RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 11:48:10 +00:00
Code Issues Activity Actions

LibUnicode: Implement text segmentation algorithms for all UTF encodings

Browse source 
Similar to commit 6d710eeb43. Rather than
pick-and-chosing what to support, let's just support all encodings now,
as it is trivial. For example, LibGUI will want the UTF-32 overloads.
This commit is contained in:
Timothy Flynn 2023-02-14 11:31:26 -05:00 • committed by Linus Groh
parent 2d487e4e4c
commit dd4c47456e
2 changed files with 85 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Userland/Libraries/LibUnicode/Segmentation.h
View file

@ -13,11 +13,16 @@
namespace Unicode {
Vector<size_t> find_grapheme_segmentation_boundaries(Utf8View const&);
Vector<size_t> find_grapheme_segmentation_boundaries(Utf16View const&);
Vector<size_t> find_grapheme_segmentation_boundaries(Utf32View const&);
Vector<size_t> find_word_segmentation_boundaries(Utf8View const&);
Vector<size_t> find_word_segmentation_boundaries(Utf16View const&);
Vector<size_t> find_word_segmentation_boundaries(Utf32View const&);
Vector<size_t> find_sentence_segmentation_boundaries(Utf8View const&);
Vector<size_t> find_sentence_segmentation_boundaries(Utf16View const&);
Vector<size_t> find_sentence_segmentation_boundaries(Utf32View const&);
}