parthchandra commented on code in PR #1122:
URL: https://github.com/apache/datafusion-comet/pull/1122#discussion_r1934793909
##########
native/spark-expr/src/list.rs:
##########
@@ -708,6 +708,92 @@ impl PartialEq<dyn Any> for ArrayInsert {
}
}
+#[derive(Debug, Hash)]
+pub struct ArraySize {
+ src_array_expr: Arc<dyn PhysicalExpr>,
+}
+
+impl ArraySize {
+ pub fn new(src_array_expr: Arc<dyn PhysicalExpr>) -> Self {
+ Self { src_array_expr }
+ }
+}
+
+impl Display for ArraySize {
+ fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+ write!(f, "ArraySize [array: {:?}]", self.src_array_expr)
+ }
+}
+
+impl PartialEq<dyn Any> for ArraySize {
+ fn eq(&self, other: &dyn Any) -> bool {
+ down_cast_any_ref(other)
+ .downcast_ref::<Self>()
+ .map(|x| self.src_array_expr.eq(&x.src_array_expr))
+ .unwrap_or(false)
+ }
+}
+
+impl PhysicalExpr for ArraySize {
+ fn as_any(&self) -> &dyn Any {
+ self
+ }
+
+ fn data_type(&self, _input_schema: &Schema) -> DataFusionResult<DataType> {
+ Ok(DataType::Int32)
+ }
+
+ fn nullable(&self, input_schema: &Schema) -> DataFusionResult<bool> {
+ self.src_array_expr.nullable(input_schema)
+ }
+
+ fn evaluate(&self, batch: &RecordBatch) -> DataFusionResult<ColumnarValue>
{
+ let array_value = self
+ .src_array_expr
+ .evaluate(batch)?
+ .into_array(batch.num_rows())?;
+ match array_value.data_type() {
+ DataType::List(_) => {
+ let list_array = as_list_array(&array_value)?;
+ let mut builder = Int32Array::builder(list_array.len());
+ for i in 0..list_array.len() {
+ if list_array.is_null(i) {
+ builder.append_null();
+ } else {
+ builder.append_value(list_array.value_length(i));
Review Comment:
Will `value_length(i)` include nulls in the array at index `i`?
##########
native/spark-expr/src/list.rs:
##########
@@ -708,6 +708,92 @@ impl PartialEq<dyn Any> for ArrayInsert {
}
}
+#[derive(Debug, Hash)]
+pub struct ArraySize {
+ src_array_expr: Arc<dyn PhysicalExpr>,
+}
+
+impl ArraySize {
+ pub fn new(src_array_expr: Arc<dyn PhysicalExpr>) -> Self {
+ Self { src_array_expr }
+ }
+}
+
+impl Display for ArraySize {
+ fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+ write!(f, "ArraySize [array: {:?}]", self.src_array_expr)
+ }
+}
+
+impl PartialEq<dyn Any> for ArraySize {
+ fn eq(&self, other: &dyn Any) -> bool {
+ down_cast_any_ref(other)
+ .downcast_ref::<Self>()
+ .map(|x| self.src_array_expr.eq(&x.src_array_expr))
+ .unwrap_or(false)
+ }
+}
+
+impl PhysicalExpr for ArraySize {
+ fn as_any(&self) -> &dyn Any {
+ self
+ }
+
+ fn data_type(&self, _input_schema: &Schema) -> DataFusionResult<DataType> {
+ Ok(DataType::Int32)
+ }
+
+ fn nullable(&self, input_schema: &Schema) -> DataFusionResult<bool> {
+ self.src_array_expr.nullable(input_schema)
+ }
+
+ fn evaluate(&self, batch: &RecordBatch) -> DataFusionResult<ColumnarValue>
{
+ let array_value = self
+ .src_array_expr
+ .evaluate(batch)?
+ .into_array(batch.num_rows())?;
+ match array_value.data_type() {
+ DataType::List(_) => {
+ let list_array = as_list_array(&array_value)?;
+ let mut builder = Int32Array::builder(list_array.len());
+ for i in 0..list_array.len() {
+ if list_array.is_null(i) {
Review Comment:
You might want to handle `legacySizeOfNull` here
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
