This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 6ab16cc7fd bug: fix `array_remove_*` with NULLS (#21013)
6ab16cc7fd is described below
commit 6ab16cc7fd974298d357da9c9b9da70e7718b74f
Author: Oleks V <[email protected]>
AuthorDate: Tue Mar 17 14:03:39 2026 -0700
bug: fix `array_remove_*` with NULLS (#21013)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Closes #21011 .
## Rationale for this change
Handle correctly `array_remove_*` functions if NULL is a value to delete
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
## What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
## Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---
datafusion/functions-nested/src/remove.rs | 2 +-
datafusion/sqllogictest/test_files/array.slt | 100 +++++++++++++++++++++++++--
2 files changed, 97 insertions(+), 5 deletions(-)
diff --git a/datafusion/functions-nested/src/remove.rs
b/datafusion/functions-nested/src/remove.rs
index 9e957c93e1..3d4076800e 100644
--- a/datafusion/functions-nested/src/remove.rs
+++ b/datafusion/functions-nested/src/remove.rs
@@ -390,7 +390,7 @@ fn general_remove<OffsetSize: OffsetSizeTrait>(
let mut valid = NullBufferBuilder::new(list_array.len());
for (row_index, offset_window) in
list_array.offsets().windows(2).enumerate() {
- if list_array.is_null(row_index) {
+ if list_array.is_null(row_index) || element_array.is_null(row_index) {
offsets.push(offsets[row_index]);
valid.append_null();
continue;
diff --git a/datafusion/sqllogictest/test_files/array.slt
b/datafusion/sqllogictest/test_files/array.slt
index 83e9c9cc9c..573938af0c 100644
--- a/datafusion/sqllogictest/test_files/array.slt
+++ b/datafusion/sqllogictest/test_files/array.slt
@@ -5528,21 +5528,47 @@ select
array_remove(make_array(1, null, 2), null),
array_remove(make_array(1, null, 2, null), null);
----
-[1, 2] [1, 2, NULL]
+NULL NULL
query ??
select
array_remove(arrow_cast(make_array(1, null, 2), 'LargeList(Int64)'), null),
array_remove(arrow_cast(make_array(1, null, 2, null), 'LargeList(Int64)'),
null);
----
-[1, 2] [1, 2, NULL]
+NULL NULL
query ??
select
array_remove(arrow_cast(make_array(1, null, 2), 'FixedSizeList(3, Int64)'),
null),
array_remove(arrow_cast(make_array(1, null, 2, null), 'FixedSizeList(4,
Int64)'), null);
----
-[1, 2] [1, 2, NULL]
+NULL NULL
+
+# array_remove with null element from column
+query ?
+select array_remove(column1, column2) from (values
+ (make_array(1, 2, 3), 2),
+ (make_array(4, 5, 6), null),
+ (make_array(7, 8, 9), 8),
+ (null, 1)
+) as t(column1, column2);
+----
+[1, 3]
+NULL
+[7, 9]
+NULL
+
+# array_remove with null element from column (LargeList)
+query ?
+select array_remove(column1, column2) from (values
+ (arrow_cast(make_array(1, 2, 3), 'LargeList(Int64)'), 2),
+ (arrow_cast(make_array(4, 5, 6), 'LargeList(Int64)'), null),
+ (arrow_cast(make_array(7, 8, 9), 'LargeList(Int64)'), 8)
+) as t(column1, column2);
+----
+[1, 3]
+NULL
+[7, 9]
# array_remove scalar function #2 (element is list)
query ??
@@ -5685,6 +5711,46 @@ select array_remove(make_array([1, 2, 3], [4, 5, 6], [4,
5, 6], [10, 11, 12], [1
## array_remove_n (aliases: `list_remove_n`)
+# array_remove_n with null element scalar
+query ??
+select array_remove_n(make_array(1, 2, 2, 1, 1), NULL, 2),
+ array_remove_n(make_array(1, 2, 2, 1, 1), 2, 2);
+----
+NULL [1, 1, 1]
+
+# array_remove_n with null element scalar (LargeList)
+query ??
+select array_remove_n(arrow_cast(make_array(1, 2, 2, 1, 1),
'LargeList(Int64)'), NULL, 2),
+ array_remove_n(arrow_cast(make_array(1, 2, 2, 1, 1),
'LargeList(Int64)'), 2, 2);
+----
+NULL [1, 1, 1]
+
+# array_remove_n with null element from column
+query ?
+select array_remove_n(column1, column2, column3) from (values
+ (make_array(1, 2, 2, 1, 1), 2, 2),
+ (make_array(3, 4, 4, 3, 3), null, 2),
+ (make_array(5, 6, 6, 5, 5), 6, 1),
+ (null, 1, 1)
+) as t(column1, column2, column3);
+----
+[1, 1, 1]
+NULL
+[5, 6, 5, 5]
+NULL
+
+# array_remove_n with null element from column (LargeList)
+query ?
+select array_remove_n(column1, column2, column3) from (values
+ (arrow_cast(make_array(1, 2, 2, 1, 1), 'LargeList(Int64)'), 2, 2),
+ (arrow_cast(make_array(3, 4, 4, 3, 3), 'LargeList(Int64)'), null, 2),
+ (arrow_cast(make_array(5, 6, 6, 5, 5), 'LargeList(Int64)'), 6, 1)
+) as t(column1, column2, column3);
+----
+[1, 1, 1]
+NULL
+[5, 6, 5, 5]
+
# array_remove_n scalar function #1
query ???
select array_remove_n(make_array(1, 2, 2, 1, 1), 2, 2),
array_remove_n(make_array(1.0, 2.0, 2.0, 1.0, 1.0), 1.0, 2),
array_remove_n(make_array('h', 'e', 'l', 'l', 'o'), 'l', 3);
@@ -5777,7 +5843,33 @@ select array_remove_n(make_array([1, 2, 3], [4, 5, 6],
[4, 5, 6], [10, 11, 12],
query ?
select array_remove_all(make_array(1, 2, 2, 1, 1), NULL);
----
-[1, 2, 2, 1, 1]
+NULL
+
+# array_remove_all with null element from column
+query ?
+select array_remove_all(column1, column2) from (values
+ (make_array(1, 2, 2, 1, 1), 2),
+ (make_array(3, 4, 4, 3, 3), null),
+ (make_array(5, 6, 6, 5, 5), 6),
+ (null, 1)
+) as t(column1, column2);
+----
+[1, 1, 1]
+NULL
+[5, 5, 5]
+NULL
+
+# array_remove_all with null element from column (LargeList)
+query ?
+select array_remove_all(column1, column2) from (values
+ (arrow_cast(make_array(1, 2, 2, 1, 1), 'LargeList(Int64)'), 2),
+ (arrow_cast(make_array(3, 4, 4, 3, 3), 'LargeList(Int64)'), null),
+ (arrow_cast(make_array(5, 6, 6, 5, 5), 'LargeList(Int64)'), 6)
+) as t(column1, column2);
+----
+[1, 1, 1]
+NULL
+[5, 5, 5]
# array_remove_all scalar function #1
query ???
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
