aboutsummaryrefslogtreecommitdiff
path: root/test/functional/ui/multibyte_spec.lua
diff options
context:
space:
mode:
authorbfredl <bjorn.linse@gmail.com>2023-11-06 14:52:27 +0100
committerbfredl <bjorn.linse@gmail.com>2023-11-17 12:58:57 +0100
commitb522cb1ac3fbdf6e68eed5d0b6e1cbeaf3ac2254 (patch)
tree434ec27e069ba57406ce9f6d194627e95c3d315c /test/functional/ui/multibyte_spec.lua
parent20ec4c776a07492c2e3b995e10b40b1cdb52bc7a (diff)
downloadrneovim-b522cb1ac3fbdf6e68eed5d0b6e1cbeaf3ac2254.tar.gz
rneovim-b522cb1ac3fbdf6e68eed5d0b6e1cbeaf3ac2254.tar.bz2
rneovim-b522cb1ac3fbdf6e68eed5d0b6e1cbeaf3ac2254.zip
refactor(grid): make screen rendering more multibyte than ever before
Problem: buffer text with composing chars are converted from UTF-8 to an array of up to seven UTF-32 values and then converted back to UTF-8 strings. Solution: Convert buffer text directly to UTF-8 based schar_T values. The limit of the text size is now in schar_T bytes, which is currently 31+1 but easily could be raised as it no longer multiplies the size of the entire screen grid when not used, the full size is only required for temporary scratch buffers. Also does some general cleanup to win_line text handling, which was unnecessarily complicated due to multibyte rendering being an "opt-in" feature long ago. Nowadays, a char is just a char, regardless if it consists of one ASCII byte or multiple bytes.
Diffstat (limited to 'test/functional/ui/multibyte_spec.lua')
-rw-r--r--test/functional/ui/multibyte_spec.lua30
1 files changed, 30 insertions, 0 deletions
diff --git a/test/functional/ui/multibyte_spec.lua b/test/functional/ui/multibyte_spec.lua
index 077dd1a779..d72bf27d6b 100644
--- a/test/functional/ui/multibyte_spec.lua
+++ b/test/functional/ui/multibyte_spec.lua
@@ -228,6 +228,36 @@ describe("multibyte rendering", function()
]]}
end)
+
+ it('works with arabicshape and multiple composing chars', function()
+ -- this tests an important edge case: arabicshape might increase the byte size of the base
+ -- character in a way so that the last composing char no longer fits. use "g8" on the text
+ -- to observe what is happening (the final E1 80 B7 gets deleted with 'arabicshape')
+ -- If we would increase the schar_t size, say from 32 to 64 bytes, we need to extend the
+ -- test text with even more zalgo energy to still touch this edge case.
+
+ meths.buf_set_lines(0,0,-1,true, {"سلام့̀́̂̃̄̅̆̇̈̉̊̋̌"})
+ command('set noarabicshape')
+
+ screen:expect{grid=[[
+ ^سلام့̀́̂̃̄̅̆̇̈̉̊̋̌ |
+ {1:~ }|
+ {1:~ }|
+ {1:~ }|
+ {1:~ }|
+ |
+ ]]}
+
+ command('set arabicshape')
+ screen:expect{grid=[[
+ ^ﺱﻼﻣ̀́̂̃̄̅̆̇̈̉̊̋̌ |
+ {1:~ }|
+ {1:~ }|
+ {1:~ }|
+ {1:~ }|
+ |
+ ]]}
+ end)
end)
describe('multibyte rendering: statusline', function()