tustvold commented on code in PR #1577:
URL: https://github.com/apache/arrow-rs/pull/1577#discussion_r852752035
##########
arrow/src/compute/kernels/substring.rs:
##########
@@ -35,37 +36,45 @@ fn generic_substring<OffsetSize: StringOffsetSizeTrait>(
let data = values.as_slice();
let zero = OffsetSize::zero();
- let cal_new_start: Box<dyn Fn(OffsetSize, OffsetSize) -> OffsetSize> = if
start
- >= zero
- {
- // count from the start of string
- Box::new(|old_start: OffsetSize, end: OffsetSize| (old_start +
start).min(end))
- } else {
- // count from the end of string
- Box::new(|old_start: OffsetSize, end: OffsetSize| (end +
start).max(old_start))
+ // Check if `offset` is at a valid char boundary.
+ // If yes, return `offset`, else return error
+ let check_char_boundary = {
+ let data_str = unsafe { std::str::from_utf8_unchecked(data) };
Review Comment:
```suggestion
// Safety: a StringArray must contain valid UTF8 data
let data_str = unsafe { std::str::from_utf8_unchecked(data) };
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
