Add ScalarValue::RunEndEncoded variant (#19895)

## 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 #18563

## 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.
-->

Support RunEndEncoded scalar values, similar to how we support for
Dictionary.

## 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.
-->

- Add new `ScalarValue::RunEndEncoded` enum variant
- Fix `ScalarValue::new_default` to support `Decimal32` and `Decimal64`
- Support RunEndEncoded type in proto for both `ScalarValue` message and
`ArrowType` message

## 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)?
-->

Added 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.
-->

New variant for `ScalarValue`

Protobuf changes to support RunEndEncoded type

<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->

---------

Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>

Author: Jefffrey

datafusion/common/src/cast.rs

@@ -25,8 +25,9 @@ use arrow::array::{
     BinaryViewArray, Decimal32Array, Decimal64Array, DurationMicrosecondArray,
     DurationMillisecondArray, DurationNanosecondArray, DurationSecondArray, Float16Array,
     Int8Array, Int16Array, LargeBinaryArray, LargeListViewArray, LargeStringArray,
-    ListViewArray, StringViewArray, UInt16Array,
+    ListViewArray, RunArray, StringViewArray, UInt16Array,
 };
+use arrow::datatypes::RunEndIndexType;
 use arrow::{
     array::{
         Array, BinaryArray, BooleanArray, Date32Array, Date64Array, Decimal128Array,
@@ -334,3 +335,8 @@ pub fn as_list_view_array(array: &dyn Array) -> Result<&ListViewArray> {
 pub fn as_large_list_view_array(array: &dyn Array) -> Result<&LargeListViewArray> {
     Ok(downcast_value!(array, LargeListViewArray))
 }
+
+// Downcast Array to RunArray
+pub fn as_run_array<T: RunEndIndexType>(array: &dyn Array) -> Result<&RunArray<T>> {
+    Ok(downcast_value!(array, RunArray, T))
+}

datafusion/common/src/scalar/mod.rs

@@ -183,6 +183,11 @@ message Map {
   bool keys_sorted = 2;
 }
 
+message RunEndEncoded {
+  Field run_ends_field = 1;
+  Field values_field = 2;
+}
+
 enum UnionMode{
   sparse = 0;
   dense = 1;
@@ -236,6 +241,12 @@ message ScalarDictionaryValue {
   ScalarValue value = 2;
 }
 
+message ScalarRunEndEncodedValue {
+  Field run_ends_field = 1;
+  Field values_field = 2;
+  ScalarValue value = 3;
+}
+
 message IntervalDayTimeValue {
   int32 days = 1;
   int32 milliseconds = 2;
@@ -321,6 +332,8 @@ message ScalarValue{
     IntervalMonthDayNanoValue interval_month_day_nano = 31;
     ScalarFixedSizeBinary fixed_size_binary_value = 34;
     UnionValue union_value = 42;
+
+    ScalarRunEndEncodedValue run_end_encoded_value = 45;
   }
 }
 
@@ -389,6 +402,7 @@ message ArrowType{
     Union UNION = 29;
     Dictionary DICTIONARY = 30;
     Map MAP = 33;
+    RunEndEncoded RUN_END_ENCODED = 42;
   }
 }
 

datafusion/proto-common/proto/datafusion_common.proto

@@ -326,6 +326,19 @@ impl TryFrom<&protobuf::arrow_type::ArrowTypeEnum> for DataType {
                 let keys_sorted = map.keys_sorted;
                 DataType::Map(Arc::new(field), keys_sorted)
             }
+            arrow_type::ArrowTypeEnum::RunEndEncoded(run_end_encoded) => {
+                let run_ends_field: Field = run_end_encoded
+                    .as_ref()
+                    .run_ends_field
+                    .as_deref()
+                    .required("run_ends_field")?;
+                let value_field: Field = run_end_encoded
+                    .as_ref()
+                    .values_field
+                    .as_deref()
+                    .required("values_field")?;
+                DataType::RunEndEncoded(run_ends_field.into(), value_field.into())
+            }
         })
     }
 }
@@ -578,6 +591,32 @@ impl TryFrom<&protobuf::ScalarValue> for ScalarValue {
 
                 Self::Dictionary(Box::new(index_type), Box::new(value))
             }
+            Value::RunEndEncodedValue(v) => {
+                let run_ends_field: Field = v
+                    .run_ends_field
+                    .as_ref()
+                    .ok_or_else(|| Error::required("run_ends_field"))?
+                    .try_into()?;
+
+                let values_field: Field = v
+                    .values_field
+                    .as_ref()
+                    .ok_or_else(|| Error::required("values_field"))?
+                    .try_into()?;
+
+                let value: Self = v
+                    .value
+                    .as_ref()
+                    .ok_or_else(|| Error::required("value"))?
+                    .as_ref()
+                    .try_into()?;
+
+                Self::RunEndEncoded(
+                    run_ends_field.into(),
+                    values_field.into(),
+                    Box::new(value),
+                )
+            }
             Value::BinaryValue(v) => Self::Binary(Some(v.clone())),
             Value::BinaryViewValue(v) => Self::BinaryView(Some(v.clone())),
             Value::LargeBinaryValue(v) => Self::LargeBinary(Some(v.clone())),