unicode_normalize.hpp
Go to the documentation of this file.
1 /*
2  * SPDX-FileCopyrightText: Copyright (c) 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>
11 #include <cudf/utilities/export.hpp>
13 
14 namespace CUDF_EXPORT nvtext {
27 enum class unicode_normalization_form : int32_t {
28  NFD,
29  NFC,
30  NFKD,
31  NFKC
32 };
33 
85  unicode_normalizer(cudf::table_view const& unicode_data,
87  cuda::stream_ref stream = cudf::get_default_stream(),
90 
91  struct unicode_normalizer_impl;
92  std::unique_ptr<unicode_normalizer_impl> _impl;
93 };
94 
106 std::unique_ptr<unicode_normalizer> create_unicode_normalizer(
107  cudf::table_view const& unicode_data,
109  cuda::stream_ref stream = cudf::get_default_stream(),
111 
137 std::unique_ptr<cudf::column> normalize_unicode(
138  cudf::strings_column_view const& input,
139  unicode_normalizer const& normalizer,
140  cuda::stream_ref stream = cudf::get_default_stream(),
142  // end of group
144 } // namespace CUDF_EXPORT nvtext
Given a column-view of strings type, an instance of this class provides a wrapper on this compound co...
A set of cudf::column_view's of the same size.
Definition: table_view.hpp:206
Class definition for cudf::column.
column view class definitions
cuda::stream_ref 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< cudf::column > normalize_unicode(cudf::strings_column_view const &input, unicode_normalizer const &normalizer, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Normalize a strings column using Unicode TR15 normalization.
unicode_normalization_form
Unicode normalization form per Unicode Standard Annex #15.
std::unique_ptr< unicode_normalizer > create_unicode_normalizer(cudf::table_view const &unicode_data, unicode_normalization_form form, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Create a unicode_normalizer object.
@ NFKC
Compatibility Decomposition followed by Canonical Composition.
@ NFKD
Compatibility Decomposition.
@ NFD
Canonical Decomposition.
@ NFC
Canonical Decomposition followed by Canonical Composition.
APIs for getting and setting the current device memory resource.
NVText APIs.
Class definition for cudf::strings_column_view.
Normalizer object for Unicode TR15 normalization.
unicode_normalizer(cudf::table_view const &unicode_data, unicode_normalization_form form, cuda::stream_ref stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Construct a unicode_normalizer from UnicodeData.txt columns.
Class definitions for (mutable)_table_view