rules/variants-hu.yaml
- !include icu-rules/variants-it.yaml
- !include icu-rules/variants-ja.yaml
- !include icu-rules/variants-mg.yaml
- !include icu-rules/variants-ms.yaml
- !include icu-rules/variants-nl.yaml
- !include icu-rules/variants-no.yaml
- !include icu-rules/variants-pl.yaml
- !include icu-rules/variants-pt.yaml
- !include icu-rules/variants-ro.yaml
- !include icu-rules/variants-ru.yaml
- !include icu-rules/variants-sk.yaml
- !include icu-rules/variants-sl.yaml
- !include icu-rules/variants-sv.yaml
- !include icu-rules/variants-tr.yaml
- !include icu-rules/variants-uk.yaml
- !include icu-rules/variants-vi.yaml