zifeif2 commented on code in PR #53316:
URL: https://github.com/apache/spark/pull/53316#discussion_r2624920497
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSource.scala:
##########
@@ -268,13 +291,23 @@ class StateDataSource extends TableProvider with
DataSourceRegister with Logging
if (sourceOptions.readRegisteredTimers) {
stateVarName = TimerStateUtils.getTimerStateVarNames(timeMode)._1
}
-
- val stateVarInfoList = operatorProperties.stateVariables
- .filter(stateVar => stateVar.stateName == stateVarName)
- require(stateVarInfoList.size == 1, s"Failed to find unique state
variable info " +
- s"for state variable $stateVarName in operator
${sourceOptions.operatorId}")
- val stateVarInfo = stateVarInfoList.head
- transformWithStateVariableInfoOpt = Some(stateVarInfo)
+ if (sourceOptions.internalOnlyReadAllColumnFamilies) {
+ stateVariableInfos = operatorProperties.stateVariables
+ } else {
+ var stateVarInfoList = operatorProperties.stateVariables
+ .filter(stateVar => stateVar.stateName == stateVarName)
+ if (stateVarInfoList.isEmpty &&
Review Comment:
added comment below. Also added comment why
internalOnlyReadAllColumnFamilies will collect all stateVariables above
--
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]
