Blizzara commented on code in PR #716:
URL: https://github.com/apache/datafusion-comet/pull/716#discussion_r1690532403
##########
native/spark-expr/src/cast.rs:
##########
@@ -502,158 +502,163 @@ impl Cast {
eval_mode,
}
}
+}
- fn cast_array(&self, array: ArrayRef) -> DataFusionResult<ArrayRef> {
- let to_type = &self.data_type;
- let array = array_with_timezone(array, self.timezone.clone(),
Some(to_type))?;
- let from_type = array.data_type().clone();
- 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) =>
- {
- let dict_array = array
- .as_any()
- .downcast_ref::<DictionaryArray<Int32Type>>()
- .expect("Expected a dictionary array");
-
- let casted_dictionary = DictionaryArray::<Int32Type>::new(
- dict_array.keys().clone(),
- self.cast_array(dict_array.values().clone())?,
- );
-
- let casted_result = match to_type {
- DataType::Dictionary(_, _) =>
Arc::new(casted_dictionary.clone()),
- _ => take(casted_dictionary.values().as_ref(),
dict_array.keys(), None)?,
- };
- return Ok(spark_cast(casted_result, &from_type, to_type));
- }
- _ => array,
- };
- let from_type = array.data_type();
-
- let cast_result = match (from_type, to_type) {
- (DataType::Utf8, DataType::Boolean) => {
- Self::spark_cast_utf8_to_boolean::<i32>(&array, self.eval_mode)
- }
- (DataType::LargeUtf8, DataType::Boolean) => {
- Self::spark_cast_utf8_to_boolean::<i64>(&array, self.eval_mode)
- }
- (DataType::Utf8, DataType::Timestamp(_, _)) => {
- Self::cast_string_to_timestamp(&array, to_type, self.eval_mode)
- }
- (DataType::Utf8, DataType::Date32) => {
- Self::cast_string_to_date(&array, to_type, self.eval_mode)
- }
- (DataType::Int64, DataType::Int32)
- | (DataType::Int64, DataType::Int16)
- | (DataType::Int64, DataType::Int8)
- | (DataType::Int32, DataType::Int16)
- | (DataType::Int32, DataType::Int8)
- | (DataType::Int16, DataType::Int8)
- if self.eval_mode != EvalMode::Try =>
- {
- Self::spark_cast_int_to_int(&array, self.eval_mode, from_type,
to_type)
- }
- (
- DataType::Utf8,
- DataType::Int8 | DataType::Int16 | DataType::Int32 |
DataType::Int64,
- ) => Self::cast_string_to_int::<i32>(to_type, &array,
self.eval_mode),
- (
- DataType::LargeUtf8,
- DataType::Int8 | DataType::Int16 | DataType::Int32 |
DataType::Int64,
- ) => Self::cast_string_to_int::<i64>(to_type, &array,
self.eval_mode),
- (DataType::Float64, DataType::Utf8) => {
- Self::spark_cast_float64_to_utf8::<i32>(&array, self.eval_mode)
- }
- (DataType::Float64, DataType::LargeUtf8) => {
- Self::spark_cast_float64_to_utf8::<i64>(&array, self.eval_mode)
- }
- (DataType::Float32, DataType::Utf8) => {
- Self::spark_cast_float32_to_utf8::<i32>(&array, self.eval_mode)
- }
- (DataType::Float32, DataType::LargeUtf8) => {
- Self::spark_cast_float32_to_utf8::<i64>(&array, self.eval_mode)
- }
- (DataType::Float32, DataType::Decimal128(precision, scale)) => {
- Self::cast_float32_to_decimal128(&array, *precision, *scale,
self.eval_mode)
- }
- (DataType::Float64, DataType::Decimal128(precision, scale)) => {
- Self::cast_float64_to_decimal128(&array, *precision, *scale,
self.eval_mode)
- }
- (DataType::Float32, DataType::Int8)
- | (DataType::Float32, DataType::Int16)
- | (DataType::Float32, DataType::Int32)
- | (DataType::Float32, DataType::Int64)
- | (DataType::Float64, DataType::Int8)
- | (DataType::Float64, DataType::Int16)
- | (DataType::Float64, DataType::Int32)
- | (DataType::Float64, DataType::Int64)
- | (DataType::Decimal128(_, _), DataType::Int8)
- | (DataType::Decimal128(_, _), DataType::Int16)
- | (DataType::Decimal128(_, _), DataType::Int32)
- | (DataType::Decimal128(_, _), DataType::Int64)
- if self.eval_mode != EvalMode::Try =>
- {
- Self::spark_cast_nonintegral_numeric_to_integral(
- &array,
- 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)?)
- }
- _ => {
- // 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(SparkError::Internal(format!(
- "Native cast invoked for unsupported cast from
{from_type:?} to {to_type:?}"
- )))
- }
- };
- Ok(spark_cast(cast_result?, from_type, to_type))
+pub fn spark_cast_array(
Review Comment:
added some in
https://github.com/apache/datafusion-comet/pull/716/commits/eaf224d2ba621456942a3fd4c62c7acc2ce3b387!
Though not sure what exactly would be useful here, lmk if you had anything
specifc in mind :)
--
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
