andygrove commented on code in PR #461:
URL: https://github.com/apache/datafusion-comet/pull/461#discussion_r1614788921
##########
core/src/execution/datafusion/expressions/cast.rs:
##########
@@ -622,14 +590,89 @@ impl Cast {
self.eval_mode,
from_type,
to_type,
- )?
+ )
+ }
+ _ if Self::is_datafusion_spark_compatible(from_type, to_type) => {
+ // use DataFusion cast only when we know that it is compatible
with Spark
+ Ok(cast_with_options(&array, to_type, &CAST_OPTIONS)?)
}
_ => {
- // when we have no Spark-specific casting we delegate to
DataFusion
- cast_with_options(&array, to_type, &CAST_OPTIONS)?
+ // we should never reach this code because the Scala code
should be checking
+ // for supported cast operations and falling back to Spark for
anything that
+ // is not yet supported
+ Err(CometError::Internal(format!(
+ "Native cast invoked for unsupported cast from
{from_type:?} to {to_type:?}"
+ )))
}
};
- Ok(spark_cast(cast_result, from_type, to_type))
+ Ok(spark_cast(cast_result?, from_type, to_type))
+ }
+
+ /// Determines if DataFusion supports the given cast in a way that is
+ /// compatible with Spark
+ fn is_datafusion_spark_compatible(from_type: &DataType, to_type:
&DataType) -> bool {
+ if from_type == to_type {
+ return true;
+ }
+ match from_type {
+ DataType::Boolean => matches!(
+ to_type,
+ DataType::Int8
+ | DataType::Int16
+ | DataType::Int32
+ | DataType::Int64
+ | DataType::Float32
+ | DataType::Float64
+ | DataType::Utf8
Review Comment:
Removing that case causes a test failure:
```
- scalar subquery *** FAILED *** (8 seconds, 253 milliseconds)
Cause: java.util.concurrent.ExecutionException:
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in
stage 410.0 failed 1 times, most recent failure: Lost task 0.0 in stage 410.0
(TID 1286) (192.168.64.23 executor driver):
org.apache.comet.CometNativeException: Execution error: Comet Internal Error:
Native cast invoked for unsupported cast from Int32 to Decimal128(38, 10)
```
--
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
