nik/lush
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Correction in utf8.offset

Browse Source 
Wrong utf-8 character may have no continuation bytes.
This commit is contained in:
Roberto Ierusalimschy
2025-07-18 16:10:28 -03:00
parent 60b6599e83
commit ccb8b307f1
2 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
testes/utf8.lua
View File

@@ -152,11 +152,20 @@ checkerror("position out of bounds", utf8.offset, "", 1, -1)
checkerror("continuation byte", utf8.offset, "𦧺", 1, 2)
checkerror("continuation byte", utf8.offset, "𦧺", 1, 2)
checkerror("continuation byte", utf8.offset, "\x80", 1)
checkerror("continuation byte", utf8.offset, "\x9c", -1)
-- error in indices for len
checkerror("out of bounds", utf8.len, "abc", 0, 2)
checkerror("out of bounds", utf8.len, "abc", 1, 4)
do -- missing continuation bytes
-- get what is available
local p, e = utf8.offset("\xE0", 1)
assert(p == 1 and e == 1)
local p, e = utf8.offset("\xE0\x9e", -1)
assert(p == 1 and e == 2)
end
local s = "hello World"
local t = {string.byte(s, 1, -1)}