ngrams_tokenize.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2020-2024, NVIDIA CORPORATION.
 * SPDX-License-Identifier: Apache-2.0
 */
#pragma once
 
#include <cudf/column/column.hpp>
#include <cudf/scalar/scalar.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> ngrams_tokenize(
  cudf::strings_column_view const& input,
  cudf::size_type ngrams,
  cudf::string_scalar const& delimiter,
  cudf::string_scalar const& separator,
  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