Weijun-H commented on code in PR #8268:
URL: https://github.com/apache/arrow-datafusion/pull/8268#discussion_r1415632397
##########
datafusion/physical-expr/src/array_expressions.rs:
##########
@@ -1998,6 +1998,66 @@ pub fn array_intersect(args: &[ArrayRef]) ->
Result<ArrayRef> {
}
}
+pub fn general_array_distinct<OffsetSize: OffsetSizeTrait>(
+ array: &GenericListArray<OffsetSize>,
+ field: &FieldRef,
+) -> Result<ArrayRef> {
+ let dt = array.value_type();
+ let mut offsets = Vec::with_capacity(array.len());
+ offsets.push(OffsetSize::usize_as(0));
+ let mut new_arrays = Vec::with_capacity(array.len());
+ let converter = RowConverter::new(vec![SortField::new(dt.clone())])?;
+ // distinct for each list in ListArray
+ for arr in array.iter().flatten() {
+ let values = converter.convert_columns(&[arr])?;
+ // sort elements in list and remove duplicates
+ let rows = values.iter().sorted().dedup().collect::<Vec<_>>();
+ let last_offset: OffsetSize = offsets.last().copied().unwrap();
+ offsets.push(last_offset + OffsetSize::usize_as(rows.len()));
+ let arrays = converter.convert_rows(rows)?;
+ let array = match arrays.get(0) {
+ Some(array) => array.clone(),
+ None => {
+ return internal_err!("array_distinct: failed to get array from
rows")
+ }
+ };
+ new_arrays.push(array);
+ }
+ let offsets = OffsetBuffer::new(offsets.into());
+ let new_arrays_ref = new_arrays.iter().map(|v|
v.as_ref()).collect::<Vec<_>>();
+ let values = compute::concat(&new_arrays_ref)?;
+ Ok(Arc::new(GenericListArray::<OffsetSize>::try_new(
+ field.clone(),
+ offsets,
+ values,
+ None,
+ )?))
+}
+
+/// array_distinct SQL function
+/// example: from list [1, 3, 2, 3, 1, 2, 4] to [1, 2, 3, 4]
+pub fn array_distinct(args: &[ArrayRef]) -> Result<ArrayRef> {
+ assert_eq!(args.len(), 1);
+
+ // handle null
+ if args[0].data_type() == &DataType::Null {
+ return Ok(args[0].clone());
+ }
+
+ // handle for list & largelist
+ match args[0].data_type() {
+ DataType::List(field) => {
+ let array = as_list_array(&args[0])?;
+ general_array_distinct(array, field)
+ }
+ DataType::LargeList(field) => {
+ let array = as_large_list_array(&args[0])?;
Review Comment:
nit: put `let array = as_large_list_array(&args[0])?;` into
`general_array_distinct `
--
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]
