Skip to content

[SPARK-16488] Fix codegen variable namespace collision in pmod and partitionBy #14144

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
wants to merge 2 commits into from
Closed

[SPARK-16488] Fix codegen variable namespace collision in pmod and partitionBy #14144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8e7b05f
Fix codegen variable namespace collision for pmod
sameeragarwal Jul 12, 2016
8b2639f
s/r/remainder
sameeragarwal Jul 12, 2016
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
25 changes: 13 additions & 12 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -498,34 +498,35 @@ case class Pmod(left: Expression, right: Expression) extends BinaryArithmetic wi

override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
nullSafeCodeGen(ctx, ev, (eval1, eval2) => {
val remainder = ctx.freshName("remainder")
dataType match {
case dt: DecimalType =>
val decimalAdd = "$plus"
s"""
${ctx.javaType(dataType)} r = $eval1.remainder($eval2);
if (r.compare(new org.apache.spark.sql.types.Decimal().set(0)) < 0) {
${ev.value} = (r.$decimalAdd($eval2)).remainder($eval2);
${ctx.javaType(dataType)} $remainder = $eval1.remainder($eval2);
if ($remainder.compare(new org.apache.spark.sql.types.Decimal().set(0)) < 0) {
${ev.value} = ($remainder.$decimalAdd($eval2)).remainder($eval2);
} else {
${ev.value} = r;
${ev.value} = $remainder;
}
"""
// byte and short are casted into int when add, minus, times or divide
case ByteType | ShortType =>
s"""
${ctx.javaType(dataType)} r = (${ctx.javaType(dataType)})($eval1 % $eval2);
if (r < 0) {
${ev.value} = (${ctx.javaType(dataType)})((r + $eval2) % $eval2);
${ctx.javaType(dataType)} $remainder = (${ctx.javaType(dataType)})($eval1 % $eval2);
if ($remainder < 0) {
${ev.value} = (${ctx.javaType(dataType)})(($remainder + $eval2) % $eval2);
} else {
${ev.value} = r;
${ev.value} = $remainder;
}
"""
case _ =>
s"""
${ctx.javaType(dataType)} r = $eval1 % $eval2;
if (r < 0) {
${ev.value} = (r + $eval2) % $eval2;
${ctx.javaType(dataType)} $remainder = $eval1 % $eval2;
if ($remainder < 0) {
${ev.value} = ($remainder + $eval2) % $eval2;
} else {
${ev.value} = r;
${ev.value} = $remainder;
}
"""
}
Expand Down
14 changes: 14 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/test/DataFrameReaderWriterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,6 +449,20 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
}
}

test("pmod with partitionBy") {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you can remove this once #14146 makes it in.

val spark = this.spark
import spark.implicits._

case class Test(a: Int, b: String)
val data = Seq((0, "a"), (1, "b"), (1, "a"))
spark.createDataset(data).createOrReplaceTempView("test")
sql("select * from test distribute by pmod(_1, 2)")
.write
.partitionBy("_2")
.mode("overwrite")
.parquet(dir)
}

private def testRead(
df: => DataFrame,
expectedResult: Seq[String],
Expand Down