multibyte_split.hpp
Go to the documentation of this file.
1 /*
2  * SPDX-FileCopyrightText: Copyright (c) 2021-2025, NVIDIA CORPORATION.
3  * SPDX-License-Identifier: Apache-2.0
4  */
5 
6 #pragma once
7 
8 #include <cudf/column/column.hpp>
12 
14 
15 #include <memory>
16 #include <optional>
17 #include <string_view>
18 
19 namespace CUDF_EXPORT cudf {
20 namespace io {
21 namespace text {
31 struct parse_options {
39  bool strip_delimiters = false;
40 };
41 
81 std::unique_ptr<cudf::column> multibyte_split(
82  data_chunk_source const& source,
83  std::string_view delimiter,
84  parse_options options = {},
87  // end of group
89 
90 } // namespace text
91 } // namespace io
92 } // 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.
detail::cccl_async_resource_ref< cuda::mr::resource_ref< cuda::mr::device_accessible > > device_async_resource_ref
cuDF interfaces
Definition: host_udf.hpp:26
Parsing options for multibyte_split.