normalize.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>
20 #include <cudf/utilities/export.hpp>
22 
24 namespace CUDF_EXPORT nvtext {
54 std::unique_ptr<cudf::column> normalize_spaces(
55  cudf::strings_column_view const& input,
58 
104 std::unique_ptr<cudf::column> normalize_characters(
105  cudf::strings_column_view const& input,
106  bool do_lower_case,
109  // end of group
111 } // namespace CUDF_EXPORT nvtext
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 > 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.
std::unique_ptr< cudf::column > 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.
NVText APIs.
Class definition for cudf::strings_column_view.