andygrove commented on code in PR #23589:
URL: https://github.com/apache/datafusion/pull/23589#discussion_r3598455626
##########
datafusion/functions/src/string/replace.rs:
##########
@@ -330,4 +440,89 @@ mod tests {
Ok(())
}
+
+ /// The scalar-argument fast path must produce output that is bit-identical
+ /// to the general (array-argument) path for every kind of pattern.
+ #[test]
+ fn scalar_fast_path_matches_general() {
+ use arrow::array::{ArrayRef, StringViewArray};
+ use arrow::datatypes::Field;
+ use datafusion_common::config::ConfigOptions;
+ use std::sync::Arc;
+
+ let rows = vec![
+ Some("hello world"),
+ None,
+ Some("aaaa"),
+ Some(""),
+ Some("a.b.c.d"),
+ Some("úñîçödé abcúñ"),
+ Some("mississippi"),
+ Some(" double spaces "),
+ ];
+ // Covers byte-map (single ASCII → single ASCII), deletion (empty
`to`),
+ // empty `from`, multi-byte `to`, and multi-byte non-ASCII `from`.
+ let cases = [
+ (" ", "_"),
+ ("a", "X"),
+ ("ss", "Z"),
+ ("", "Q"),
+ ("a", "yy"),
+ ("úñ", "A"),
+ (".", ""),
+ ("i", "II"),
+ ];
+
+ let invoke = |haystack: &ArrayRef,
+ from: ColumnarValue,
+ to: ColumnarValue|
+ -> ArrayRef {
+ let args = vec![ColumnarValue::Array(Arc::clone(haystack)), from,
to];
+ let arg_fields = args
+ .iter()
+ .enumerate()
+ .map(|(i, a)| Field::new(format!("a{i}"), a.data_type(),
true).into())
+ .collect();
+ match ReplaceFunc::new()
+ .invoke_with_args(ScalarFunctionArgs {
+ args,
+ arg_fields,
+ number_rows: haystack.len(),
+ return_field: Field::new("f", Utf8, true).into(),
+ config_options: Arc::new(ConfigOptions::default()),
+ })
+ .unwrap()
+ {
+ ColumnarValue::Array(a) => a,
+ ColumnarValue::Scalar(s) =>
s.to_array_of_size(haystack.len()).unwrap(),
+ }
+ };
+
+ for (from, to) in cases {
+ let n = rows.len();
+ for haystack in [
+ Arc::new(StringArray::from(rows.clone())) as ArrayRef,
Review Comment:
Added. Thanks for catching the gap.
--
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]
