normalize.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2020-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 */
#pragma once
 
#include <cudf/column/column.hpp>
#include <cudf/column/column_view.hpp>
#include <cudf/strings/strings_column_view.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
 
namespace CUDF_EXPORT nvtext {
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());
 
struct character_normalizer {
  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());
  ~character_normalizer();
 
  struct character_normalizer_impl;
  std::unique_ptr<character_normalizer_impl> _impl;
};
 
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());
 
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());
  // end of group
}  // namespace CUDF_EXPORT nvtext