Skip to content

Report invalid \uXXXX escape position at the u character #7676

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 3 commits into from
Apr 26, 2026
Merged

Report invalid \uXXXX escape position at the u character #7676

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
30c0bfc
Report invalid \uXXXX escape position at the u character
changjoon-park Apr 24, 2026
cf9c6b6
Add regression test for invalid \uXXXX escape position
changjoon-park Apr 25, 2026
3ce5dda
Use raise AssertionError instead of assert False (B011)
changjoon-park Apr 25, 2026
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
11 changes: 7 additions & 4 deletions crates/stdlib/src/json/machinery.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,17 +231,20 @@ pub fn scanstring<'a>(
'r' => "\r",
't' => "\t",
'u' => {
let mut uni = decode_unicode(&mut chars, char_offset + char_i)?;
// Error position for an invalid \uXXXX escape points at the
// `u`, not the `\` -- matches CPython's json.decoder.
let mut uni = decode_unicode(&mut chars, char_offset + next_char_i)?;
chunk_start = byte_i + 6;
if let Some(lead) = uni.to_lead_surrogate() {
// uni is a surrogate -- try to find its pair
let mut chars2 = chars.clone();
if let Some(((_, (byte_pos2, _)), (_, _))) = chars2
if let Some(((_, (byte_pos2, _)), (u2_char_i, (_, _)))) = chars2
.next_tuple()
.filter(|((_, (_, c1)), (_, (_, c2)))| *c1 == '\\' && *c2 == 'u')
{
let uni2 =
decode_unicode(&mut chars2, char_offset + next_char_i + 1)?;
// u2_char_i is the `u` of the second \uXXXX; same
// position convention as the primary call above.
let uni2 = decode_unicode(&mut chars2, char_offset + u2_char_i)?;
if let Some(trail) = uni2.to_trail_surrogate() {
// ok, we found what we were looking for -- \uXXXX\uXXXX, both surrogates
uni = lead.merge(trail).into();
Expand Down
16 changes: 16 additions & 0 deletions extra_tests/snippets/stdlib_json.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,3 +239,19 @@ class Dict(dict):
RecursionError,
lambda: json.loads(('[{"x":' * _deep) + "1" + ("}]" * _deep)),
)


# Invalid \uXXXX escape: error position points at the 'u', matching CPython.
try:
json.loads('"\\uXYZW"')
except json.JSONDecodeError as e:
assert e.pos == 2, f"expected pos=2, got {e.pos}"
else:
raise AssertionError("expected JSONDecodeError")

try:
json.loads('"abc\\uZZZZ"')
except json.JSONDecodeError as e:
assert e.pos == 5, f"expected pos=5, got {e.pos}"
else:
raise AssertionError("expected JSONDecodeError")
Loading