Skip to content

[SPARK-11301][SQL] Fix case sensitivity for filter on partitioned col… #14970

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
dongjoon-hyun wants to merge 1 commit into from
Closed

[SPARK-11301][SQL] Fix case sensitivity for filter on partitioned col… #14970

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
19 changes: 16 additions & 3 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,9 +255,18 @@ private[sql] object DataSourceStrategy extends Strategy with Logging {
predicates: Seq[Expression],
partitionSpec: PartitionSpec): Seq[Partition] = {
val PartitionSpec(partitionColumns, partitions) = partitionSpec
val partitionColumnNames = partitionColumns.map(_.name).toSet
val isCaseSensitive = SQLContext.getActive().get.conf.caseSensitiveAnalysis
val partitionColumnNames = if (isCaseSensitive) {
partitionColumns.map(_.name).toSet
} else {
partitionColumns.map(_.name.toLowerCase).toSet
}
val partitionPruningPredicates = predicates.filter {
_.references.map(_.name).toSet.subsetOf(partitionColumnNames)
if (isCaseSensitive) {
_.references.map(_.name).toSet.subsetOf(partitionColumnNames)
} else {
_.references.map(_.name.toLowerCase).toSet.subsetOf(partitionColumnNames)
}
}

if (partitionPruningPredicates.nonEmpty) {
Expand All @@ -268,7 +277,11 @@ private[sql] object DataSourceStrategy extends Strategy with Logging {

val boundPredicate = InterpretedPredicate.create(predicate.transform {
case a: AttributeReference =>
val index = partitionColumns.indexWhere(a.name == _.name)
val index = if (isCaseSensitive) {
partitionColumns.indexWhere(a.name == _.name)
} else {
partitionColumns.indexWhere(c => a.name.equalsIgnoreCase(c.name))
}
BoundReference(index, partitionColumns(index).dataType, nullable = true)
})

Expand Down
3 changes: 2 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1013,7 +1013,8 @@ class DataFrameSuite extends QueryTest with SharedSQLContext {
test("SPARK-11301: fix case sensitivity for filter on partitioned columns") {
withSQLConf(SQLConf.CASE_SENSITIVE.key -> "false") {
withTempPath { path =>
Seq(2012 -> "a").toDF("year", "val").write.partitionBy("year").parquet(path.getAbsolutePath)
Seq(2012 -> "a", 1999 -> "b").toDF("year", "val").write.partitionBy("year")
.parquet(path.getAbsolutePath)
val df = sqlContext.read.parquet(path.getAbsolutePath)
checkAnswer(df.filter($"yEAr" > 2000).select($"val"), Row("a"))
}
Expand Down