stemmer.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2020-2024, NVIDIA CORPORATION.
3  *
4  * Licensed under the Apache License, Version 2.0 (the "License");
5  * you may not use this file except in compliance with the License.
6  * You may obtain a copy of the License at
7  *
8  * http://www.apache.org/licenses/LICENSE-2.0
9  *
10  * Unless required by applicable law or agreed to in writing, software
11  * distributed under the License is distributed on an "AS IS" BASIS,
12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13  * See the License for the specific language governing permissions and
14  * limitations under the License.
15  */
16 #pragma once
17 
18 #include <cudf/column/column.hpp>
19 #include <cudf/scalar/scalar.hpp>
21 #include <cudf/utilities/export.hpp>
23 
24 namespace CUDF_EXPORT nvtext {
34 enum class letter_type {
35  CONSONANT,
36  VOWEL
37 };
38 
80 std::unique_ptr<cudf::column> is_letter(
81  cudf::strings_column_view const& input,
82  letter_type ltype,
83  cudf::size_type character_index,
86 
133 std::unique_ptr<cudf::column> is_letter(
134  cudf::strings_column_view const& input,
135  letter_type ltype,
136  cudf::column_view const& indices,
139 
169 std::unique_ptr<cudf::column> porter_stemmer_measure(
170  cudf::strings_column_view const& input,
173  // end of group
175 } // 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.
cuda::mr::async_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:34
@ 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:95
NVText APIs.
Class definitions for cudf::scalar.
Class definition for cudf::strings_column_view.