Skip to content

[SPARK-19065][SQL]Don't inherit expression id in dropDuplicates #16564

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
zsxwing wants to merge 3 commits into from
Closed

[SPARK-19065][SQL]Don't inherit expression id in dropDuplicates #16564

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
13f54a9
Rewrite Alias in StreamExecution if necessary
zsxwing Jan 12, 2017
4f38e3b
Don't inherit expression id in dropDuplicates
zsxwing Jan 12, 2017
26652a0
Add a regression test
zsxwing Jan 17, 2017
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
Next Next commit
Rewrite Alias in StreamExecution if necessary
  • Loading branch information
@zsxwing
zsxwing committed Jan 12, 2017
commit 13f54a93c0cf31a38455e90aec722e890af980c6
7 changes: 6 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamExecution.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ import org.apache.hadoop.fs.Path
import org.apache.spark.internal.Logging
import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.encoders.RowEncoder
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeMap, CurrentBatchTimestamp, CurrentDate, CurrentTimestamp}
import org.apache.spark.sql.catalyst.expressions.{Alias, Attribute, AttributeMap, CurrentBatchTimestamp, CurrentDate, CurrentTimestamp}
import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan}
import org.apache.spark.sql.execution.QueryExecution
import org.apache.spark.sql.execution.command.ExplainCommand
Expand Down Expand Up @@ -495,8 +495,13 @@ class StreamExecution(

// Rewire the plan to use the new attributes that were returned by the source.
val replacementMap = AttributeMap(replacements)
val exprIdMap =
replacements.map { case (oldAttr, newAttr) => (oldAttr.exprId, newAttr.exprId)}.toMap
val triggerLogicalPlan = withNewSources transformAllExpressions {
case a: Attribute if replacementMap.contains(a) => replacementMap(a)
case a: Alias if exprIdMap.contains(a.exprId) =>
// Also rewrite `Alias`s as they may use the same `exprId` of `Attribute`s.
Alias(a.child, a.name)(exprIdMap(a.exprId), a.qualifier, a.explicitMetadata, a.isGenerated)
case ct: CurrentTimestamp =>
CurrentBatchTimestamp(offsetSeqMetadata.batchTimestampMs,
ct.dataType)
Expand Down
26 changes: 26 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,6 +304,32 @@ class StreamSuite extends StreamTest {
q.stop()
}
}

test("SPARK-19065 Alia should be replaced as well") {
withTempPath { testPath =>
val data = Seq((1, 2), (2, 3), (3, 4))
data.toDS.write.mode("overwrite").json(testPath.getCanonicalPath)
val schema = spark.read.json(testPath.getCanonicalPath).schema
val query = spark
.readStream
.schema(schema)
.json(testPath.getCanonicalPath)
.dropDuplicates("_1") // dropDuplicates will create an Alias using the same exprId.
.writeStream
.format("memory")
.queryName("testquery")
.outputMode("complete")
.start()
try {
query.processAllAvailable()
if (query.exception.isDefined) {
throw query.exception.get
}
} finally {
query.stop()
}
}
}
}

/**
Expand Down