jayzhan211 commented on code in PR #25874:
URL: https://github.com/apache/datafusion/pull/25874#discussion_r4370364083
##########
datafusion/functions/src/unicode/substr.rs:
##########
@@ -112,10 +123,43 @@ impl ScalarUDFImpl for SubstrFunc {
}
fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
- Ok(arg_types[0].clone())
+ Ok(match &arg_types[0] {
+ DataType::Dictionary(key_type, value_type) if
!is_wide_key(key_type) => {
+ value_type.as_ref().clone()
+ }
+ other => other.clone(),
+ })
}
fn invoke_with_args(&self, args: ScalarFunctionArgs) ->
Result<ColumnarValue> {
+ if let DataType::Dictionary(key_type, value_type) =
args.args[0].data_type()
+ && !is_wide_key(&key_type)
+ {
+ // Per-row start/length can produce more distinct values than a
+ // narrow key type can index, so decode instead.
+ let mut args = args.args;
+ args[0] = args[0].cast_to(&value_type, None)?;
+ return make_scalar_function(substr, vec![])(&args);
+ }
+
+ if let ColumnarValue::Array(array) = &args.args[0]
+ && matches!(array.data_type(), DataType::Dictionary(_, _))
+ && array.as_any_dictionary().values().len() <= array.len()
+ && args.args[1..]
+ .iter()
+ .all(|v| matches!(v, ColumnarValue::Scalar(_)))
+ {
+ // Fast path: substr the N_distinct values, reuse the keys.
+ let dict = array.as_any_dictionary();
+ let values = Arc::clone(dict.values());
+ let mut inner = Vec::with_capacity(args.args.len());
+ inner.push(ColumnarValue::Array(values));
+ inner.extend_from_slice(&args.args[1..]);
+ let new_values = make_scalar_function(substr, vec![])(&inner)?
Review Comment:
Let me address this one and merge this PR
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
