stemmer.hpp
Go to the documentation of this file.
1 /*
2  * SPDX-FileCopyrightText: Copyright (c) 2020-2024, NVIDIA CORPORATION.
3  * SPDX-License-Identifier: Apache-2.0
4  */
5 #pragma once
6 
7 #include <cudf/column/column.hpp>
8 #include <cudf/scalar/scalar.hpp>
10 #include <cudf/utilities/export.hpp>
12 
13 namespace CUDF_EXPORT nvtext {
23 enum class letter_type {
24  CONSONANT,
25  VOWEL
26 };
27 
69 std::unique_ptr<cudf::column> is_letter(
70  cudf::strings_column_view const& input,
71  letter_type ltype,
72  cudf::size_type character_index,
75 
122 std::unique_ptr<cudf::column> is_letter(
123  cudf::strings_column_view const& input,
124  letter_type ltype,
125  cudf::column_view const& indices,
128 
158 std::unique_ptr<cudf::column> porter_stemmer_measure(
159  cudf::strings_column_view const& input,
162  // end of group
164 } // namespace CUDF_EXPORT nvtext
A non-owning, immutable view of device data as a column of elements, some of which may be null as ind...
Given a column-view of strings type, an instance of this class provides a wrapper on this compound co...
Class definition for cudf::column.
rmm::cuda_stream_view const get_default_stream()
Get the current default stream.
rmm::device_async_resource_ref get_current_device_resource_ref()
Get the current device memory resource reference.
detail::cccl_async_resource_ref< cuda::mr::resource_ref< cuda::mr::device_accessible > > device_async_resource_ref
std::unique_ptr< cudf::column > is_letter(cudf::strings_column_view const &input, letter_type ltype, cudf::column_view const &indices, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns boolean column indicating if character at indices[i] of input[i] is a consonant or vowel.
std::unique_ptr< cudf::column > porter_stemmer_measure(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 the Porter Stemmer measurements of a strings column.
letter_type
Used for specifying letter type to check.
Definition: stemmer.hpp:23
@ CONSONANT
Letter is a consonant.
@ VOWEL
Letter is not a consonant.
int32_t size_type
Row index type for columns and tables.
Definition: types.hpp:84
NVText APIs.
Class definitions for cudf::scalar.
Class definition for cudf::strings_column_view.