hvanhovell commented on code in PR #53452:
URL: https://github.com/apache/spark/pull/53452#discussion_r2612899655
##########
sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -1564,28 +1567,13 @@ class SparkConnectPlanner(
}
// Load and combine all batches
- var combinedRows: Iterator[InternalRow] = Iterator.empty
- var structType: StructType = null
-
- for ((dataHash, batchIndex) <- dataHashes.zipWithIndex) {
- val dataBytes = readChunkedCachedLocalRelationBlock(dataHash)
- val (batchRows, batchStructType) =
- ArrowConverters.fromIPCStream(dataBytes, TaskContext.get())
-
- // For the first batch, set the schema; for subsequent batches, verify
compatibility
- if (batchIndex == 0) {
- structType = batchStructType
- combinedRows = batchRows
-
- } else {
- if (batchStructType != structType) {
- throw
InvalidInputErrors.chunkedCachedLocalRelationChunksWithDifferentSchema()
- }
- combinedRows = combinedRows ++ batchRows
- }
+ val (rows, structType) = ArrowConverters.fromIPCStream(
Review Comment:
We can move this code into buildLocalRelationFromRows now...
--
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]
