RGBCube/uutils-coreutils
1
Fork 0
mirror of https://github.com/RGBCube/uutils-coreutils synced 2025-07-29 12:07:46 +00:00
Code Issues Activity

Remove utf8 feature

Browse source 
All code it provides can be implemented with `std`.
This commit is contained in:
Vinzent Steinberg 2018-09-04 14:49:27 +02:00
parent e46e3594d2
commit bc78bcac7d
5 changed files with 2 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/expand/expand.rs
View file

@ -179,7 +179,7 @@ fn expand(options: Options) {
while byte < buf.len() {
let (ctype, cwidth, nbytes) = if options.uflag {
let nbytes = uucore::utf8::utf8_char_width(buf[byte]);
let nbytes = char::from(buf[byte]).len_utf8();
if byte + nbytes > buf.len() {
// don't overrun buffer because of invalid UTF-8

1
src/unexpand/Cargo.toml
View file

@ -14,7 +14,6 @@ unicode-width = "0.1.5"
[dependencies.uucore]
path = "../uucore"
features = ["utf8"]
[[bin]]
name = "unexpand"

2
src/unexpand/unexpand.rs
View file

@ -239,7 +239,7 @@ fn unexpand(options: Options) {
}
let (ctype, cwidth, nbytes) = if options.uflag {
let nbytes = uucore::utf8::utf8_char_width(buf[byte]);
let nbytes = char::from(buf[byte]).len_utf8();
// figure out how big the next char is, if it's UTF-8
if byte + nbytes > buf.len() {

2
src/uucore/lib.rs
View file

@ -18,8 +18,6 @@ pub mod panic;
#[cfg(feature = "fs")]
pub mod fs;
#[cfg(feature = "utf8")]
pub mod utf8;
#[cfg(feature = "encoding")]
pub mod encoding;
#[cfg(feature = "parse_time")]

27
src/uucore/utf8.rs
View file

@ -1,27 +0,0 @@
/* This is taken from the rust_unicode crate. Remove once 'unicode' becomes stable */
// 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;
}