comphead commented on code in PR #307:
URL: https://github.com/apache/datafusion-comet/pull/307#discussion_r1576796459
##########
core/src/execution/datafusion/expressions/cast.rs:
##########
@@ -103,10 +126,78 @@ impl Cast {
(DataType::LargeUtf8, DataType::Boolean) => {
Self::spark_cast_utf8_to_boolean::<i64>(&array,
self.eval_mode)?
}
- _ => cast_with_options(&array, to_type, &CAST_OPTIONS)?,
+ (
+ DataType::Utf8,
+ DataType::Int8 | DataType::Int16 | DataType::Int32 |
DataType::Int64,
+ ) => Self::spark_cast_string_to_integral(to_type, &array,
self.eval_mode)?,
+ (
+ DataType::Dictionary(key_type, value_type),
+ DataType::Int8 | DataType::Int16 | DataType::Int32 |
DataType::Int64,
+ ) if key_type.as_ref() == &DataType::Int32
+ && value_type.as_ref() == &DataType::Utf8 =>
+ {
+ // Note that 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 unpacked_array =
Self::unpack_dict_string_array::<Int32Type>(&array)?;
+ Self::spark_cast_string_to_integral(to_type, &unpacked_array,
self.eval_mode)?
+ }
+ _ => {
+ // when we have no Spark-specific casting we delegate to
DataFusion
+ cast_with_options(&array, to_type, &CAST_OPTIONS)?
+ }
+ };
+ Ok(spark_cast(cast_result, from_type, to_type))
+ }
+
+ fn spark_cast_string_to_integral(
Review Comment:
`string_to_int`?
--
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
