HeartSaVioR commented on a change in pull request #29256:
URL: https://github.com/apache/spark/pull/29256#discussion_r461558114
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala
##########
@@ -1106,6 +1106,41 @@ class StreamingQuerySuite extends StreamTest with
BeforeAndAfter with Logging wi
}
}
+ test("union in streaming query of append mode without watermark") {
+ val inputData1 = MemoryStream[Int]
+ val inputData2 = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("s1", "s2") {
+ inputData1.toDF().createOrReplaceTempView("s1")
+ inputData2.toDF().createOrReplaceTempView("s2")
+ val unioned = spark.sql(
+ "select s1.value from s1 union select s2.value from s2")
+ checkExceptionMessage(unioned, dir)
+ }
+ }
+ }
+
+ test("distinct in streaming query of append mode without watermark") {
+ val inputData = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("deduptest") {
+ inputData.toDF().toDF("value").createOrReplaceTempView("deduptest")
Review comment:
Just curious: is there specific reason to do toDF() twice?
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala
##########
@@ -1106,6 +1106,41 @@ class StreamingQuerySuite extends StreamTest with
BeforeAndAfter with Logging wi
}
}
+ test("union in streaming query of append mode without watermark") {
+ val inputData1 = MemoryStream[Int]
+ val inputData2 = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("s1", "s2") {
+ inputData1.toDF().createOrReplaceTempView("s1")
+ inputData2.toDF().createOrReplaceTempView("s2")
+ val unioned = spark.sql(
+ "select s1.value from s1 union select s2.value from s2")
+ checkExceptionMessage(unioned, dir)
+ }
+ }
+ }
+
+ test("distinct in streaming query of append mode without watermark") {
+ val inputData = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("deduptest") {
+ inputData.toDF().toDF("value").createOrReplaceTempView("deduptest")
+ val distinct = spark.sql("select distinct value from deduptest")
+ checkExceptionMessage(distinct, dir)
+ }
+ }
+ }
+
+ private def checkExceptionMessage(df: DataFrame, dir: File): Unit = {
+ val exception = intercept[AnalysisException](
+ df.writeStream
+ .option("checkpointLocation", dir.getCanonicalPath)
+ .start(dir.getCanonicalPath))
Review comment:
Even we know the query will throw error, it'd be ideal to follow the
normal path, ensuring we have different dir for output and checkpoint.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingQuerySuite.scala
##########
@@ -1106,6 +1106,41 @@ class StreamingQuerySuite extends StreamTest with
BeforeAndAfter with Logging wi
}
}
+ test("union in streaming query of append mode without watermark") {
+ val inputData1 = MemoryStream[Int]
+ val inputData2 = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("s1", "s2") {
+ inputData1.toDF().createOrReplaceTempView("s1")
+ inputData2.toDF().createOrReplaceTempView("s2")
+ val unioned = spark.sql(
+ "select s1.value from s1 union select s2.value from s2")
+ checkExceptionMessage(unioned, dir)
+ }
+ }
+ }
+
+ test("distinct in streaming query of append mode without watermark") {
+ val inputData = MemoryStream[Int]
+ withTempDir { dir =>
+ withTempView("deduptest") {
+ inputData.toDF().toDF("value").createOrReplaceTempView("deduptest")
+ val distinct = spark.sql("select distinct value from deduptest")
+ checkExceptionMessage(distinct, dir)
+ }
+ }
+ }
+
+ private def checkExceptionMessage(df: DataFrame, dir: File): Unit = {
+ val exception = intercept[AnalysisException](
Review comment:
Looks like withTempDir can be added here instead of all callers, as
callers only use the dir for passing to here.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
