1
0
Fork 0
mirror of https://github.com/denoland/deno.git synced 2025-01-21 21:50:00 -05:00
denoland-deno/cli/lib/util/text_encoding.rs
David Sherret 57dd66ec3d
refactor: move denort to separate crate (#27688)
This slightly degrades the performance of CJS export analysis on
subsequent runs because I changed it to no longer cache in the DENO_DIR
with this PR (denort now properly has no idea about the DENO_DIR). We'll
have to change it to embed this data in the binary and that will also
allow us to get rid of swc in denort (will do that in a follow-up PR).
2025-01-17 20:39:29 +00:00

45 lines
1.4 KiB
Rust

// Copyright 2018-2025 the Deno authors. MIT license.
use std::borrow::Cow;
use std::sync::Arc;
#[inline(always)]
pub fn from_utf8_lossy_owned(bytes: Vec<u8>) -> String {
match String::from_utf8_lossy(&bytes) {
Cow::Owned(code) => code,
// SAFETY: `String::from_utf8_lossy` guarantees that the result is valid
// UTF-8 if `Cow::Borrowed` is returned.
Cow::Borrowed(_) => unsafe { String::from_utf8_unchecked(bytes) },
}
}
#[inline(always)]
pub fn from_utf8_lossy_cow(bytes: Cow<[u8]>) -> Cow<str> {
match bytes {
Cow::Borrowed(bytes) => String::from_utf8_lossy(bytes),
Cow::Owned(bytes) => Cow::Owned(from_utf8_lossy_owned(bytes)),
}
}
/// Converts an `Arc<str>` to an `Arc<[u8]>`.
#[allow(dead_code)]
pub fn arc_str_to_bytes(arc_str: Arc<str>) -> Arc<[u8]> {
let raw = Arc::into_raw(arc_str);
// SAFETY: This is safe because they have the same memory layout.
unsafe { Arc::from_raw(raw as *const [u8]) }
}
/// Converts an `Arc<u8>` to an `Arc<str>` if able.
#[allow(dead_code)]
pub fn arc_u8_to_arc_str(
arc_u8: Arc<[u8]>,
) -> Result<Arc<str>, std::str::Utf8Error> {
// Check that the string is valid UTF-8.
std::str::from_utf8(&arc_u8)?;
// SAFETY: the string is valid UTF-8, and the layout Arc<[u8]> is the same as
// Arc<str>. This is proven by the From<Arc<str>> impl for Arc<[u8]> from the
// standard library.
Ok(unsafe {
std::mem::transmute::<std::sync::Arc<[u8]>, std::sync::Arc<str>>(arc_u8)
})
}