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

Rollup merge of #144472 - okaneco:char_bound, r=Mark-Simulacrum

Browse source 
str: Mark unstable `round_char_boundary` feature functions as const

Mark `floor_char_boundary`, `ceil_char_boundary` const
Simplify the implementations, reducing the number of arithmetic operations

It seems unnecessary to do the lower/upper bounds calculations and extra slicing when we can jump straight to inspecting the bytes, assuming the underlying data is valid UTF-8.

Tracking issue https://github.com/rust-lang/rust/issues/93743
This commit is contained in:
Matthias Krüger 2025-07-28 08:36:53 +02:00 • committed by GitHub
commit e36b844b4e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 25 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

38
library/core/src/str/mod.rs
View file

@ -407,17 +407,22 @@ impl str {
/// ```
#[unstable(feature = "round_char_boundary", issue = "93743")]
#[inline]
pub fn floor_char_boundary(&self, index: usize) -> usize {
pub const fn floor_char_boundary(&self, index: usize) -> usize {
if index >= self.len() {
self.len()
} else {
let lower_bound = index.saturating_sub(3);
let new_index = self.as_bytes()[lower_bound..=index]
.iter()
.rposition(|b| b.is_utf8_char_boundary());
let mut i = index;
while i > 0 {
if self.as_bytes()[i].is_utf8_char_boundary() {
break;
}
i -= 1;
}
// SAFETY: we know that the character boundary will be within four bytes
unsafe { lower_bound + new_index.unwrap_unchecked() }
// The character boundary will be within four bytes of the index
debug_assert!(i >= index.saturating_sub(3));
i
}
}
@ -445,15 +450,22 @@ impl str {
/// ```
#[unstable(feature = "round_char_boundary", issue = "93743")]
#[inline]
pub fn ceil_char_boundary(&self, index: usize) -> usize {
pub const fn ceil_char_boundary(&self, index: usize) -> usize {
if index >= self.len() {
self.len()
} else {
let upper_bound = Ord::min(index + 4, self.len());
self.as_bytes()[index..upper_bound]
.iter()
.position(|b| b.is_utf8_char_boundary())
.map_or(upper_bound, |pos| pos + index)
let mut i = index;
while i < self.len() {
if self.as_bytes()[i].is_utf8_char_boundary() {
break;
}
i += 1;
}
// The character boundary will be within four bytes of the index
debug_assert!(i <= index + 3);
i
}
}