std::unique_ptr< cudf::column > normalize_spaces(cudf::strings_column_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns a new strings column by normalizing the whitespace in each string in the input column.
std::unique_ptr< character_normalizer > create_character_normalizer(bool do_lower_case, cudf::strings_column_view const &special_tokens=cudf::strings_column_view(cudf::column_view{ cudf::data_type{cudf::type_id::STRING}, 0, nullptr, nullptr, 0}), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Create a normalizer object.
std::unique_ptr< cudf::column > normalize_characters(cudf::strings_column_view const &input, character_normalizer const &normalizer, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Normalizes the text in input strings column.
Normalizer object to be used with nvtext::normalize_characters.
character_normalizer(bool do_lower_case, cudf::strings_column_view const &special_tokens, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Normalizer object constructor.