Skip to content

[SPARK-20496][SS] Bug in KafkaWriter Looks at Unanalyzed Plans #17804

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
bllchmbrs wants to merge 3 commits into from
Closed

[SPARK-20496][SS] Bug in KafkaWriter Looks at Unanalyzed Plans #17804

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
05f17c6
fix bug
Apr 28, 2017
77e25f1
minor cleanup
Apr 28, 2017
4ad21fe
nits
Apr 28, 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
4 changes: 2 additions & 2 deletions external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ private[kafka010] object KafkaWriter extends Logging {
queryExecution: QueryExecution,
kafkaParameters: ju.Map[String, Object],
topic: Option[String] = None): Unit = {
val schema = queryExecution.logical.output
val schema = queryExecution.analyzed.output
schema.find(_.name == TOPIC_ATTRIBUTE_NAME).getOrElse(
if (topic == None) {
throw new AnalysisException(s"topic option required when no " +
Expand Down Expand Up @@ -84,7 +84,7 @@ private[kafka010] object KafkaWriter extends Logging {
queryExecution: QueryExecution,
kafkaParameters: ju.Map[String, Object],
topic: Option[String] = None): Unit = {
val schema = queryExecution.logical.output
val schema = queryExecution.analyzed.output
validateQuery(queryExecution, kafkaParameters, topic)
SQLExecution.withNewExecutionId(sparkSession, queryExecution) {
queryExecution.toRdd.foreachPartition { iter =>
Expand Down
16 changes: 16 additions & 0 deletions external/kafka-0-10-sql/src/test/scala/org/apache/spark/sql/kafka010/KafkaSinkSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ import org.apache.spark.SparkException
import org.apache.spark.sql._
import org.apache.spark.sql.catalyst.expressions.{AttributeReference, SpecificInternalRow, UnsafeProjection}
import org.apache.spark.sql.execution.streaming.MemoryStream
import org.apache.spark.sql.functions._
import org.apache.spark.sql.streaming._
import org.apache.spark.sql.test.SharedSQLContext
import org.apache.spark.sql.types.{BinaryType, DataType}
Expand Down Expand Up @@ -108,6 +109,21 @@ class KafkaSinkSuite extends StreamTest with SharedSQLContext {
s"save mode overwrite not allowed for kafka"))
}

test("SPARK-20496: batch - enforce analyzed plans") {
val inputEvents =
spark.range(1, 1000)
.select(to_json(struct("*")) as 'value)

val topic = newTopic()
testUtils.createTopic(topic)
// used to throw UnresolvedException
inputEvents.write
.format("kafka")
.option("kafka.bootstrap.servers", testUtils.brokerAddress)
.option("topic", topic)
.save()
}

test("streaming - write to kafka with topic field") {
val input = MemoryStream[String]
val topic = newTopic()
Expand Down