anishshri-db commented on code in PR #52148:
URL: https://github.com/apache/spark/pull/52148#discussion_r2308800321
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceChangeDataReadSuite.scala:
##########
@@ -322,4 +336,91 @@ abstract class StateDataSourceChangeDataReaderSuite
extends StateDataSourceTestB
checkAnswer(keyToNumValuesDf, keyToNumValuesDfExpectedDf)
}
}
+
+ test("read change feed past multiple snapshots") {
+ withSQLConf("spark.sql.streaming.stateStore.minDeltasForSnapshot" -> "2") {
+ withTempDir { tempDir =>
+ val inputData = MemoryStream[Int]
+ val df = inputData.toDF().groupBy("value").count()
+ testStream(df, OutputMode.Update)(
+ StartStream(checkpointLocation = tempDir.getAbsolutePath),
+ AddData(inputData, 1, 2, 3, 4, 1),
+ ProcessAllAvailable(),
+ AddData(inputData, 2, 3, 4, 5),
+ ProcessAllAvailable(),
+ AddData(inputData, 3, 4, 5, 6),
+ ProcessAllAvailable(),
+ AddData(inputData, 1, 1),
+ ProcessAllAvailable(),
+ AddData(inputData, 1, 1),
+ ProcessAllAvailable(),
+ AddData(inputData, 1, 1),
+ ProcessAllAvailable()
+ )
+
+ val stateDf = spark.read.format("statestore")
+ .option(StateSourceOptions.READ_CHANGE_FEED, value = true)
+ .option(StateSourceOptions.CHANGE_START_BATCH_ID, 0)
+ .option(StateSourceOptions.CHANGE_END_BATCH_ID, 5)
+ .load(tempDir.getAbsolutePath)
+
+ val expectedDf = Seq(
+ Row(0L, "update", Row(3), Row(1), 1),
Review Comment:
Can we also track other operations such as `insert`, `update`, `delete` etc ?
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
