Jefffrey commented on code in PR #21366:
URL: https://github.com/apache/datafusion/pull/21366#discussion_r3091329333
##########
datafusion/functions/src/unicode/substr.rs:
##########
@@ -319,15 +318,107 @@ fn string_view_substr(
}
}
-fn string_substr<'a, V>(string_array: V, args: &[ArrayRef]) -> Result<ArrayRef>
-where
- V: StringArrayType<'a> + Copy,
-{
+fn values_fit_in_u32<T: OffsetSizeTrait>(string_array: &GenericStringArray<T>)
-> bool {
+ string_array
+ .offsets()
+ .last()
+ .map(|offset| offset.as_usize() <= u32::MAX as usize)
+ .unwrap_or(true)
+}
+
+#[inline]
+fn append_view_from_buffer(
+ views_buf: &mut Vec<u128>,
+ substr: &str,
+ byte_offset: usize,
+) -> bool {
+ let is_out_of_line = substr.len() > 12;
+ let view = if is_out_of_line {
+ let byte_offset = u32::try_from(byte_offset)
+ .expect("validated string buffer offset fits in u32");
+ make_view(substr.as_bytes(), 0, byte_offset)
+ } else {
+ make_view(substr.as_bytes(), 0, 0)
Review Comment:
Do we strictly need this branching?
##########
datafusion/functions/src/unicode/substr.rs:
##########
@@ -319,15 +318,107 @@ fn string_view_substr(
}
}
-fn string_substr<'a, V>(string_array: V, args: &[ArrayRef]) -> Result<ArrayRef>
-where
- V: StringArrayType<'a> + Copy,
-{
+fn values_fit_in_u32<T: OffsetSizeTrait>(string_array: &GenericStringArray<T>)
-> bool {
+ string_array
+ .offsets()
+ .last()
+ .map(|offset| offset.as_usize() <= u32::MAX as usize)
Review Comment:
Same comment as on left/right PR, where we should check `i32::MAX`
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
