Skip to content

[SPARK-48499][SQL] Use Math.abs to get Positive Numbers #46834

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
jackylee-ch wants to merge 1 commit into from
Closed

[SPARK-48499][SQL] Use Math.abs to get Positive Numbers #46834

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion core/src/main/scala/org/apache/spark/scheduler/SplitInfo.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ class SplitInfo(
hashCode = hashCode * 31 + hostLocation.hashCode
hashCode = hashCode * 31 + path.hashCode
// ignore overflow ? It is hashcode anyway !
hashCode = hashCode * 31 + (length & 0x7fffffff).toInt
hashCode = hashCode * 31 + length.toInt
hashCode
}

Expand Down
2 changes: 1 addition & 1 deletion sql/catalyst/src/test/scala/org/apache/spark/sql/connector/catalog/InMemoryBaseTable.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,7 +186,7 @@ abstract class InMemoryBaseTable(
)
var dataTypeHashCode = 0
valueTypePairs.foreach(dataTypeHashCode += _._2.hashCode())
((valueHashCode + 31 * dataTypeHashCode) & Integer.MAX_VALUE) % numBuckets
Math.abs(valueHashCode + 31 * dataTypeHashCode) % numBuckets
case NamedTransform("truncate", Seq(ref: NamedReference, length: Literal[_])) =>
extractor(ref.fieldNames, cleanedSchema, row) match {
case (str: UTF8String, StringType) =>
Expand Down
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,7 +245,7 @@ object FileFormatWriter extends Logging {
jobTrackerID = jobTrackerID,
sparkStageId = taskContext.stageId(),
sparkPartitionId = taskContext.partitionId(),
sparkAttemptNumber = taskContext.taskAttemptId().toInt & Integer.MAX_VALUE,
sparkAttemptNumber = Math.abs(taskContext.taskAttemptId().toInt),
committer,
iterator = iter,
concurrentOutputWriterSpec = concurrentOutputWriterSpec)
Expand Down
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/WriteFiles.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ case class WriteFilesExec(
rddWithNonEmptyPartitions.mapPartitionsInternal { iterator =>
val sparkStageId = TaskContext.get().stageId()
val sparkPartitionId = TaskContext.get().partitionId()
val sparkAttemptNumber = TaskContext.get().taskAttemptId().toInt & Int.MaxValue
val sparkAttemptNumber = Math.abs(TaskContext.get().taskAttemptId().toInt)

val ret = FileFormatWriter.executeTask(
description,
Expand Down
2 changes: 1 addition & 1 deletion ...core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWriterFactory.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ case class FileWriterFactory (
@transient private lazy val jobId = SparkHadoopWriterUtils.createJobID(jobTrackerID, 0)

override def createWriter(partitionId: Int, realTaskId: Long): DataWriter[InternalRow] = {
val taskAttemptContext = createTaskAttemptContext(partitionId, realTaskId.toInt & Int.MaxValue)
val taskAttemptContext = createTaskAttemptContext(partitionId, Math.abs(realTaskId.toInt))
committer.setupTask(taskAttemptContext)
if (description.partitionColumns.isEmpty) {
new SingleDirectoryDataWriter(description, taskAttemptContext, committer)
Expand Down
2 changes: 1 addition & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ class KeyGroupedPartitioningSuite extends DistributionAndOrderingSuiteBase {
Seq(TransformExpression(BucketFunction, Seq(attr("ts")), Some(32))))

// Has exactly one partition.
val partitionValues = Seq(31).map(v => InternalRow.fromSeq(Seq(v)))
val partitionValues = Seq(1).map(v => InternalRow.fromSeq(Seq(v)))
checkQueryPlan(df, distribution,
physical.KeyGroupedPartitioning(distribution.clustering, 1, partitionValues, partitionValues))
}
Expand Down