RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 19:17:44 +00:00
Code Issues Activity Actions

LibUnicode+LibJS: Move text segmentation algorithms to their own files

Browse source 
These algorithms are quite chonky, and more APIs around them are to be
added, so let's move them to their own files for a bit of organization.
This commit is contained in:
Timothy Flynn 2023-02-14 11:08:25 -05:00 • committed by Linus Groh
parent 9ba3c8e36d
commit 2d487e4e4c
7 changed files with 439 additions and 401 deletions
Download patch file Download diff file Expand all files Collapse all files

23
Userland/Libraries/LibUnicode/Segmentation.h Normal file
View file

@ -0,0 +1,23 @@
/*
* Copyright (c) 2022, Idan Horowitz <idan.horowitz@serenityos.org>
* Copyright (c) 2023, Tim Flynn <trflynn89@serenityos.org>
*
* SPDX-License-Identifier: BSD-2-Clause
*/
#pragma once
#include <AK/Forward.h>
#include <AK/Types.h>
#include <AK/Vector.h>
namespace Unicode {
Vector<size_t> find_grapheme_segmentation_boundaries(Utf16View const&);
Vector<size_t> find_word_segmentation_boundaries(Utf8View const&);
Vector<size_t> find_word_segmentation_boundaries(Utf16View const&);
Vector<size_t> find_sentence_segmentation_boundaries(Utf16View const&);
}