HaoYang670 commented on a change in pull request #1374:
URL: https://github.com/apache/arrow-rs/pull/1374#discussion_r816532130
##########
File path: arrow/src/compute/kernels/aggregate.rs
##########
@@ -32,39 +32,26 @@ fn is_nan<T: ArrowNativeType + PartialOrd + Copy>(a: T) ->
bool {
!(a == a)
}
-/// Helper macro to perform min/max of strings
-fn min_max_string<T: StringOffsetSizeTrait, F: Fn(&str, &str) -> bool>(
- array: &GenericStringArray<T>,
- cmp: F,
-) -> Option<&str> {
+/// Helper function to perform min/max of strings
+fn min_max_string<T, F>(array: &GenericStringArray<T>, cmp: F) -> Option<&str>
+where
+ T: StringOffsetSizeTrait,
+ F: Fn(&str, &str) -> bool,
+{
let null_count = array.null_count();
if null_count == array.len() {
- return None;
- }
- let data = array.data();
- let mut n;
- if null_count == 0 {
- n = array.value(0);
- for i in 1..data.len() {
- let item = array.value(i);
- if cmp(n, item) {
- n = item;
- }
- }
+ None
+ } else if null_count == 0 {
+ (0..array.len())
+ .map(|i| array.value(i))
+ .reduce(|acc, item| if cmp(acc, item) { item } else { acc })
} else {
- n = "";
- let mut has_value = false;
-
- for i in 0..data.len() {
- let item = array.value(i);
- if data.is_valid(i) && (!has_value || cmp(n, item)) {
- has_value = true;
- n = item;
- }
- }
+ array
Review comment:
No. You can see the benchmark "min nulls string 512". Time decreases
from 2.4us to 1.8us. I this this is a performance improvement.
--
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]
