Feat: Support array flatten() on List(LargeList(_)) types (#18363)

## 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 #17670 
- Closes #18419

## Rationale for this change

<!--
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?

Added a `flatten()` `List(LargeList)` test to the `sqllogictest`

Added support for array `flatten()` on `List(LargeList(_))` types
<!--
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?

`sqllogictest` passes, but I still need to implement a test where
offsets could not be downcasted from i64 to i32
<!--
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?

Users will be able to use `flatten` on `List(LargeList)` types
<!--
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: sdf-jkl

datafusion/functions-nested/src/flatten.rs

@@ -96,6 +96,7 @@ impl ScalarUDFImpl for Flatten {
         let data_type = match &arg_types[0] {
             List(field) => match field.data_type() {
                 List(field) | FixedSizeList(field, _) => List(Arc::clone(field)),
+                LargeList(field) => LargeList(Arc::clone(field)),
                 _ => arg_types[0].clone(),
             },
             LargeList(field) => match field.data_type() {
@@ -143,7 +144,8 @@ pub fn flatten_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
                 List(_) => {
                     let (inner_field, inner_offsets, inner_values, _) =
                         as_list_array(&values)?.clone().into_parts();
-                    let offsets = get_offsets_for_flatten::<i32>(inner_offsets, offsets);
+                    let offsets =
+                        get_offsets_for_flatten::<i32, i32>(inner_offsets, offsets);
                     let flattened_array = GenericListArray::<i32>::new(
                         inner_field,
                         offsets,
@@ -154,7 +156,17 @@ pub fn flatten_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
                     Ok(Arc::new(flattened_array) as ArrayRef)
                 }
                 LargeList(_) => {
-                    exec_err!("flatten does not support type '{:?}'", array.data_type())?
+                    let (inner_field, inner_offsets, inner_values, _) =
+                        as_large_list_array(&values)?.clone().into_parts();
+                    let offsets =
+                        get_offsets_for_flatten::<i64, i32>(inner_offsets, offsets);
+                    let flattened_array = GenericListArray::<i64>::new(
+                        inner_field,
+                        offsets,
+                        inner_values,
+                        nulls,
+                    );
+                    Ok(Arc::new(flattened_array) as ArrayRef)
                 }
                 _ => Ok(Arc::clone(array) as ArrayRef),
             }
@@ -179,9 +191,10 @@ pub fn flatten_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
                     Ok(Arc::new(flattened_array) as ArrayRef)
                 }
                 LargeList(_) => {
-                    let (inner_field, inner_offsets, inner_values, nulls) =
+                    let (inner_field, inner_offsets, inner_values, _) =
                         as_large_list_array(&values)?.clone().into_parts();
-                    let offsets = get_offsets_for_flatten::<i64>(inner_offsets, offsets);
+                    let offsets =
+                        get_offsets_for_flatten::<i64, i64>(inner_offsets, offsets);
                     let flattened_array = GenericListArray::<i64>::new(
                         inner_field,
                         offsets,
@@ -202,12 +215,12 @@ pub fn flatten_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
 }
 
 // Create new offsets that are equivalent to `flatten` the array.
-fn get_offsets_for_flatten<O: OffsetSizeTrait>(
-    offsets: OffsetBuffer<O>,
-    indexes: OffsetBuffer<O>,
+fn get_offsets_for_flatten<O: OffsetSizeTrait, P: OffsetSizeTrait>(
+    inner_offsets: OffsetBuffer<O>,
+    outer_offsets: OffsetBuffer<P>,
 ) -> OffsetBuffer<O> {
-    let buffer = offsets.into_inner();
-    let offsets: Vec<O> = indexes
+    let buffer = inner_offsets.into_inner();
+    let offsets: Vec<O> = outer_offsets
         .iter()
         .map(|i| buffer[i.to_usize().unwrap()])
         .collect();
@@ -216,11 +229,11 @@ fn get_offsets_for_flatten<O: OffsetSizeTrait>(
 
 // Create new large offsets that are equivalent to `flatten` the array.
 fn get_large_offsets_for_flatten<O: OffsetSizeTrait, P: OffsetSizeTrait>(
-    offsets: OffsetBuffer<O>,
-    indexes: OffsetBuffer<P>,
+    inner_offsets: OffsetBuffer<O>,
+    outer_offsets: OffsetBuffer<P>,
 ) -> OffsetBuffer<i64> {
-    let buffer = offsets.into_inner();
-    let offsets: Vec<i64> = indexes
+    let buffer = inner_offsets.into_inner();
+    let offsets: Vec<i64> = outer_offsets
         .iter()
         .map(|i| buffer[i.to_usize().unwrap()].to_i64().unwrap())
         .collect();

datafusion/sqllogictest/test_files/array.slt

@@ -7757,7 +7757,7 @@ select flatten(make_array(1, 2, 1, 3, 2)),
 
 query ???
 select flatten(arrow_cast(make_array(1, 2, 1, 3, 2), 'LargeList(Int64)')),
-       flatten(arrow_cast(make_array([1], [2, 3], [null], make_array(4, null, 5)), 'LargeList(LargeList(Int64))')),
+       flatten(arrow_cast(make_array([1], null, [2, 3], [null], make_array(4, null, 5)), 'LargeList(LargeList(Int64))')),
        flatten(arrow_cast(make_array([[1.1]], [[2.2]], [[3.3], [4.4]]), 'LargeList(LargeList(LargeList(Float64)))'));
 ----
 [1, 2, 1, 3, 2] [1, 2, 3, NULL, 4, NULL, 5] [[1.1], [2.2], [3.3], [4.4]]
@@ -7769,6 +7769,14 @@ select flatten(arrow_cast(make_array(1, 2, 1, 3, 2), 'FixedSizeList(5, Int64)'))
 ----
 [1, 2, 1, 3, 2] [1, 2, 3, NULL, 4, NULL, 5] [[1.1], [2.2], [3.3], [4.4]]
 
+query ??TT
+select flatten(arrow_cast(make_array([1], [2, 3], [null], make_array(4, null, 5)), 'FixedSizeList(4, LargeList(Int64))')),
+       flatten(arrow_cast(make_array([[1.1], [2.2]], [[3.3], [4.4]]), 'List(LargeList(FixedSizeList(1, Float64)))')),
+       arrow_typeof(flatten(arrow_cast(make_array([1], [2, 3], [null], make_array(4, null, 5)), 'FixedSizeList(4, LargeList(Int64))'))),
+       arrow_typeof(flatten(arrow_cast(make_array([[1.1], [2.2]], [[3.3], [4.4]]), 'List(LargeList(FixedSizeList(1, Float64)))')));
+----
+[1, 2, 3, NULL, 4, NULL, 5] [[1.1], [2.2], [3.3], [4.4]] LargeList(nullable Int64) LargeList(nullable FixedSizeList(1 x nullable Float64))
+
 # flatten with column values
 query ????
 select flatten(column1),