nvtext/replace.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 
25 namespace CUDF_EXPORT nvtext {
87 std::unique_ptr<cudf::column> replace_tokens(
88  cudf::strings_column_view const& input,
89  cudf::strings_column_view const& targets,
90  cudf::strings_column_view const& replacements,
91  cudf::string_scalar const& delimiter = cudf::string_scalar{""},
94 
136 std::unique_ptr<cudf::column> filter_tokens(
137  cudf::strings_column_view const& input,
138  cudf::size_type min_token_length,
139  cudf::string_scalar const& replacement = cudf::string_scalar{""},
140  cudf::string_scalar const& delimiter = cudf::string_scalar{""},
143  // end of group
145 } // namespace CUDF_EXPORT nvtext
An owning class to represent a string in device memory.
Definition: scalar.hpp:429
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 > replace_tokens(cudf::strings_column_view const &input, cudf::strings_column_view const &targets, cudf::strings_column_view const &replacements, cudf::string_scalar const &delimiter=cudf::string_scalar{""}, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Replaces specified tokens with corresponding replacement strings.
std::unique_ptr< cudf::column > filter_tokens(cudf::strings_column_view const &input, cudf::size_type min_token_length, cudf::string_scalar const &replacement=cudf::string_scalar{""}, cudf::string_scalar const &delimiter=cudf::string_scalar{""}, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Removes tokens whose lengths are less than a specified number of characters.
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.