translate.hpp
Go to the documentation of this file.
1 /*
2  * SPDX-FileCopyrightText: Copyright (c) 2019-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
3  * SPDX-License-Identifier: Apache-2.0
4  */
5 #pragma once
6 
7 #include <cudf/column/column.hpp>
8 #include <cudf/scalar/scalar.hpp>
12 
13 #include <vector>
14 
20 namespace CUDF_EXPORT cudf {
21 namespace strings {
48 std::unique_ptr<column> translate(
49  strings_column_view const& input,
50  std::vector<std::pair<char_utf8, char_utf8>> const& chars_table,
53 
57 enum class filter_type : bool {
58  KEEP,
59  REMOVE
60 };
61 
93 std::unique_ptr<column> filter_characters(
94  strings_column_view const& input,
95  std::vector<std::pair<cudf::char_utf8, cudf::char_utf8>> characters_to_filter,
96  filter_type keep_characters = filter_type::KEEP,
97  string_scalar const& replacement = string_scalar(""),
100  // end of doxygen group
102 } // namespace strings
103 } // namespace CUDF_EXPORT cudf
An owning class to represent a string in device memory.
Definition: scalar.hpp:411
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::resource_ref< cuda::mr::device_accessible > device_async_resource_ref
std::unique_ptr< column > filter_characters(strings_column_view const &input, std::vector< std::pair< cudf::char_utf8, cudf::char_utf8 >> characters_to_filter, filter_type keep_characters=filter_type::KEEP, string_scalar const &replacement=string_scalar(""), rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Removes ranges of characters from each string in a strings column.
filter_type
Removes or keeps the specified character ranges in cudf::strings::filter_characters.
Definition: translate.hpp:57
std::unique_ptr< column > translate(strings_column_view const &input, std::vector< std::pair< char_utf8, char_utf8 >> const &chars_table, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Translates individual characters within each string.
@ KEEP
All characters but those specified are removed.
@ REMOVE
Only the specified characters are removed.
APIs for getting and setting the current device memory resource.
cuDF interfaces
Definition: host_udf.hpp:26
Class definitions for cudf::scalar.
Class definition for cudf::string_view.
Class definition for cudf::strings_column_view.