std::unique_ptr< cudf::column > normalize_unicode(cudf::strings_column_view const &input, unicode_normalizer const &normalizer, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Normalize a strings column using Unicode TR15 normalization.
unicode_normalization_form
Unicode normalization form per Unicode Standard Annex #15.
std::unique_ptr< unicode_normalizer > create_unicode_normalizer(cudf::table_view const &unicode_data, unicode_normalization_form form, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Create a unicode_normalizer object.
@ NFKC
Compatibility Decomposition followed by Canonical Composition.
@ NFKD
Compatibility Decomposition.
@ NFC
Canonical Decomposition followed by Canonical Composition.
Normalizer object for Unicode TR15 normalization.
unicode_normalizer(cudf::table_view const &unicode_data, unicode_normalization_form form, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Construct a unicode_normalizer from UnicodeData.txt columns.