Skip to content

Clarify UTF-16 decoding errors #149696

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jnodorp wants to merge 1 commit into
base: main
Choose a base branch
from
+20 −7
Open

Clarify UTF-16 decoding errors #149696

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 20 additions & 7 deletions library/alloc/src/string.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -410,7 +410,16 @@ pub struct FromUtf8Error {
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
#[derive(Debug)]
pub struct FromUtf16Error(());
pub struct FromUtf16Error {
kind: FromUtf16ErrorKind,
}

#[cfg_attr(no_global_oom_handling, allow(dead_code))]
#[derive(Clone, PartialEq, Eq, Debug)]
enum FromUtf16ErrorKind {
LoneSurrogate,
OddBytes,
}

impl String {
/// Creates a new empty `String`.
Expand Down Expand Up @@ -723,7 +732,7 @@ impl String {
if let Ok(c) = c {
ret.push(c);
} else {
return Err(FromUtf16Error(()));
return Err(FromUtf16Error { kind: FromUtf16ErrorKind::LoneSurrogate });
}
}
Ok(ret)
Expand Down Expand Up @@ -785,13 +794,13 @@ impl String {
#[unstable(feature = "str_from_utf16_endian", issue = "116258")]
pub fn from_utf16le(v: &[u8]) -> Result<String, FromUtf16Error> {
let (chunks, []) = v.as_chunks::<2>() else {
return Err(FromUtf16Error(()));
return Err(FromUtf16Error { kind: FromUtf16ErrorKind::OddBytes });
};
match (cfg!(target_endian = "little"), unsafe { v.align_to::<u16>() }) {
(true, ([], v, [])) => Self::from_utf16(v),
_ => char::decode_utf16(chunks.iter().copied().map(u16::from_le_bytes))
.collect::<Result<_, _>>()
.map_err(|_| FromUtf16Error(())),
.map_err(|_| FromUtf16Error { kind: FromUtf16ErrorKind::LoneSurrogate }),
}
}

Expand Down Expand Up @@ -860,13 +869,13 @@ impl String {
#[unstable(feature = "str_from_utf16_endian", issue = "116258")]
pub fn from_utf16be(v: &[u8]) -> Result<String, FromUtf16Error> {
let (chunks, []) = v.as_chunks::<2>() else {
return Err(FromUtf16Error(()));
return Err(FromUtf16Error { kind: FromUtf16ErrorKind::OddBytes });
};
match (cfg!(target_endian = "big"), unsafe { v.align_to::<u16>() }) {
(true, ([], v, [])) => Self::from_utf16(v),
_ => char::decode_utf16(chunks.iter().copied().map(u16::from_be_bytes))
.collect::<Result<_, _>>()
.map_err(|_| FromUtf16Error(())),
.map_err(|_| FromUtf16Error { kind: FromUtf16ErrorKind::LoneSurrogate }),
}
}

Expand Down Expand Up @@ -2332,7 +2341,11 @@ impl fmt::Display for FromUtf8Error {
#[stable(feature = "rust1", since = "1.0.0")]
impl fmt::Display for FromUtf16Error {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fmt::Display::fmt("invalid utf-16: lone surrogate found", f)
match self.kind {
FromUtf16ErrorKind::LoneSurrogate => "invalid utf-16: lone surrogate found",
FromUtf16ErrorKind::OddBytes => "invalid utf-16: odd number of bytes",
}
.fmt(f)
}
}

Expand Down
Loading