From e894a03bea638e35677eaf27876966013dd64bf4 Mon Sep 17 00:00:00 2001
From: Neil Conway <neil.conway@gmail.com>
Date: Wed, 25 Feb 2026 13:12:42 -0500
Subject: [PATCH] perf: Use Hashbrown for array_distinct (#20538)

## Which issue does this PR close?

N/A

## Rationale for this change

#20364 recently optimized `array_distinct` to use batched row
conversion. As part of that PR, `std::HashSet` was used. This PR just
replaces `std::HashSet` with `hashbrown::HashSet`, which measurably
improves performance.

## What changes are included in this PR?

## Are these changes tested?

Yes.

## Are there any user-facing changes?

No.
---
 datafusion/functions-nested/src/set_ops.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datafusion/functions-nested/src/set_ops.rs b/datafusion/functions-nested/src/set_ops.rs
index 2348b3c53..150559111 100644
--- a/datafusion/functions-nested/src/set_ops.rs
+++ b/datafusion/functions-nested/src/set_ops.rs
@@ -34,8 +34,8 @@ use datafusion_expr::{
     ColumnarValue, Documentation, ScalarUDFImpl, Signature, Volatility,
 };
 use datafusion_macros::user_doc;
+use hashbrown::HashSet;
 use std::any::Any;
-use std::collections::HashSet;
 use std::fmt::{Display, Formatter};
 use std::sync::Arc;