This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-comet.git
The following commit(s) were added to refs/heads/main by this push:
new cdfdc2146 chore: Update documentation and ignore Spark SQL tests for
known issue with count distinct on NaN in aggregate (#1847)
cdfdc2146 is described below
commit cdfdc2146f879bf9246361687ec4d0d25eb2a87e
Author: Andy Grove <agr...@apache.org>
AuthorDate: Fri Jun 6 12:59:30 2025 -0600
chore: Update documentation and ignore Spark SQL tests for known issue with
count distinct on NaN in aggregate (#1847)
---
dev/diffs/3.4.3.diff | 12 +++++++++++-
dev/diffs/3.5.4.diff | 12 +++++++++++-
dev/diffs/3.5.5.diff | 12 +++++++++++-
dev/diffs/4.0.0-preview1.diff | 12 +++++++++++-
docs/source/user-guide/compatibility.md | 9 +++------
docs/templates/compatibility-template.md | 9 +++------
6 files changed, 50 insertions(+), 16 deletions(-)
diff --git a/dev/diffs/3.4.3.diff b/dev/diffs/3.4.3.diff
index 049671c2e..bf44e3d7a 100644
--- a/dev/diffs/3.4.3.diff
+++ b/dev/diffs/3.4.3.diff
@@ -247,7 +247,7 @@ index cf40e944c09..bdd5be4f462 100644
test("A cached table preserves the partitioning and ordering of its cached
SparkPlan") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
-index 1cc09c3d7fc..f031fa45c33 100644
+index 1cc09c3d7fc..b85b53a9688 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
@@ -27,7 +27,7 @@ import org.apache.spark.SparkException
@@ -268,6 +268,16 @@ index 1cc09c3d7fc..f031fa45c33 100644
}
assert(exchangePlans.length == 1)
}
+@@ -1100,7 +1100,8 @@ class DataFrameAggregateSuite extends QueryTest
+ }
+ }
+
+- test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate") {
++ test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate",
++ IgnoreComet("TODO:
https://github.com/apache/datafusion-comet/issues/1824";)) {
+ withTempView("view") {
+ val nan1 = java.lang.Float.intBitsToFloat(0x7f800001)
+ val nan2 = java.lang.Float.intBitsToFloat(0x7fffffff)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
index 56e9520fdab..917932336df 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
diff --git a/dev/diffs/3.5.4.diff b/dev/diffs/3.5.4.diff
index c594fbbe4..8b7f05280 100644
--- a/dev/diffs/3.5.4.diff
+++ b/dev/diffs/3.5.4.diff
@@ -226,7 +226,7 @@ index 9815cb816c9..95b5f9992b0 100644
test("A cached table preserves the partitioning and ordering of its cached
SparkPlan") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
-index 5a8681aed97..da9d25e2eb4 100644
+index 5a8681aed97..db69fde723a 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
@@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.plans.logical.Expand
@@ -247,6 +247,16 @@ index 5a8681aed97..da9d25e2eb4 100644
}
assert(exchangePlans.length == 1)
}
+@@ -1255,7 +1255,8 @@ class DataFrameAggregateSuite extends QueryTest
+ }
+ }
+
+- test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate") {
++ test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate",
++ IgnoreComet("TODO:
https://github.com/apache/datafusion-comet/issues/1824";)) {
+ withTempView("view") {
+ val nan1 = java.lang.Float.intBitsToFloat(0x7f800001)
+ val nan2 = java.lang.Float.intBitsToFloat(0x7fffffff)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
index 56e9520fdab..917932336df 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
diff --git a/dev/diffs/3.5.5.diff b/dev/diffs/3.5.5.diff
index 310aa6881..26a51f6c4 100644
--- a/dev/diffs/3.5.5.diff
+++ b/dev/diffs/3.5.5.diff
@@ -226,7 +226,7 @@ index 9815cb816c9..95b5f9992b0 100644
test("A cached table preserves the partitioning and ordering of its cached
SparkPlan") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
-index 5a8681aed97..da9d25e2eb4 100644
+index 5a8681aed97..db69fde723a 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
@@ -28,7 +28,7 @@ import org.apache.spark.sql.catalyst.plans.logical.Expand
@@ -247,6 +247,16 @@ index 5a8681aed97..da9d25e2eb4 100644
}
assert(exchangePlans.length == 1)
}
+@@ -1255,7 +1255,8 @@ class DataFrameAggregateSuite extends QueryTest
+ }
+ }
+
+- test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate") {
++ test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate",
++ IgnoreComet("TODO:
https://github.com/apache/datafusion-comet/issues/1824";)) {
+ withTempView("view") {
+ val nan1 = java.lang.Float.intBitsToFloat(0x7f800001)
+ val nan2 = java.lang.Float.intBitsToFloat(0x7fffffff)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
index 56e9520fdab..917932336df 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
diff --git a/dev/diffs/4.0.0-preview1.diff b/dev/diffs/4.0.0-preview1.diff
index c014660cf..99cbd0325 100644
--- a/dev/diffs/4.0.0-preview1.diff
+++ b/dev/diffs/4.0.0-preview1.diff
@@ -268,7 +268,7 @@ index d023fb82185..0f4f03bda6c 100644
withTempView("t0", "t1", "t2") {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
-index 620ee430cab..9d383a4bff9 100644
+index 620ee430cab..f5df9218fc1 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
@@ -28,7 +28,7 @@ import
org.apache.spark.sql.catalyst.util.AUTO_GENERATED_ALIAS
@@ -289,6 +289,16 @@ index 620ee430cab..9d383a4bff9 100644
}
assert(exchangePlans.length == 1)
}
+@@ -1275,7 +1275,8 @@ class DataFrameAggregateSuite extends QueryTest
+ }
+ }
+
+- test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate") {
++ test("SPARK-32038: NormalizeFloatingNumbers should work on distinct
aggregate",
++ IgnoreComet("TODO:
https://github.com/apache/datafusion-comet/issues/1824";)) {
+ withTempView("view") {
+ val nan1 = java.lang.Float.intBitsToFloat(0x7f800001)
+ val nan2 = java.lang.Float.intBitsToFloat(0x7fffffff)
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
index f6fd6b501d7..11870c85d82 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameJoinSuite.scala
diff --git a/docs/source/user-guide/compatibility.md
b/docs/source/user-guide/compatibility.md
index 212dc0dc3..39cd3a058 100644
--- a/docs/source/user-guide/compatibility.md
+++ b/docs/source/user-guide/compatibility.md
@@ -29,12 +29,6 @@ Comet aims to provide consistent results with the version of
Apache Spark that i
This guide offers information about areas of functionality where there are
known differences.
-# Compatibility Guide
-
-Comet aims to provide consistent results with the version of Apache Spark that
is being used.
-
-This guide offers information about areas of functionality where there are
known differences.
-
## Parquet Scans
Comet currently has three distinct implementations of the Parquet scan
operator. The configuration property
@@ -89,6 +83,9 @@ because they are handled well in Spark (e.g.,
`SQLOrderingUtil.compareFloats`).
functions of arrow-rs used by DataFusion do not normalize NaN and zero (e.g.,
[arrow::compute::kernels::cmp::eq](https://docs.rs/arrow/latest/arrow/compute/kernels/cmp/fn.eq.html#)).
So Comet will add additional normalization expression of NaN and zero for
comparison.
+There is a known bug with using count(distinct) within aggregate queries,
where each NaN value will be counted
+separately [#1824](https://github.com/apache/datafusion-comet/issues/1824).
+
## Incompatible Expressions
Some Comet native expressions are not 100% compatible with Spark and are
disabled by default. These expressions
diff --git a/docs/templates/compatibility-template.md
b/docs/templates/compatibility-template.md
index 9f9f9911b..e304d933f 100644
--- a/docs/templates/compatibility-template.md
+++ b/docs/templates/compatibility-template.md
@@ -29,12 +29,6 @@ Comet aims to provide consistent results with the version of
Apache Spark that i
This guide offers information about areas of functionality where there are
known differences.
-# Compatibility Guide
-
-Comet aims to provide consistent results with the version of Apache Spark that
is being used.
-
-This guide offers information about areas of functionality where there are
known differences.
-
## Parquet Scans
Comet currently has three distinct implementations of the Parquet scan
operator. The configuration property
@@ -89,6 +83,9 @@ because they are handled well in Spark (e.g.,
`SQLOrderingUtil.compareFloats`).
functions of arrow-rs used by DataFusion do not normalize NaN and zero (e.g.,
[arrow::compute::kernels::cmp::eq](https://docs.rs/arrow/latest/arrow/compute/kernels/cmp/fn.eq.html#)).
So Comet will add additional normalization expression of NaN and zero for
comparison.
+There is a known bug with using count(distinct) within aggregate queries,
where each NaN value will be counted
+separately [#1824](https://github.com/apache/datafusion-comet/issues/1824).
+
## Incompatible Expressions
Some Comet native expressions are not 100% compatible with Spark and are
disabled by default. These expressions
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@datafusion.apache.org
For additional commands, e-mail: commits-h...@datafusion.apache.org
