jonahgao commented on code in PR #9475:
URL: https://github.com/apache/arrow-datafusion/pull/9475#discussion_r1515371821
##########
datafusion/physical-expr/src/unicode_expressions.rs:
##########
@@ -481,40 +481,28 @@ pub fn substr_index<T: OffsetSizeTrait>(args:
&[ArrayRef]) -> Result<ArrayRef> {
.zip(count_array.iter())
.map(|((string, delimiter), n)| match (string, delimiter, n) {
(Some(string), Some(delimiter), Some(n)) => {
- let mut res = String::new();
- match n {
- 0 => {
- "".to_string();
- }
- _other => {
- if n > 0 {
- let idx = string
- .split(delimiter)
- .take(n as usize)
- .fold(0, |len, x| len + x.len() +
delimiter.len())
- - delimiter.len();
- res.push_str(if idx >= string.len() {
- string
- } else {
- &string[..idx]
- });
- } else {
- let idx = (string.split(delimiter).take((-n) as
usize).fold(
- string.len() as isize,
- |len, x| {
- len - x.len() as isize - delimiter.len()
as isize
- },
- ) + delimiter.len() as isize)
- as usize;
- res.push_str(if idx >= string.len() {
- string
- } else {
- &string[idx..]
- });
- }
- }
+ // In MySQL, these cases will return an empty string.
Review Comment:
> About the MySQL comments, does that mean some cases are not the same
between MySQL and Postgres?
No, actually there is no such function in PostgreSQL. The closest one is
[split_part](https://www.postgresql.org/docs/current/functions-string.html),
but their functionalities are different.
--
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]
