alamb commented on code in PR #11274:
URL: https://github.com/apache/arrow-rs/pull/11274#discussion_r4144910389
##########
arrow-string/src/regexp.rs:
##########
@@ -332,6 +332,7 @@ fn get_scalar_pattern_flag_utf8view<'a>(
macro_rules! process_regexp_match {
($array:expr, $regex:expr, $list_builder:expr) => {
+ let mut capture_locations = None;
Review Comment:
Can we add a small comment about the use of this (that it is a cache to
reuse the locations)?
##########
arrow-string/src/regexp.rs:
##########
@@ -342,19 +343,25 @@ macro_rules! process_regexp_match {
$list_builder.values().append_value("");
$list_builder.append(true);
}
- Some(value) => match $regex.captures(value) {
- Some(caps) => {
- let mut iter = caps.iter();
- if caps.len() > 1 {
- iter.next();
- }
- for m in iter.flatten() {
-
$list_builder.values().append_value(m.as_str());
+ Some(value) => {
+ let locations =
+ capture_locations.get_or_insert_with(||
$regex.capture_locations());
+ match $regex.captures_read(locations, value) {
Review Comment:
I think this is the key change -- to use
https://docs.rs/regex/latest/regex/struct.Regex.html#method.captures_read
instead of `captures`
--
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]
