[branch-54] backport #23192 array_compact handle edge case with NULLs (#23196)

## 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 #.

## Rationale for this change

Backport `array_compact` handle edge case with NULLs. The issue causing
correctness issues and has no breaking API, therefore should fall into
backport criteria

<!--
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.
-->

Author: comphead

datafusion/functions-nested/src/array_compact.rs

@@ -130,14 +130,22 @@ fn compact_list<O: OffsetSizeTrait>(
     field: &Arc<arrow::datatypes::Field>,
 ) -> Result<ArrayRef> {
     let values = list_array.values();
-
-    // Fast path: no nulls in values, return input unchanged
-    if values.null_count() == 0 {
+    // Use logical nulls so element types without a validity buffer
+    // (e.g. NullArray) are still treated as null.
+    let Some(values_nulls) = values.logical_nulls() else {
+        // Fast path: no validity buffer, no nulls to remove
+        return Ok(Arc::new(list_array.clone()));
+    };
+    let values_null_count = values_nulls.null_count();
+    if values_null_count == 0 {
+        // Fast path: validity buffer present but no nulls set
         return Ok(Arc::new(list_array.clone()));
     }
 
+    let list_nulls = list_array.nulls();
+    let list_offsets = list_array.offsets();
     let original_data = values.to_data();
-    let capacity = original_data.len() - values.null_count();
+    let capacity = original_data.len() - values_null_count;
     let mut offsets = Vec::<O>::with_capacity(list_array.len() + 1);
     offsets.push(O::zero());
     let mut mutable = MutableArrayData::with_capacities(
@@ -147,25 +155,25 @@ fn compact_list<O: OffsetSizeTrait>(
     );
 
     for row_index in 0..list_array.len() {
-        if list_array.nulls().is_some_and(|n| n.is_null(row_index)) {
+        if list_nulls.is_some_and(|n| n.is_null(row_index)) {
             offsets.push(offsets[row_index]);
             continue;
         }
 
-        let start = list_array.offsets()[row_index].as_usize();
-        let end = list_array.offsets()[row_index + 1].as_usize();
-        let mut copied = 0usize;
+        let start = list_offsets[row_index].as_usize();
+        let end = list_offsets[row_index + 1].as_usize();
+        let row_null_count = values_nulls.slice(start, end - start).null_count();
+        let kept = (end - start) - row_null_count;
 
         // Batch consecutive non-null elements into single extend() calls
         // to reduce per-element overhead. For [1, 2, NULL, 3, 4] this
         // produces 2 extend calls (0..2, 3..5) instead of 4 individual ones.
         let mut batch_start: Option<usize> = None;
         for i in start..end {
-            if values.is_null(i) {
+            if values_nulls.is_null(i) {
                 // Null breaks the current batch — flush it
                 if let Some(bs) = batch_start {
                     mutable.extend(0, bs, i);
-                    copied += i - bs;
                     batch_start = None;
                 }
             } else if batch_start.is_none() {
@@ -175,17 +183,16 @@ fn compact_list<O: OffsetSizeTrait>(
         // Flush any remaining batch after the loop
         if let Some(bs) = batch_start {
             mutable.extend(0, bs, end);
-            copied += end - bs;
         }
 
-        offsets.push(offsets[row_index] + O::usize_as(copied));
+        offsets.push(offsets[row_index] + O::usize_as(kept));
     }
 
     let new_values = make_array(mutable.freeze());
     Ok(Arc::new(GenericListArray::<O>::try_new(
         Arc::clone(field),
         OffsetBuffer::new(offsets.into()),
         new_values,
-        list_array.nulls().cloned(),
+        list_nulls.cloned(),
     )?))
 }

datafusion/sqllogictest/test_files/array/array_distinct.slt

@@ -137,6 +137,12 @@ select array_compact(arrow_cast([NULL, NULL, NULL], 'List(Int64)'));
 ----
 []
 
+# all nulls with untyped NULLs (List(Null) inner values are a NullArray)
+query ?
+select array_compact(make_array(NULL, NULL, NULL));
+----
+[]
+
 # empty array
 query ?
 select array_compact([]);
@@ -167,6 +173,17 @@ select array_compact([make_array(1, 2), NULL, make_array(3, 4)]);
 ----
 [[1, 2], [3, 4]]
 
+# nested array of all-null inner lists: outer elements are non-null, kept as-is
+query ?
+select array_compact(make_array(make_array(NULL, NULL, NULL), make_array(NULL, NULL)));
+----
+[[NULL, NULL, NULL], [NULL, NULL]]
+
+query ?
+select array_compact(make_array(make_array(NULL, NULL, NULL), make_array(NULL, NULL, NULL)));
+----
+[[NULL, NULL, NULL], [NULL, NULL, NULL]]
+
 # LargeList
 query ?
 select array_compact(arrow_cast([1, NULL, 2, NULL, 3], 'LargeList(Int64)'));