Skip to content

Match common encoding names before normalizing them #8862

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

Merged
youknowone merged 1 commit into from
Sep 27, 2026
Merged

Match common encoding names before normalizing them #8862

Show file tree
Hide file tree
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
7 changes: 7 additions & 0 deletions crates/vm/src/codecs.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -596,6 +596,13 @@ impl FastCodec {
"latin",
"latin1",
];
// The spellings used most often, matched before normalizing allocates.
match encoding {
"utf-8" | "utf8" | "UTF-8" => return Some(Self::Utf8),
"ascii" => return Some(Self::Ascii),
"latin-1" | "latin1" | "iso-8859-1" => return Some(Self::Latin1),
_ => {}
}
let normalized = normalize_encoding_name(encoding);
let normalized = normalized.as_ref();
if UTF8_ALIASES.contains(&normalized) {
Expand Down
15 changes: 15 additions & 0 deletions extra_tests/snippets/builtin_str_encode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,3 +41,18 @@ def round_trip(s, encoding="utf-8"):
assert "\ud800\ud800".encode("unicode_escape") == b"\\ud800\\ud800"
assert "\ud800\udc00".encode("unicode_escape") == b"\\ud800\\udc00"
assert "\U00010000".encode("unicode_escape") == b"\\U00010000"

# Common encoding spellings pick the same codec, with its canonical name in errors
for spelling in ["utf-8", "utf8", "UTF-8", "Utf-8", "utf_8"]:
assert "é€".encode(spelling) == b"\xc3\xa9\xe2\x82\xac"
with assert_raises(UnicodeDecodeError, _msg=spelling) as cm:
b"\xff".decode(spelling)
assert str(cm.exception).startswith("'utf-8' codec"), str(cm.exception)
for spelling in ["latin-1", "latin1", "iso-8859-1", "l1"]:
assert b"\xe9".decode(spelling) == "é"
with assert_raises(UnicodeEncodeError) as cm:
"€".encode(spelling)
assert str(cm.exception).startswith("'latin-1' codec"), str(cm.exception)
with assert_raises(UnicodeEncodeError) as cm:
"é".encode("ascii")
assert str(cm.exception).startswith("'ascii' codec"), str(cm.exception)
Loading