Skip to content

[SPARK-16301] [SQL] The analyzer rule for resolving using joins should respect the case sensitivity setting. #13977

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
yhuai wants to merge 3 commits into from
Closed

[SPARK-16301] [SQL] The analyzer rule for resolving using joins should respect the case sensitivity setting. #13977

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
52ba666
[SPARK-16301] [SQL] The analyzer rulr for resolving using joins shoul…
yhuai Jun 29, 2016
e051a88
Format
yhuai Jun 29, 2016
b5b5954
Add asserts
yhuai Jun 29, 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
26 changes: 19 additions & 7 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1836,13 +1836,25 @@ class Analyzer(
}

private def commonNaturalJoinProcessing(
left: LogicalPlan,
right: LogicalPlan,
joinType: JoinType,
joinNames: Seq[String],
condition: Option[Expression]) = {
val leftKeys = joinNames.map(keyName => left.output.find(_.name == keyName).get)
val rightKeys = joinNames.map(keyName => right.output.find(_.name == keyName).get)
left: LogicalPlan,
right: LogicalPlan,
joinType: JoinType,
joinNames: Seq[String],
condition: Option[Expression]) = {
Copy link
Contributor Author

@yhuai yhuai Jun 29, 2016

Choose a reason for hiding this comment

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

These 5 lines are just formatting changes.

val leftKeys = joinNames.map { keyName =>
val joinColumn = left.output.find(attr => resolver(attr.name, keyName))
assert(
joinColumn.isDefined,
s"$keyName should exist in ${left.output.map(_.name).mkString(",")}")
joinColumn.get
}
val rightKeys = joinNames.map { keyName =>
val joinColumn = right.output.find(attr => resolver(attr.name, keyName))
assert(
joinColumn.isDefined,
s"$keyName should exist in ${right.output.map(_.name).mkString(",")}")
joinColumn.get
}
val joinPairs = leftKeys.zip(rightKeys)

val newCondition = (condition ++ joinPairs.map(EqualTo.tupled)).reduceOption(And)
Expand Down
30 changes: 30 additions & 0 deletions ...alyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveNaturalJoinSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,4 +113,34 @@ class ResolveNaturalJoinSuite extends AnalysisTest {
assert(error.message.contains(
"using columns ['d] can not be resolved given input columns: [b, a, c]"))
}

test("using join with a case sensitive analyzer") {
val expected = r1.join(r2, Inner, Some(EqualTo(a, a))).select(a, b, c)

{
val usingPlan = r1.join(r2, UsingJoin(Inner, Seq(UnresolvedAttribute("a"))), None)
checkAnalysis(usingPlan, expected, caseSensitive = true)
}

{
val usingPlan = r1.join(r2, UsingJoin(Inner, Seq(UnresolvedAttribute("A"))), None)
assertAnalysisError(
usingPlan,
Seq("using columns ['A] can not be resolved given input columns: [b, a, c, a]"))
}
}

test("using join with a case insensitive analyzer") {
val expected = r1.join(r2, Inner, Some(EqualTo(a, a))).select(a, b, c)

{
val usingPlan = r1.join(r2, UsingJoin(Inner, Seq(UnresolvedAttribute("a"))), None)
checkAnalysis(usingPlan, expected, caseSensitive = false)
}

{
val usingPlan = r1.join(r2, UsingJoin(Inner, Seq(UnresolvedAttribute("A"))), None)
checkAnalysis(usingPlan, expected, caseSensitive = false)
}
}
}