You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ue...@apache.org on 2018/09/04 05:00:06 UTC
spark git commit: [SPARK-25310][SQL] ArraysOverlap may throw a
CompilationException
Repository: spark
Updated Branches:
refs/heads/master b60ee3a33 -> 4cb2ff9d8
[SPARK-25310][SQL] ArraysOverlap may throw a CompilationException
## What changes were proposed in this pull request?
This PR fixes a problem that `ArraysOverlap` function throws a `CompilationException` with non-nullable array type.
The following is the stack trace of the original problem:
```
Code generation of arrays_overlap([1,2,3], [4,5,3]) failed:
java.util.concurrent.ExecutionException: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 56, Column 11: failed to compile: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 56, Column 11: Expression "isNull_0" is not an rvalue
java.util.concurrent.ExecutionException: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 56, Column 11: failed to compile: org.codehaus.commons.compiler.CompileException: File 'generated.java', Line 56, Column 11: Expression "isNull_0" is not an rvalue
at com.google.common.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
at com.google.common.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
at com.google.common.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
at com.google.common.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
at com.google.common.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
at com.google.common.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
at com.google.common.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
at com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2257)
at com.google.common.cache.LocalCache.get(LocalCache.java:4000)
at com.google.common.cache.LocalCache.getOrLoad(LocalCache.java:4004)
at com.google.common.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4874)
at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator$.compile(CodeGenerator.scala:1305)
at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:143)
at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:48)
at org.apache.spark.sql.catalyst.expressions.codegen.GenerateMutableProjection$.create(GenerateMutableProjection.scala:32)
at org.apache.spark.sql.catalyst.expressions.codegen.CodeGenerator.generate(CodeGenerator.scala:1260)
```
## How was this patch tested?
Added test in `CollectionExpressionSuite`.
Closes #22317 from kiszk/SPARK-25310.
Authored-by: Kazuaki Ishizaki <is...@jp.ibm.com>
Signed-off-by: Takuya UESHIN <ue...@databricks.com>
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/4cb2ff9d
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/4cb2ff9d
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/4cb2ff9d
Branch: refs/heads/master
Commit: 4cb2ff9d8a58da5170744a634f672ba07b0a6a24
Parents: b60ee3a
Author: Kazuaki Ishizaki <is...@jp.ibm.com>
Authored: Tue Sep 4 14:00:00 2018 +0900
Committer: Takuya UESHIN <ue...@databricks.com>
Committed: Tue Sep 4 14:00:00 2018 +0900
----------------------------------------------------------------------
.../spark/sql/catalyst/expressions/collectionOperations.scala | 6 ++++--
.../sql/catalyst/expressions/CollectionExpressionsSuite.scala | 5 +++++
2 files changed, 9 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/4cb2ff9d/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
----------------------------------------------------------------------
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
index a29828e..5e4f48e 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
@@ -1636,12 +1636,13 @@ case class ArraysOverlap(left: Expression, right: Expression)
val set = ctx.freshName("set")
val addToSetFromSmallerCode = nullSafeElementCodegen(
smaller, i, s"$set.add($getFromSmaller);", s"${ev.isNull} = true;")
+ val setIsNullCode = if (nullable) s"${ev.isNull} = false;" else ""
val elementIsInSetCode = nullSafeElementCodegen(
bigger,
i,
s"""
|if ($set.contains($getFromBigger)) {
- | ${ev.isNull} = false;
+ | $setIsNullCode
| ${ev.value} = true;
| break;
|}
@@ -1666,12 +1667,13 @@ case class ArraysOverlap(left: Expression, right: Expression)
val j = ctx.freshName("j")
val getFromSmaller = CodeGenerator.getValue(smaller, elementType, j)
val getFromBigger = CodeGenerator.getValue(bigger, elementType, i)
+ val setIsNullCode = if (nullable) s"${ev.isNull} = false;" else ""
val compareValues = nullSafeElementCodegen(
smaller,
j,
s"""
|if (${ctx.genEqual(elementType, getFromSmaller, getFromBigger)}) {
- | ${ev.isNull} = false;
+ | $setIsNullCode
| ${ev.value} = true;
|}
""".stripMargin,
http://git-wip-us.apache.org/repos/asf/spark/blob/4cb2ff9d/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollectionExpressionsSuite.scala
----------------------------------------------------------------------
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollectionExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollectionExpressionsSuite.scala
index 96ae7d1..c7db4ec 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollectionExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CollectionExpressionsSuite.scala
@@ -449,6 +449,7 @@ class CollectionExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper
val a4 = Literal.create(Seq[String](null, ""), ArrayType(StringType))
val a5 = Literal.create(Seq[String]("", "abc"), ArrayType(StringType))
val a6 = Literal.create(Seq[String]("def", "ghi"), ArrayType(StringType))
+ val a7 = Literal.create(Seq(1, 2, 3), ArrayType(IntegerType, containsNull = false))
val emptyIntArray = Literal.create(Seq.empty[Int], ArrayType(IntegerType))
@@ -463,6 +464,7 @@ class CollectionExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper
checkEvaluation(ArraysOverlap(a4, a5), true)
checkEvaluation(ArraysOverlap(a4, a6), null)
checkEvaluation(ArraysOverlap(a5, a6), false)
+ checkEvaluation(ArraysOverlap(a7, a7), true)
// null handling
checkEvaluation(ArraysOverlap(emptyIntArray, a2), false)
@@ -481,9 +483,12 @@ class CollectionExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper
ArrayType(BinaryType))
val b2 = Literal.create(Seq[Array[Byte]](Array[Byte](2, 1), Array[Byte](4, 3)),
ArrayType(BinaryType))
+ val b3 = Literal.create(Seq[Array[Byte]](Array[Byte](1, 2), Array[Byte](3, 4)),
+ ArrayType(BinaryType, containsNull = false))
checkEvaluation(ArraysOverlap(b0, b1), true)
checkEvaluation(ArraysOverlap(b0, b2), false)
+ checkEvaluation(ArraysOverlap(b3, b3), true)
// arrays of complex data types
val aa0 = Literal.create(Seq[Array[String]](Array[String]("a", "b"), Array[String]("c", "d")),
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org