Skip to content

Fix canonical json utf-16 surrogate pair detection logic #423

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
merged 2 commits into from
Dec 12, 2023
Merged

Fix canonical json utf-16 surrogate pair detection logic #423

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a907b4f
Fix canonical json utf-16 surrogate pair detection logic
devonh Dec 8, 2023
6a0f0bd
Merge branch 'main' into utf16-json
S7evinK Dec 12, 2023
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
2 changes: 1 addition & 1 deletion json.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -329,7 +329,7 @@ func compactUnicodeEscape(input, output []byte, index int) ([]byte, int) {
// Otherwise the character only needs escaping if it is a QUOTE '"' or BACKSLASH '\\'.
output = append(output, '\\', byte(c))
} else if utf16.IsSurrogate(c) {
if input[index] != '\\' && input[index+1] != 'u' {
if input[index] != '\\' || input[index+1] != 'u' {
return output, index
}
index += 2 // skip the \u"
Expand Down
20 changes: 20 additions & 0 deletions json_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,26 @@ func TestCompactUnicodeEscapeWithUTF16Surrogate(t *testing.T) {
}
}

func TestCompactUnicodeEscapeWithBadUTF16Surrogate(t *testing.T) {
input := []byte(`\ud83d\zdc08`)
output, n := compactUnicodeEscape(input[2:], nil, 0)
if n != 4 {
t.Fatalf("should have consumed 4 bytes but consumed %d bytes", n)
}
if string(output) != "" {
t.Fatalf("expected output to be empty")
}

input = []byte(`\ud83d udc08`)
output, n = compactUnicodeEscape(input[2:], nil, 0)
if n != 4 {
t.Fatalf("should have consumed 4 bytes but consumed %d bytes", n)
}
if string(output) != "" {
t.Fatalf("expected output to be empty")
}
}

func testReadHex(t *testing.T, input string, want rune) {
got := readHexDigits([]byte(input))
if want != got {
Expand Down