alamb commented on a change in pull request #1660:
URL: https://github.com/apache/arrow-datafusion/pull/1660#discussion_r796026830
##########
File path: datafusion/src/physical_plan/unicode_expressions.rs
##########
@@ -457,21 +457,29 @@ pub fn substr<T: StringOffsetSizeTrait>(args:
&[ArrayRef]) -> Result<ArrayRef> {
start,
count
)))
- } else if start <= 0 {
- Ok(Some(string.to_string()))
} else {
let graphemes =
string.graphemes(true).collect::<Vec<&str>>();
- let start_pos = start as usize - 1;
- let count_usize = count as usize;
- if graphemes.len() < start_pos {
+ let (start_pos, end_pos) = if start <= 0 {
+ let end_pos = start + count - 1;
+ (
+ 0_usize,
+ if end_pos < 0 {
+ // we use 0 as workaround for usize to
return empty string
+ 0
+ } else {
+ end_pos as usize
+ },
Review comment:
@ovr would you like to make this change so we can merge the PR? I can
find some time to do so too if that would help.
--
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]
