Skip to content

text: replace deprecated std.unicode.utf8Decode #750

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
fizzy-pm merged 3 commits into from
Oct 26, 2026
Merged

text: replace deprecated std.unicode.utf8Decode #750

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b5b8d34
text: replace deprecated std.unicode.utf8Decode
foxnne Oct 22, 2026
7c9d2d9
Merge main into text/utf8-decode
fizzy-linux[bot] Oct 26, 2026
e47608f
text: test appendLossy on malformed multi-byte sequences
fizzy-linux[bot] Oct 26, 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: 8 additions & 3 deletions plugins/text/src/textcore/encoding.zig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ pub fn looksBinary(bytes: []const u8) bool {
while (i < sample.len) {
const n = std.unicode.utf8ByteSequenceLength(sample[i]) catch return true;
if (i + n > sample.len) break;
_ = std.unicode.utf8Decode(sample[i..][0..n]) catch return true;
if (!std.unicode.utf8ValidateSlice(sample[i..][0..n])) return true;
i += n;
}
return false;
Expand Down Expand Up @@ -61,10 +61,10 @@ pub fn appendLossy(list: *std.ArrayList(u8), gpa: std.mem.Allocator, bytes: []co
try list.appendSlice(gpa, replacement);
break;
}
if (std.unicode.utf8Decode(bytes[i..][0..n])) |_| {
if (std.unicode.utf8ValidateSlice(bytes[i..][0..n])) {
try list.appendSlice(gpa, bytes[i .. i + n]);
i += n;
} else |_| {
} else {
try list.appendSlice(gpa, replacement);
i += 1;
}
Expand All @@ -79,4 +79,9 @@ test appendLossy {
list.clearRetainingCapacity();
try appendLossy(&list, std.testing.allocator, "a\x00b\xffc");
try std.testing.expectEqualStrings("a\u{FFFD}b\u{FFFD}c", list.items);
list.clearRetainingCapacity();
// Well-formed multi-byte sequences pass through; a bad continuation byte or a surrogate
// is replaced a byte at a time.
try appendLossy(&list, std.testing.allocator, "\xc3\xa9\xe2\x28\xa1\xed\xa0\x80");
try std.testing.expectEqualStrings("\u{e9}\u{FFFD}(\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}", list.items);
}
Loading