bjoernager/rust
bjoernager/rust
1
Fork 0
Code Activity

Only keep one copy of the UTF8_CHAR_WIDTH table.

Browse source 
… instead of one of each of libcore and libstd_unicode.

Move the `utf8_char_width` function to `core::str`
under the `str_internals` unstable feature.
This commit is contained in:
Simon Sapin 2017-03-01 22:41:44 +01:00
parent 691eba1358
commit 031f9b15df
6 changed files with 12 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/libstd_unicode/lib.rs
View file

@ -47,7 +47,7 @@ pub mod char;
#[allow(deprecated)]
pub mod str {
pub use u_str::{SplitWhitespace, UnicodeStr};
pub use u_str::{is_utf16, utf8_char_width};
pub use u_str::is_utf16;
pub use u_str::Utf16Encoder;
}

26
src/libstd_unicode/u_str.rs
View file

@ -77,32 +77,6 @@ impl UnicodeStr for str {
}
}
// https://tools.ietf.org/html/rfc3629
static UTF8_CHAR_WIDTH: [u8; 256] = [
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // 0x1F
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // 0x3F
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // 0x5F
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // 0x7F
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 0x9F
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 0xBF
0,0,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // 0xDF
3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3, // 0xEF
4,4,4,4,4,0,0,0,0,0,0,0,0,0,0,0, // 0xFF
];
/// Given a first byte, determine how many bytes are in this UTF-8 character
#[inline]
pub fn utf8_char_width(b: u8) -> usize {
return UTF8_CHAR_WIDTH[b as usize] as usize;
}
/// Determines if a vector of `u16` contains valid UTF-16
pub fn is_utf16(v: &[u16]) -> bool {
let mut it = v.iter();