GitHub/neovim
1
0
Fork 0
mirror of https://github.com/neovim/neovim synced 2025-07-16 01:01:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(lsp): str_byteindex_enc bounds checking #30747

Browse Source 
Problem:
Previously the index was only checked against the UTF8 length. This
could cause unexpected behaviours for strings containing multibyte chars

Solution:
Check indicies correctly against their max value before returning the
fallback length

(cherry picked from commit 80e37aa533)
This commit is contained in:
Tristan Knight
2024-10-16 17:12:19 +01:00
committed by github-actions[bot]
parent bbefbc995e
commit 84bbbd9fbe
1 changed files with 10 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
runtime/lua/vim/lsp/util.lua
View File

@ -155,25 +155,24 @@ end
---@param encoding string utf-8|utf-16|utf-32| defaults to utf-16 ---@param encoding string utf-8|utf-16|utf-32| defaults to utf-16
---@return integer byte (utf-8) index of `encoding` index `index` in `line` ---@return integer byte (utf-8) index of `encoding` index `index` in `line`
function M._str_byteindex_enc(line, index, encoding) function M._str_byteindex_enc(line, index, encoding)
local len = #line -- LSP spec: if character > line length, default to the line length.
if index > len then -- https://microsoft.github.io/language-server-protocol/specifications/lsp/3.17/specification/#position
-- LSP spec: if character > line length, default to the line length. local len8 = #line
-- https://microsoft.github.io/language-server-protocol/specifications/lsp/3.17/specification/#position
return len
end
if not encoding then if not encoding then
encoding = 'utf-16' encoding = 'utf-16'
end end
if encoding == 'utf-8' then if encoding == 'utf-8' then
if index then if index and index <= len8 then
return index return index
else else
return len return len8
end end
elseif encoding == 'utf-16' then end
return vim.str_byteindex(line, index, true) local len32, len16 = vim.str_utfindex(line)
if encoding == 'utf-16' then
return index <= len16 and vim.str_byteindex(line, index, true) or len8
elseif encoding == 'utf-32' then elseif encoding == 'utf-32' then
return vim.str_byteindex(line, index) return index <= len32 and vim.str_byteindex(line, index) or len8
else else
error('Invalid encoding: ' .. vim.inspect(encoding)) error('Invalid encoding: ' .. vim.inspect(encoding))
end end