RGBCube/serenity
1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-07-25 04:07:44 +00:00
Code Issues Activity Actions

LibUnicode: Update to Unicode version 15.1.0

Browse source 
https://unicode.org/versions/Unicode15.1.0/

This update includes a new set of code point properties, Indic Conjunct
Break. These may have the values Consonant, Linker, or Extend. These are
used in text segmentation to prevent breaking on some extended grapheme
cluster sequences.
This commit is contained in:
Timothy Flynn 2023-09-15 09:23:56 -04:00 • committed by Andreas Kling
parent ae15b68b79
commit 139c575cc9
4 changed files with 70 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

21
Tests/LibUnicode/TestSegmentation.cpp
View file

@ -51,6 +51,27 @@ TEST_CASE(grapheme_segmentation)
test_grapheme_segmentation("a👩🏼‍❤️‍👨🏻b"sv, { 0u, 1u, 29u, 30u });
}
TEST_CASE(grapheme_segmentation_indic_conjunct_break)
{
test_grapheme_segmentation("\u0915"sv, { 0u, 3u });
test_grapheme_segmentation("\u0915a"sv, { 0u, 3u, 4u });
test_grapheme_segmentation("\u0915\u0916"sv, { 0u, 3u, 6u });
test_grapheme_segmentation("\u0915\u094D\u0916"sv, { 0u, 9u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u094D\u0916"sv, { 0u, 15u });
test_grapheme_segmentation("\u0915\u094D\u09BC\u09CD\u0916"sv, { 0u, 15u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u094D\u09BC\u09CD\u0916"sv, { 0u, 21u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u09BC\u09CD\u094D\u0916"sv, { 0u, 21u });
test_grapheme_segmentation("\u0915\u094D\u09BC\u09CD\u09BC\u09CD\u0916"sv, { 0u, 21u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u09BC\u09CD\u094D\u09BC\u09CD\u0916"sv, { 0u, 27u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u094D\u09BC\u09CD\u09BC\u09CD\u0916"sv, { 0u, 27u });
test_grapheme_segmentation("\u0915\u09BC\u09CD\u09BC\u09CD\u094D\u09BC\u09CD\u09BC\u09CD\u0916"sv, { 0u, 33u });
}
template<size_t N>
static void test_word_segmentation(StringView string, size_t const (&expected_boundaries)[N])
{