From a677c967564e6864c6ef119482c354e1a9eeeab0 Mon Sep 17 00:00:00 2001
From: Michael Kleen <mkleen@gmail.com>
Date: Tue, 18 Aug 2026 09:44:57 +0200
Subject: [PATCH] Add support for dictionary for approx_distinct

---
 .../src/approx_distinct.rs                    |  2 ++
 .../sqllogictest/test_files/aggregate.slt     | 34 +++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/datafusion/functions-aggregate/src/approx_distinct.rs b/datafusion/functions-aggregate/src/approx_distinct.rs
index 1746edd8239f2..00a69713b79db 100644
--- a/datafusion/functions-aggregate/src/approx_distinct.rs
+++ b/datafusion/functions-aggregate/src/approx_distinct.rs
@@ -840,6 +840,7 @@ impl AggregateUDFImpl for ApproxDistinct {
             | DataType::Map(_, _)
             | DataType::Struct(_)
             | DataType::Union(_, _)
+            | DataType::Dictionary(_, _)
             | DataType::LargeBinary => Box::new(HLLAccumulator::new()),
             DataType::Null => {
                 Box::new(NoopAccumulator::new(ScalarValue::UInt64(Some(0))))
@@ -919,6 +920,7 @@ fn is_hll_groups_type(data_type: &DataType) -> bool {
             | DataType::Map(_, _)
             | DataType::Struct(_)
             | DataType::Union(_, _)
+            | DataType::Dictionary(_, _)
     )
 }
 
diff --git a/datafusion/sqllogictest/test_files/aggregate.slt b/datafusion/sqllogictest/test_files/aggregate.slt
index 11651ef64ce1a..592efc50458e3 100644
--- a/datafusion/sqllogictest/test_files/aggregate.slt
+++ b/datafusion/sqllogictest/test_files/aggregate.slt
@@ -1793,6 +1793,40 @@ SELECT g, approx_distinct(arrow_cast(arrow_cast(s, 'Binary'), 'FixedSizeBinary(1
 4 1
 
 
+# Dictionary: dictionary-encoded values must hash identically to the plain
+# (non-dictionary) values, so the counts below match the Utf8 case above.
+
+# Dictionary non-grouped
+query I
+SELECT approx_distinct(arrow_cast(s, 'Dictionary(Int32, Utf8)')) FROM approx_distinct_group_test WHERE g = 2;
+----
+2
+
+# Dictionary grouped
+query II
+SELECT g, approx_distinct(arrow_cast(s, 'Dictionary(Int32, Utf8)')) FROM approx_distinct_group_test GROUP BY g ORDER BY g;
+----
+1 2
+2 2
+3 0
+4 1
+
+# Dictionary with a non-string value type (Int32), also exercising a
+# larger (Int64) key type
+query I
+SELECT approx_distinct(arrow_cast(i, 'Dictionary(Int64, Int32)')) FROM approx_distinct_group_test WHERE g = 2;
+----
+2
+
+query II
+SELECT g, approx_distinct(arrow_cast(i, 'Dictionary(Int64, Int32)')) FROM approx_distinct_group_test GROUP BY g ORDER BY g;
+----
+1 2
+2 2
+3 0
+4 1
+
+
 # List
 statement ok
 CREATE TABLE approx_distinct_list_test (g INT, l INT[]) AS VALUES