multibyte_split.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2021-2025, 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 
17 #pragma once
18 
19 #include <cudf/column/column.hpp>
23 
25 
26 #include <memory>
27 #include <optional>
28 #include <string_view>
29 
30 namespace CUDF_EXPORT cudf {
31 namespace io {
32 namespace text {
42 struct parse_options {
50  bool strip_delimiters = false;
51 };
52 
92 std::unique_ptr<cudf::column> multibyte_split(
93  data_chunk_source const& source,
94  std::string_view delimiter,
95  parse_options options = {},
98  // end of group
100 
101 } // namespace text
102 } // namespace io
103 } // namespace CUDF_EXPORT cudf
stores offset and size used to indicate a byte range
a data source capable of creating a reader which can produce views of the data source in device memor...
Class definition for cudf::column.
rmm::cuda_stream_view const get_default_stream()
Get the current default stream.
byte_range_info create_byte_range_info_max()
Create a byte_range_info which represents as much of a file as possible. Specifically,...
std::unique_ptr< cudf::column > multibyte_split(data_chunk_source const &source, std::string_view delimiter, parse_options options={}, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Splits the source text into a strings column using a multiple byte delimiter.
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
cuDF interfaces
Definition: host_udf.hpp:37
Parsing options for multibyte_split.