Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: support LargeList in cardinality #8726

Merged
merged 5 commits into from
Jan 5, 2024
Merged

feat: support LargeList in cardinality #8726

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6a77ef8
support LargeList in cardinality
Weijun-H Jan 3, 2024
a0ec42d
fix fmt
Weijun-H Jan 3, 2024
32c3d9b
reduce code duplication
Weijun-H Jan 4, 2024
3444f89
fix clippy
Weijun-H Jan 4, 2024
068218d
improve error report
Weijun-H Jan 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 18 additions & 3 deletions datafusion/physical-expr/src/array_expressions.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2110,16 +2110,31 @@ pub fn cardinality(args: &[ArrayRef]) -> Result<ArrayRef> {
return exec_err!("cardinality expects one argument");
}

let list_array = as_list_array(&args[0])?.clone();
match &args[0].data_type() {
DataType::List(_) => {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Although this implementation is small, I think having a closure for generic array is still a good practice.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I agree it would be better to avoid the duplication if possible

let list_array = as_list_array(&args[0])?;
generic_list_cardinality::<i32>(list_array)
}
DataType::LargeList(_) => {
let list_array = as_large_list_array(&args[0])?;
generic_list_cardinality::<i64>(list_array)
}
other => {
exec_err!("cardinality does not support type '{:?}'", other)
}
}
}

let result = list_array
fn generic_list_cardinality<O: OffsetSizeTrait>(
array: &GenericListArray<O>,
) -> Result<ArrayRef> {
let result = array
.iter()
.map(|arr| match compute_array_dims(arr)? {
Some(vector) => Ok(Some(vector.iter().map(|x| x.unwrap()).product::<u64>())),
None => Ok(None),
})
.collect::<Result<UInt64Array>>()?;

Ok(Arc::new(result) as ArrayRef)
}

Expand Down
26 changes: 26 additions & 0 deletions datafusion/sqllogictest/test_files/array.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3283,18 +3283,33 @@ select cardinality(make_array(1, 2, 3, 4, 5)), cardinality([1, 3, 5]), cardinali
----
5 3 5

query III
select cardinality(arrow_cast(make_array(1, 2, 3, 4, 5), 'LargeList(Int64)')), cardinality(arrow_cast([1, 3, 5], 'LargeList(Int64)')), cardinality(arrow_cast(make_array('h', 'e', 'l', 'l', 'o'), 'LargeList(Utf8)'));
----
5 3 5

# cardinality scalar function #2
query II
select cardinality(make_array([1, 2], [3, 4], [5, 6])), cardinality(array_repeat(array_repeat(array_repeat(3, 3), 2), 3));
----
6 18

query I
select cardinality(arrow_cast(make_array([1, 2], [3, 4], [5, 6]), 'LargeList(List(Int64))'));
----
6

# cardinality scalar function #3
query II
select cardinality(make_array()), cardinality(make_array(make_array()))
----
NULL 0

query II
select cardinality(arrow_cast(make_array(), 'LargeList(Null)')), cardinality(arrow_cast(make_array(make_array()), 'LargeList(List(Null))'))
----
NULL 0

# cardinality with columns
query III
select cardinality(column1), cardinality(column2), cardinality(column3) from arrays;
Expand All @@ -3307,6 +3322,17 @@ NULL 3 4
4 NULL 1
4 3 NULL

query III
select cardinality(column1), cardinality(column2), cardinality(column3) from large_arrays;
----
4 3 5
4 3 5
4 3 5
4 3 3
NULL 3 4
4 NULL 1
4 3 NULL

## array_remove (aliases: `list_remove`)

# array_remove scalar function #1
Expand Down