andygrove commented on code in PR #627:
URL: https://github.com/apache/datafusion-comet/pull/627#discussion_r1670551445
##########
native/core/src/execution/datafusion/expressions/cast.rs:
##########
@@ -501,18 +504,24 @@ impl Cast {
let array = array_with_timezone(array, self.timezone.clone(),
Some(to_type))?;
let from_type = array.data_type().clone();
- // unpack dictionary string arrays first
- // TODO: we are unpacking a dictionary-encoded array and then
performing
- // the cast. We could potentially improve performance here by casting
the
- // dictionary values directly without unpacking the array first,
although this
- // would add more complexity to the code
let array = match &from_type {
DataType::Dictionary(key_type, value_type)
if key_type.as_ref() == &DataType::Int32
&& (value_type.as_ref() == &DataType::Utf8
|| value_type.as_ref() == &DataType::LargeUtf8) =>
{
- cast_with_options(&array, value_type.as_ref(), &CAST_OPTIONS)?
+ let dict_array = array
+ .as_any()
+ .downcast_ref::<DictionaryArray<Int32Type>>()
+ .expect("Expected a dictionary array");
+ let values = dict_array.values();
+ let cast_values = self.cast_array(values.clone())?;
+ let cast_array = Arc::new(DictionaryArray::<Int32Type>::new(
+ dict_array.keys().clone(),
+ cast_values,
+ )) as ArrayRef;
Review Comment:
This code looks good and is converting the input dictionary array to the
output dictionary array that we want
--
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
