Skip to content

[SPARK-29065][SQL][TEST] Extend EXTRACT benchmark #25772

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

Closed
MaxGekk wants to merge 11 commits into from
Closed

[SPARK-29065][SQL][TEST] Extend EXTRACT benchmark #25772

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
d65d834
Benchmark results before changes
MaxGekk Sep 11, 2019
20c9fe8
Extend the extract benchmark
MaxGekk Sep 11, 2019
0844c76
Regenerate results
MaxGekk Sep 11, 2019
cb1e6c0
Support casting long (int, short, byte) to date
MaxGekk Sep 11, 2019
6b9ad66
Add tests for casting to date
MaxGekk Sep 12, 2019
5d20e20
Revert "Add tests for casting to date"
MaxGekk Sep 12, 2019
6a67b99
Revert "Support casting long (int, short, byte) to date"
MaxGekk Sep 12, 2019
c9241d8
Cast to DATE via TIMESTAMP
MaxGekk Sep 12, 2019
e54c41a
Re-gen benchmark results
MaxGekk Sep 12, 2019
add2a4a
Run benchmarks for codegen only
MaxGekk Sep 12, 2019
766110a
Re-gen results
MaxGekk Sep 12, 2019
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
7 changes: 7 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ object Cast {

case (StringType, DateType) => true
case (TimestampType, DateType) => true
case (_: IntegralType, DateType) => true

case (StringType, CalendarIntervalType) => true

Expand Down Expand Up @@ -474,6 +475,10 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
// throw valid precision more than seconds, according to Hive.
// Timestamp.nanos is in 0 to 999,999,999, no more than a second.
buildCast[Long](_, t => microsToEpochDays(t, zoneId))
case LongType => buildCast[Long](_, l => l.toInt)
case IntegerType => buildCast[Int](_, identity)
case ShortType => buildCast[Short](_, s => s.toInt)
case ByteType => buildCast[Byte](_, b => b.toInt)
}

// IntervalConverter
Expand Down Expand Up @@ -1076,6 +1081,8 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
(c, evPrim, evNull) =>
code"""$evPrim =
org.apache.spark.sql.catalyst.util.DateTimeUtils.microsToEpochDays($c, $zid);"""
case _: IntegralType =>
(c, evPrim, _) => code"$evPrim = (int)$c;"
case _ =>
(c, evPrim, evNull) => code"$evNull = true;"
}
Expand Down
11 changes: 7 additions & 4 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -855,10 +855,6 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
assert(cast("1234", DateType).checkInputDataTypes().isSuccess)
assert(cast(new Timestamp(1), DateType).checkInputDataTypes().isSuccess)
assert(cast(false, DateType).checkInputDataTypes().isFailure)
assert(cast(1.toByte, DateType).checkInputDataTypes().isFailure)
assert(cast(1.toShort, DateType).checkInputDataTypes().isFailure)
assert(cast(1, DateType).checkInputDataTypes().isFailure)
assert(cast(1L, DateType).checkInputDataTypes().isFailure)
assert(cast(1.0.toFloat, DateType).checkInputDataTypes().isFailure)
assert(cast(1.0, DateType).checkInputDataTypes().isFailure)
}
Expand Down Expand Up @@ -1200,4 +1196,11 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
checkEvaluation(cast(Long.MinValue - 0.9D, LongType), Long.MinValue)
}
}

test("cast integral types to date") {
checkCast(0.toByte, Date.valueOf("1970-01-01"))
checkCast(-1.toShort, Date.valueOf("1969-12-31"))
checkCast(1, Date.valueOf("1970-01-02"))
checkCast(365, Date.valueOf("1971-01-01"))
}
}
Loading