cloud-fan commented on a change in pull request #34747:
URL: https://github.com/apache/spark/pull/34747#discussion_r758924914
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
##########
@@ -198,21 +205,39 @@ class Analyzer(override val catalogManager:
CatalogManager)
}
def executeAndCheck(plan: LogicalPlan, tracker: QueryPlanningTracker):
LogicalPlan = {
- if (plan.analyzed) return plan
AnalysisHelper.markInAnalyzer {
val analyzed = executeAndTrack(plan, tracker)
try {
checkAnalysis(analyzed)
analyzed
} catch {
case e: AnalysisException =>
- val ae = e.copy(plan = Option(analyzed))
+ val ae = e.copy(plan = Option(analyzed),
+ message = e.message + extraHintForAnsiTypeCoercion(plan))
ae.setStackTrace(e.getStackTrace)
throw ae
}
}
}
+ private def extraHintForAnsiTypeCoercion(plan: LogicalPlan): String = {
+ if (!conf.ansiEnabled) {
+ ""
+ } else {
+ val nonAnsiPlan = AnalysisContext.withDefaultTypeCoercionAnalysisContext
{
+ executeSameContext(plan)
+ }
+ try {
+ checkAnalysis(nonAnsiPlan)
+ "\nTo fix the error, you might need to add explicit type casts.\n" +
Review comment:
Another point is, the analyzer has "side effects", as it may send RPC
requests to the remote catalog. I think it's better to not run the entire
analyzer again, even if the query fails.
--
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]
