Copilot commented on code in PR #13214:
URL: https://github.com/apache/gluten/pull/13214#discussion_r4478140329
##########
backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala:
##########
@@ -197,6 +197,62 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateSuite {
}
}
+ test("shiftrightunsigned") {
Review Comment:
The test name only mentions `shiftrightunsigned`, but it also conditionally
validates the `>>>` operator. Renaming the test to reflect both (e.g., include
`>>>`) would make failures easier to triage and better communicate the covered
surface area.
##########
backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala:
##########
@@ -197,6 +197,62 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateSuite {
}
}
+ test("shiftrightunsigned") {
+ withTempPath {
+ path =>
+ withTempView("shift_input") {
+ Seq[(Integer, java.lang.Long, Integer)](
+ (8, 8L, 1),
+ (-1, -1L, 1),
+ (Int.MinValue, Long.MinValue, 1),
+ (Int.MinValue, Long.MinValue, 31),
+ (-1, -1L, 32),
+ (-1, -1L, 33),
+ (-1, -1L, 63),
+ (-1, -1L, 64),
+ (-1, -1L, 65),
+ (-1, -1L, -1),
+ (Int.MinValue, Long.MinValue, Int.MaxValue),
+ (null, null, 1),
+ (1, 1L, null)
+ )
+ .toDF("int_value", "long_value", "shift")
+ .write
+ .parquet(path.getCanonicalPath)
+
+
spark.read.parquet(path.getCanonicalPath).createOrReplaceTempView("shift_input")
+ runQueryAndCompare(
+ """
+ |SELECT
+ | shiftrightunsigned(int_value, shift),
+ | shiftrightunsigned(long_value, shift)
+ |FROM shift_input
+ |""".stripMargin) {
+ df =>
+ checkGlutenPlan[ProjectExecTransformer](df)
+ assert(
+
!getExecutedPlan(df).exists(_.isInstanceOf[ColumnarPartialProjectExec]),
+ "Unsigned shifts must not use partial JVM projection")
Review Comment:
The plan assertions are duplicated across the function and operator queries.
Extracting a small helper (e.g., `assertNoPartialProject(df)`) reduces
duplication and makes it less error-prone to update the check/message
consistently in the future.
##########
backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala:
##########
@@ -197,6 +197,62 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateSuite {
}
}
+ test("shiftrightunsigned") {
+ withTempPath {
+ path =>
+ withTempView("shift_input") {
+ Seq[(Integer, java.lang.Long, Integer)](
+ (8, 8L, 1),
+ (-1, -1L, 1),
+ (Int.MinValue, Long.MinValue, 1),
+ (Int.MinValue, Long.MinValue, 31),
+ (-1, -1L, 32),
+ (-1, -1L, 33),
+ (-1, -1L, 63),
+ (-1, -1L, 64),
+ (-1, -1L, 65),
+ (-1, -1L, -1),
+ (Int.MinValue, Long.MinValue, Int.MaxValue),
+ (null, null, 1),
+ (1, 1L, null)
+ )
+ .toDF("int_value", "long_value", "shift")
+ .write
+ .parquet(path.getCanonicalPath)
+
+
spark.read.parquet(path.getCanonicalPath).createOrReplaceTempView("shift_input")
+ runQueryAndCompare(
+ """
+ |SELECT
+ | shiftrightunsigned(int_value, shift),
+ | shiftrightunsigned(long_value, shift)
+ |FROM shift_input
+ |""".stripMargin) {
+ df =>
+ checkGlutenPlan[ProjectExecTransformer](df)
+ assert(
+
!getExecutedPlan(df).exists(_.isInstanceOf[ColumnarPartialProjectExec]),
+ "Unsigned shifts must not use partial JVM projection")
+ }
+ if (isSparkVersionGE("4.0")) {
+ runQueryAndCompare(
+ """
+ |SELECT
+ | int_value >>> shift,
+ | long_value >>> shift
+ |FROM shift_input
+ |""".stripMargin) {
Review Comment:
The test name only mentions `shiftrightunsigned`, but it also conditionally
validates the `>>>` operator. Renaming the test to reflect both (e.g., include
`>>>`) would make failures easier to triage and better communicate the covered
surface area.
##########
docs/backends/velox/velox-backend-scalar-function-support.md:
##########
@@ -1,6 +1,6 @@
# Scalar Functions Support Status
-**Out of 433 scalar functions in Spark 4.1, Gluten currently fully supports
261 functions and partially supports 31 functions.**
+**Out of 433 scalar functions in Spark 4.1, Gluten currently fully supports
262 functions and partially supports 31 functions.**
Review Comment:
The supported/partial totals are manually maintained and can easily drift
from the table (especially since the table contains multiple syntaxes/aliases
mapping to the same Spark expression). Consider generating these counts from
the same source as the table (or removing the hard-coded totals) to prevent
inconsistencies over time.
##########
backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala:
##########
@@ -197,6 +197,62 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateSuite {
}
}
+ test("shiftrightunsigned") {
+ withTempPath {
+ path =>
+ withTempView("shift_input") {
+ Seq[(Integer, java.lang.Long, Integer)](
+ (8, 8L, 1),
+ (-1, -1L, 1),
+ (Int.MinValue, Long.MinValue, 1),
+ (Int.MinValue, Long.MinValue, 31),
+ (-1, -1L, 32),
+ (-1, -1L, 33),
+ (-1, -1L, 63),
+ (-1, -1L, 64),
+ (-1, -1L, 65),
+ (-1, -1L, -1),
+ (Int.MinValue, Long.MinValue, Int.MaxValue),
+ (null, null, 1),
+ (1, 1L, null)
+ )
+ .toDF("int_value", "long_value", "shift")
+ .write
+ .parquet(path.getCanonicalPath)
+
+
spark.read.parquet(path.getCanonicalPath).createOrReplaceTempView("shift_input")
+ runQueryAndCompare(
+ """
+ |SELECT
+ | shiftrightunsigned(int_value, shift),
+ | shiftrightunsigned(long_value, shift)
+ |FROM shift_input
+ |""".stripMargin) {
+ df =>
+ checkGlutenPlan[ProjectExecTransformer](df)
+ assert(
+
!getExecutedPlan(df).exists(_.isInstanceOf[ColumnarPartialProjectExec]),
+ "Unsigned shifts must not use partial JVM projection")
Review Comment:
When this assertion fails, the error message doesn’t show which node(s)
triggered it. Consider capturing the matching nodes and including them in the
assertion message (e.g., list the offending plan fragments/classes). This makes
CI-only failures much faster to debug.
##########
backends-velox/src/test/scala/org/apache/gluten/functions/ScalarFunctionsValidateSuite.scala:
##########
@@ -197,6 +197,62 @@ class ScalarFunctionsValidateSuite extends
FunctionsValidateSuite {
}
}
+ test("shiftrightunsigned") {
+ withTempPath {
+ path =>
+ withTempView("shift_input") {
+ Seq[(Integer, java.lang.Long, Integer)](
+ (8, 8L, 1),
+ (-1, -1L, 1),
+ (Int.MinValue, Long.MinValue, 1),
+ (Int.MinValue, Long.MinValue, 31),
+ (-1, -1L, 32),
+ (-1, -1L, 33),
+ (-1, -1L, 63),
+ (-1, -1L, 64),
+ (-1, -1L, 65),
+ (-1, -1L, -1),
+ (Int.MinValue, Long.MinValue, Int.MaxValue),
+ (null, null, 1),
+ (1, 1L, null)
+ )
+ .toDF("int_value", "long_value", "shift")
+ .write
+ .parquet(path.getCanonicalPath)
+
+
spark.read.parquet(path.getCanonicalPath).createOrReplaceTempView("shift_input")
+ runQueryAndCompare(
+ """
+ |SELECT
+ | shiftrightunsigned(int_value, shift),
+ | shiftrightunsigned(long_value, shift)
+ |FROM shift_input
+ |""".stripMargin) {
+ df =>
+ checkGlutenPlan[ProjectExecTransformer](df)
+ assert(
+
!getExecutedPlan(df).exists(_.isInstanceOf[ColumnarPartialProjectExec]),
+ "Unsigned shifts must not use partial JVM projection")
+ }
+ if (isSparkVersionGE("4.0")) {
+ runQueryAndCompare(
+ """
+ |SELECT
+ | int_value >>> shift,
+ | long_value >>> shift
+ |FROM shift_input
+ |""".stripMargin) {
+ df =>
+ checkGlutenPlan[ProjectExecTransformer](df)
+ assert(
+
!getExecutedPlan(df).exists(_.isInstanceOf[ColumnarPartialProjectExec]),
+ "Unsigned shifts must not use partial JVM projection")
Review Comment:
The plan assertions are duplicated across the function and operator queries.
Extracting a small helper (e.g., `assertNoPartialProject(df)`) reduces
duplication and makes it less error-prone to update the check/message
consistently in the future.
--
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]
