Skip to content

fix: enable cast tests for Spark 4.0 #2919

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
andygrove merged 1 commit into from
Dec 22, 2025
Merged

fix: enable cast tests for Spark 4.0 #2919

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 15 additions & 18 deletions spark/src/test/scala/org/apache/comet/CometCastSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,6 @@ import org.apache.spark.sql.functions.col
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{ArrayType, BooleanType, ByteType, DataType, DataTypes, DecimalType, IntegerType, LongType, ShortType, StringType, StructField, StructType}

import org.apache.comet.CometSparkSessionExtensions.isSpark40Plus
import org.apache.comet.expressions.{CometCast, CometEvalMode}
import org.apache.comet.rules.CometScanTypeChecker
import org.apache.comet.serde.Compatible
Expand Down Expand Up @@ -575,8 +574,6 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
// CAST from StringType

test("cast StringType to BooleanType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
val testValues =
(Seq("TRUE", "True", "true", "FALSE", "False", "false", "1", "0", "", null) ++
gen.generateStrings(dataSize, "truefalseTRUEFALSEyesno10" + whitespaceChars, 8)).toDF("a")
Expand Down Expand Up @@ -617,35 +614,27 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
)

test("cast StringType to ByteType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
// test with hand-picked values
castTest(castStringToIntegralInputs.toDF("a"), DataTypes.ByteType)
// fuzz test
castTest(gen.generateStrings(dataSize, numericPattern, 4).toDF("a"), DataTypes.ByteType)
}

test("cast StringType to ShortType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
// test with hand-picked values
castTest(castStringToIntegralInputs.toDF("a"), DataTypes.ShortType)
// fuzz test
castTest(gen.generateStrings(dataSize, numericPattern, 5).toDF("a"), DataTypes.ShortType)
}

test("cast StringType to IntegerType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
// test with hand-picked values
castTest(castStringToIntegralInputs.toDF("a"), DataTypes.IntegerType)
// fuzz test
castTest(gen.generateStrings(dataSize, numericPattern, 8).toDF("a"), DataTypes.IntegerType)
}

test("cast StringType to LongType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
// test with hand-picked values
castTest(castStringToIntegralInputs.toDF("a"), DataTypes.LongType)
// fuzz test
Expand Down Expand Up @@ -707,8 +696,6 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
}

test("cast StringType to DateType") {
// TODO fix for Spark 4.0.0
assume(!isSpark40Plus)
val validDates = Seq(
"262142-01-01",
"262142-01-01 ",
Expand Down Expand Up @@ -1295,10 +1282,21 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
} else {
if (CometSparkSessionExtensions.isSpark40Plus) {
// for Spark 4 we expect to sparkException carries the message
assert(
sparkException.getMessage
.replace(".WITH_SUGGESTION] ", "]")
.startsWith(cometMessage))
assert(sparkMessage.contains("SQLSTATE"))
if (sparkMessage.startsWith("[NUMERIC_VALUE_OUT_OF_RANGE.WITH_SUGGESTION]")) {
assert(
sparkMessage.replace(".WITH_SUGGESTION] ", "]").startsWith(cometMessage))
} else if (cometMessage.startsWith("[CAST_INVALID_INPUT]") || cometMessage
.startsWith("[CAST_OVERFLOW]")) {
assert(
sparkMessage.startsWith(
cometMessage
.replace(
"If necessary set \"spark.sql.ansi.enabled\" to \"false\" to bypass this error.",
"")))
} else {
assert(sparkMessage.startsWith(cometMessage))
}
} else {
// for Spark 3.4 we expect to reproduce the error message exactly
assert(cometMessage == sparkMessage)
Expand All @@ -1325,5 +1323,4 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
df.write.mode(SaveMode.Overwrite).parquet(filename)
spark.read.parquet(filename)
}

}
Loading