jayzhan211 commented on code in PR #8081:
URL: https://github.com/apache/arrow-datafusion/pull/8081#discussion_r1387992400
##########
datafusion/physical-expr/src/array_expressions.rs:
##########
@@ -1807,6 +1809,62 @@ pub fn string_to_array<T: OffsetSizeTrait>(args:
&[ArrayRef]) -> Result<ArrayRef
Ok(Arc::new(list_array) as ArrayRef)
}
+/// array_intersect SQL function
+pub fn array_intersect(args: &[ArrayRef]) -> Result<ArrayRef> {
+ assert_eq!(args.len(), 2);
+
+ let first_array = as_list_array(&args[0])?;
+ let second_array = as_list_array(&args[1])?;
+
+ if first_array.value_type() != second_array.value_type() {
+ return internal_err!("array_intersect is not implemented for
'{first_array:?}' and '{second_array:?}'");
+ }
+ let dt = first_array.value_type().clone();
+
+ let mut offsets = vec![0];
+ let mut tmp_values = vec![];
+
+ let converter = RowConverter::new(vec![SortField::new(dt.clone())])?;
+ for (first_arr, second_arr) in first_array.iter().zip(second_array.iter())
{
+ if let (Some(first_arr), Some(second_arr)) = (first_arr, second_arr) {
+ let l_values = converter.convert_columns(&[first_arr])?;
+ let r_values = converter.convert_columns(&[second_arr])?;
+
+ let values_set: HashSet<_> = l_values.iter().collect();
+ let mut rows = Vec::with_capacity(r_values.num_rows());
+ for r_val in r_values.iter().sorted().dedup() {
+ if values_set.contains(&r_val) {
+ rows.push(r_val);
+ }
+ }
+
+ let last_offset: i32 = match offsets.last().copied() {
+ Some(offset) => offset,
+ None => return internal_err!("offsets should not be empty"),
+ };
+ offsets.push(last_offset + rows.len() as i32);
+ let tmp_value = converter.convert_rows(rows)?;
Review Comment:
can you rename tmp_xxx to others? like arrays, elements or concated_arrays.
I think this is far from tmp_xxx
--
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]
