[arrow-datafusion] branch main updated: enable hash joins on FixedSizeBinary columns (#5461)

[alamb]

This is an automated email from the ASF dual-hosted git repository.

alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion.git


The following commit(s) were added to refs/heads/main by this push:
     new ac618f034 enable hash joins on FixedSizeBinary columns (#5461)
ac618f034 is described below

commit ac618f034f566719f0a76c28608529b0a455a1c1
Author: Max Burke <m...@urbanlogiq.com>
AuthorDate: Fri Mar 3 04:27:26 2023 -0800

    enable hash joins on FixedSizeBinary columns (#5461)
---
 datafusion/core/src/physical_plan/joins/hash_join.rs | 11 +++++++----
 datafusion/expr/src/utils.rs                         |  1 +
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/datafusion/core/src/physical_plan/joins/hash_join.rs 
b/datafusion/core/src/physical_plan/joins/hash_join.rs
index f30e18aa7..7752e1ebf 100644
--- a/datafusion/core/src/physical_plan/joins/hash_join.rs
+++ b/datafusion/core/src/physical_plan/joins/hash_join.rs
@@ -23,10 +23,10 @@ use ahash::RandomState;
 use arrow::{
     array::{
         ArrayData, ArrayRef, BooleanArray, Date32Array, Date64Array, 
Decimal128Array,
-        DictionaryArray, LargeStringArray, PrimitiveArray, 
Time32MillisecondArray,
-        Time32SecondArray, Time64MicrosecondArray, Time64NanosecondArray,
-        TimestampMicrosecondArray, TimestampMillisecondArray, 
TimestampSecondArray,
-        UInt32BufferBuilder, UInt64BufferBuilder,
+        DictionaryArray, FixedSizeBinaryArray, LargeStringArray, 
PrimitiveArray,
+        Time32MillisecondArray, Time32SecondArray, Time64MicrosecondArray,
+        Time64NanosecondArray, TimestampMicrosecondArray, 
TimestampMillisecondArray,
+        TimestampSecondArray, UInt32BufferBuilder, UInt64BufferBuilder,
     },
     datatypes::{
         Int16Type, Int32Type, Int64Type, Int8Type, UInt16Type, UInt32Type, 
UInt64Type,
@@ -1026,6 +1026,9 @@ fn equal_rows(
             DataType::LargeUtf8 => {
                 equal_rows_elem!(LargeStringArray, l, r, left, right, 
null_equals_null)
             }
+            DataType::FixedSizeBinary(_) => {
+                equal_rows_elem!(FixedSizeBinaryArray, l, r, left, right, 
null_equals_null)
+            }
             DataType::Decimal128(_, lscale) => match r.data_type() {
                 DataType::Decimal128(_, rscale) => {
                     if lscale == rscale {
diff --git a/datafusion/expr/src/utils.rs b/datafusion/expr/src/utils.rs
index 5706ef304..8c1be4687 100644
--- a/datafusion/expr/src/utils.rs
+++ b/datafusion/expr/src/utils.rs
@@ -960,6 +960,7 @@ pub fn can_hash(data_type: &DataType) -> bool {
         DataType::Decimal128(_, _) => true,
         DataType::Date32 => true,
         DataType::Date64 => true,
+        DataType::FixedSizeBinary(_) => true,
         DataType::Dictionary(key_type, value_type)
             if *value_type.as_ref() == DataType::Utf8 =>
         {