mirrors/v
1
0
Fork 0
mirror of https://github.com/vlang/v.git synced 2025-09-16 07:52:32 +03:00
Code Issues Projects Releases Packages Wiki Activity Actions 24

encoding.utf8: add more tests for UTF-8 strings (#24544)

Browse source
This commit is contained in:
Laurent Cheylus 2025-05-21 17:45:01 +02:00 • committed by GitHub
parent a5c8b4f94a
commit 31c6db51ba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 91 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

13
vlib/encoding/utf8/validate/validate_utf8.v
View file

@ -48,6 +48,19 @@ fn (mut s Utf8State) seq(r0 bool, r1 bool, is_tail bool) bool {
return false
}
/* Check UTF-8 Byte sequences according to Unicode Standard
* https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/
* Code Points 1st 2s 3s 4s
* U+0000..U+007F 00..7F
* U+0080..U+07FF C2..DF 80..BF
* U+0800..U+0FFF E0 A0..BF 80..BF
* U+1000..U+CFFF E1..EC 80..BF 80..BF
* U+D000..U+D7FF ED 80..9F 80..BF
* U+E000..U+FFFF EE..EF 80..BF 80..BF
* U+10000..U+3FFFF F0 90..BF 80..BF 80..BF
* U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
* U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
*/
fn (mut s Utf8State) next_state(c u8) {
// sequence 1
if s.index == 0 {