Skip to content

[SPARK-18674][SQL][Follow-Up] improve the error message of using join #16110

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
wants to merge 3 commits into from
Closed

[SPARK-18674][SQL][Follow-Up] improve the error message of using join #16110

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
70a2d44
added an example.
gatorsmile Dec 1, 2016
e754ef5
added a message
gatorsmile Dec 1, 2016
4d43bca
address comments
gatorsmile Dec 2, 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: 4 additions & 4 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 @@ -1974,14 +1974,14 @@ class Analyzer(
condition: Option[Expression]) = {
val leftKeys = joinNames.map { keyName =>
left.output.find(attr => resolver(attr.name, keyName)).getOrElse {
throw new AnalysisException(s"USING column `$keyName` can not be resolved with the " +
s"left join side, the left output is: [${left.output.map(_.name).mkString(", ")}]")
throw new AnalysisException(s"USING column `$keyName` cannot be resolved on the left " +
s"side of the join. The left-side columns: [${left.output.map(_.name).mkString(", ")}]")
}
}
val rightKeys = joinNames.map { keyName =>
right.output.find(attr => resolver(attr.name, keyName)).getOrElse {
throw new AnalysisException(s"USING column `$keyName` can not be resolved with the " +
s"right join side, the right output is: [${right.output.map(_.name).mkString(", ")}]")
throw new AnalysisException(s"USING column `$keyName` cannot be resolved on the right " +
s"side of the join. The right-side columns: [${right.output.map(_.name).mkString(", ")}]")
}
}
val joinPairs = leftKeys.zip(rightKeys)
Expand Down
16 changes: 13 additions & 3 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 @@ -28,13 +28,16 @@ class ResolveNaturalJoinSuite extends AnalysisTest {
lazy val a = 'a.string
lazy val b = 'b.string
lazy val c = 'c.string
lazy val d = 'd.struct('f1.int, 'f2.long)
lazy val aNotNull = a.notNull
lazy val bNotNull = b.notNull
lazy val cNotNull = c.notNull
lazy val r1 = LocalRelation(b, a)
lazy val r2 = LocalRelation(c, a)
lazy val r3 = LocalRelation(aNotNull, bNotNull)
lazy val r4 = LocalRelation(cNotNull, bNotNull)
lazy val r5 = LocalRelation(d)
lazy val r6 = LocalRelation(d)

test("natural/using inner join") {
val naturalPlan = r1.join(r2, NaturalJoin(Inner), None)
Expand Down Expand Up @@ -108,10 +111,10 @@ class ResolveNaturalJoinSuite extends AnalysisTest {
test("using unresolved attribute") {
assertAnalysisError(
r1.join(r2, UsingJoin(Inner, Seq("d"))),
"USING column `d` can not be resolved with the left join side" :: Nil)
"USING column `d` cannot be resolved on the left side of the join" :: Nil)
assertAnalysisError(
r1.join(r2, UsingJoin(Inner, Seq("b"))),
"USING column `b` can not be resolved with the right join side" :: Nil)
"USING column `b` cannot be resolved on the right side of the join" :: Nil)
}

test("using join with a case sensitive analyzer") {
Expand All @@ -122,7 +125,14 @@ class ResolveNaturalJoinSuite extends AnalysisTest {

assertAnalysisError(
r1.join(r2, UsingJoin(Inner, Seq("A"))),
"USING column `A` can not be resolved with the left join side" :: Nil)
"USING column `A` cannot be resolved on the left side of the join" :: Nil)
}

test("using join on nested fields") {
assertAnalysisError(
r5.join(r6, UsingJoin(Inner, Seq("d.f1"))),
"USING column `d.f1` cannot be resolved on the left side of the join. " +
"The left-side columns: [d]" :: Nil)
}

test("using join with a case insensitive analyzer") {
Expand Down