Go to the source code of this file.
|
std::unique_ptr< cudf::column > | nvtext::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. More...
|
|
std::unique_ptr< cudf::column > | nvtext::normalize_characters (cudf::strings_column_view const &input, bool do_lower_case, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref()) |
| Normalizes strings characters for tokenizing. More...
|
|
std::unique_ptr< character_normalizer > | nvtext::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. More...
|
|
std::unique_ptr< cudf::column > | nvtext::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. More...
|
|