translate.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019-2023, 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>
22 
23 #include <rmm/mr/device/per_device_resource.hpp>
24 
25 #include <vector>
26 
27 namespace cudf {
28 namespace strings {
56 std::unique_ptr<column> translate(
57  strings_column_view const& input,
58  std::vector<std::pair<char_utf8, char_utf8>> const& chars_table,
59  rmm::cuda_stream_view stream = cudf::get_default_stream(),
60  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
61 
65 enum class filter_type : bool {
66  KEEP,
67  REMOVE
68 };
69 
101 std::unique_ptr<column> filter_characters(
102  strings_column_view const& input,
103  std::vector<std::pair<cudf::char_utf8, cudf::char_utf8>> characters_to_filter,
104  filter_type keep_characters = filter_type::KEEP,
105  string_scalar const& replacement = string_scalar(""),
106  rmm::cuda_stream_view stream = cudf::get_default_stream(),
107  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
108  // end of doxygen group
110 } // namespace strings
111 } // namespace cudf
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.
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::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
Removes ranges of characters from each string in a strings column.
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::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource())
Translates individual characters within each string.
filter_type
Removes or keeps the specified character ranges in cudf::strings::filter_characters.
Definition: translate.hpp:65
@ KEEP
All characters but those specified are removed.
@ REMOVE
Only the specified characters are removed.
cuDF interfaces
Definition: aggregation.hpp:34
Class definitions for cudf::scalar.
Class definition for cudf::string_view.
Class definition for cudf::strings_column_view.