yyy1000 commented on code in PR #9436:
URL: https://github.com/apache/arrow-datafusion/pull/9436#discussion_r1530573336
##########
datafusion/proto/tests/cases/roundtrip_physical_plan.rs:
##########
@@ -665,6 +670,133 @@ fn roundtrip_scalar_udf() -> Result<()> {
roundtrip_test_with_context(Arc::new(project), ctx)
}
+#[test]
+fn roundtrip_scalar_udf_extension_codec() {
+ #[derive(Debug)]
+ struct MyRegexUdf {
+ signature: Signature,
+ // regex as original string
+ pattern: String,
+ }
+
+ impl MyRegexUdf {
+ fn new(pattern: String) -> Self {
+ Self {
+ signature: Signature::uniform(
+ 1,
+ vec![DataType::Int32],
+ Volatility::Immutable,
+ ),
+ pattern,
+ }
+ }
+ }
+
+ /// Implement the ScalarUDFImpl trait for MyRegexUdf
+ impl ScalarUDFImpl for MyRegexUdf {
+ fn as_any(&self) -> &dyn Any {
+ self
+ }
+ fn name(&self) -> &str {
+ "regex_udf"
+ }
+ fn signature(&self) -> &Signature {
+ &self.signature
+ }
+ fn return_type(&self, args: &[DataType]) -> Result<DataType> {
+ if !matches!(args.first(), Some(&DataType::Utf8)) {
+ return plan_err!("regex_udf only accepts Utf8 arguments");
+ }
+ Ok(DataType::Int32)
+ }
+ fn invoke(&self, _args: &[ColumnarValue]) -> Result<ColumnarValue> {
+ unimplemented!()
+ }
+ }
+
+ #[derive(Clone, PartialEq, ::prost::Message)]
+ pub struct MyRegexUdfNode {
+ #[prost(string, tag = "1")]
+ pub pattern: String,
+ }
+
+ #[derive(Debug)]
+ pub struct ScalarUDFExtensionCodec {}
+
+ impl PhysicalExtensionCodec for ScalarUDFExtensionCodec {
+ fn try_decode(
+ &self,
+ _buf: &[u8],
+ _inputs: &[Arc<dyn ExecutionPlan>],
+ _registry: &dyn FunctionRegistry,
+ ) -> Result<Arc<dyn ExecutionPlan>> {
+ not_impl_err!("No extension codec provided")
+ }
+
+ fn try_encode(
+ &self,
+ _node: Arc<dyn ExecutionPlan>,
+ _buf: &mut Vec<u8>,
+ ) -> Result<()> {
+ not_impl_err!("No extension codec provided")
+ }
+
+ fn try_decode_udf(&self, name: &str, buf: &[u8]) ->
Result<Arc<ScalarUDF>> {
+ if name == "regex_udf" {
+ let proto = MyRegexUdfNode::decode(buf).map_err(|err| {
+ DataFusionError::Internal(format!(
+ "failed to decode regex_udf: {}",
+ err
+ ))
+ })?;
+
+ Ok(Arc::new(ScalarUDF::new_from_impl(MyRegexUdf::new(
+ proto.pattern,
+ ))))
+ } else {
+ not_impl_err!("unrecognized scalar UDF implementation, cannot
decode")
+ }
+ }
+
+ fn try_encode_udf(&self, node: &ScalarUDF, buf: &mut Vec<u8>) ->
Result<()> {
+ let binding = node.inner();
+ let udf = binding.as_any().downcast_ref::<MyRegexUdf>().unwrap();
+ let proto = MyRegexUdfNode {
+ pattern: udf.pattern.clone(),
+ };
+ proto.encode(buf).map_err(|e| {
+ DataFusionError::Internal(format!("failed to encode udf:
{e:?}"))
+ })?;
Review Comment:
Great, it's a good improvement!
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
