tlm365 commented on code in PR #13696:
URL: https://github.com/apache/datafusion/pull/13696#discussion_r1875613725
##########
datafusion/functions/src/unicode/character_length.rs:
##########
@@ -136,31 +136,40 @@ fn character_length(args: &[ArrayRef]) ->
Result<ArrayRef> {
}
}
-fn character_length_general<'a, T: ArrowPrimitiveType, V: StringArrayType<'a>>(
- array: V,
-) -> Result<ArrayRef>
+fn character_length_general<'a, T, V>(array: V) -> Result<ArrayRef>
where
+ T: ArrowPrimitiveType,
T::Native: OffsetSizeTrait,
+ V: StringArrayType<'a>,
{
+ let mut builder = PrimitiveBuilder::<T>::with_capacity(array.len());
+
// String characters are variable length encoded in UTF-8, counting the
// number of chars requires expensive decoding, however checking if the
// string is ASCII only is relatively cheap.
// If strings are ASCII only, count bytes instead.
let is_array_ascii_only = array.is_ascii();
- let iter = array.iter();
- let result = iter
- .map(|string| {
- string.map(|string: &str| {
- if is_array_ascii_only {
- T::Native::usize_as(string.len())
- } else {
- T::Native::usize_as(string.chars().count())
- }
- })
- })
- .collect::<PrimitiveArray<T>>();
-
- Ok(Arc::new(result) as ArrayRef)
+ if is_array_ascii_only {
+ for i in 0..array.len() {
+ if array.is_null(i) {
Review Comment:
@Dandandan Thank you so much for the review. Yeah, nice catch 👍
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
