user0/rust
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Optimize is_utf8

Browse source 
Manually unroll the multibyte loops, and optimize for the single
byte chars.
This commit is contained in:
Gary Linscott 2013-07-10 17:06:16 -04:00
parent 179637304a
commit 5aee5a11e3
2 changed files with 27 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/test/run-pass/utf8_chars.rs
View file

@ -27,9 +27,20 @@ pub fn main() {
assert!(s.char_at(1u) == 'é');
assert!((str::is_utf8(s.as_bytes())));
// invalid prefix
assert!((!str::is_utf8(~[0x80_u8])));
// invalid 2 byte prefix
assert!((!str::is_utf8(~[0xc0_u8])));
assert!((!str::is_utf8(~[0xc0_u8, 0x10_u8])));
// invalid 3 byte prefix
assert!((!str::is_utf8(~[0xe0_u8])));
assert!((!str::is_utf8(~[0xe0_u8, 0x10_u8])));
assert!((!str::is_utf8(~[0xe0_u8, 0xff_u8, 0x10_u8])));
// invalid 4 byte prefix
assert!((!str::is_utf8(~[0xf0_u8])));
assert!((!str::is_utf8(~[0xf0_u8, 0x10_u8])));
assert!((!str::is_utf8(~[0xf0_u8, 0xff_u8, 0x10_u8])));
assert!((!str::is_utf8(~[0xf0_u8, 0xff_u8, 0xff_u8, 0x10_u8])));
let mut stack = ~"a×c€";
assert_eq!(stack.pop_char(), '€');