anishshri-db commented on code in PR #48686:
URL: https://github.com/apache/spark/pull/48686#discussion_r1819916471
##########
sql/core/src/test/scala/org/apache/spark/sql/streaming/TransformWithStateInitialStateSuite.scala:
##########
@@ -497,4 +537,85 @@ class TransformWithStateInitialStateSuite extends
StateStoreMetricsTest
)
}
}
+
+ test("transformWithStateWithInitialState - correctness test, " +
+ "run with state data source reader dataframe as initial state") {
+ withSQLConf(SQLConf.STATE_STORE_PROVIDER_CLASS.key ->
+ classOf[RocksDBStateStoreProvider].getName,
+ SQLConf.SHUFFLE_PARTITIONS.key ->
+ TransformWithStateSuiteUtils.NUM_SHUFFLE_PARTITIONS.toString) {
+ withTempDir { checkpointDir =>
+ val inputData = MemoryStream[String]
+ val result = inputData.toDS()
+ .groupByKey(x => x)
+ .transformWithState(new StatefulProcessorWithAllStateVars(),
+ TimeMode.None(),
+ OutputMode.Update())
+
+ testStream(result, OutputMode.Update())(
+ StartStream(checkpointLocation = checkpointDir.getCanonicalPath),
+ AddData(inputData, "a", "b"),
+ CheckNewAnswer(("a", "1"), ("b", "1")),
+ AddData(inputData, "a", "b", "a"),
+ CheckNewAnswer(("a", "3"), ("b", "2"))
+ )
+
+ // state data source reader for state vars
+ val valueDf = spark.read
+ .format("statestore")
+ .option(StateSourceOptions.PATH, checkpointDir.getAbsolutePath)
+ .option(StateSourceOptions.STATE_VAR_NAME, "countState")
+ .load()
+ .selectExpr(
+ "key.value AS groupingKey", "value.value AS value")
+ val listDf = spark.read
+ .format("statestore")
+ .option(StateSourceOptions.PATH, checkpointDir.getAbsolutePath)
+ .option(StateSourceOptions.STATE_VAR_NAME, "listState")
+ .option(StateSourceOptions.FLATTEN_COLLECTION_TYPES, true)
Review Comment:
Can we add a test for list and map with this config set to `false` too ?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
