Skip to content

[SPARK-14578] [SQL] Fix codegen for CreateExternalRow with nested wide schema #12338

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
davies wants to merge 2 commits into from
Closed

[SPARK-14578] [SQL] Fix codegen for CreateExternalRow with nested wide schema #12338

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
1c42e2c
fix codegen of nested CreateExternalRow
Apr 12, 2016
4a472de
regression tests
Apr 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
8 changes: 5 additions & 3 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,6 +446,8 @@ case class MapObjects private(
override def genCode(ctx: CodegenContext, ev: ExprCode): String = {
val javaType = ctx.javaType(dataType)
val elementJavaType = ctx.javaType(loopVar.dataType)
ctx.addMutableState("boolean", loopVar.isNull, "")
ctx.addMutableState(elementJavaType, loopVar.value, "")
val genInputData = inputData.gen(ctx)
val genFunction = lambdaFunction.gen(ctx)
val dataLength = ctx.freshName("dataLength")
Expand All @@ -466,9 +468,9 @@ case class MapObjects private(
}

val loopNullCheck = if (primitiveElement) {
s"boolean ${loopVar.isNull} = ${genInputData.value}.isNullAt($loopIndex);"
s"${loopVar.isNull} = ${genInputData.value}.isNullAt($loopIndex);"
} else {
s"boolean ${loopVar.isNull} = ${genInputData.isNull} || ${loopVar.value} == null;"
s"${loopVar.isNull} = ${genInputData.isNull} || ${loopVar.value} == null;"
}

s"""
Expand All @@ -484,7 +486,7 @@ case class MapObjects private(

int $loopIndex = 0;
while ($loopIndex < $dataLength) {
$elementJavaType ${loopVar.value} =
${loopVar.value} =
($elementJavaType)${genInputData.value}${itemAccessor(loopIndex)};
$loopNullCheck

Expand Down
15 changes: 15 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1664,4 +1664,19 @@ class JsonSuite extends QueryTest with SharedSQLContext with TestJsonData {
)
}
}

test("wide nested json table") {
val nested = (1 to 100).map { i =>
s"""
|"c$i": $i
""".stripMargin
}.mkString(", ")
val json = s"""
|{"a": [{$nested}], "b": [{$nested}]}
""".stripMargin
val rdd = sqlContext.sparkContext.makeRDD(Seq(json))
val df = sqlContext.read.json(rdd)
assert(df.schema.size === 2)
df.collect()
}
}