anew commented on code in PR #57365:
URL: https://github.com/apache/spark/pull/57365#discussion_r3627447254
##########
sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd2BatchProcessor.scala:
##########
@@ -811,6 +811,93 @@ case class Scd2BatchProcessor(
staged.select(outputColumns.toImmutableArraySeq: _*)
}
+ /**
+ * Drop delete-encoded rows (tombstones and decomposition tails) that became
redundant after
+ * reconciliation.
+ *
+ * A tombstone or decomposition tail is redundant when the immediately
preceding row's reconciled
+ * [[endAtColName]] equals its own sequence: the preceding upsert already
encodes the delete
+ * boundary, so the standalone delete-encoded row should no longer be routed
to aux.
+ *
+ * For example, an open upsert `[startAt=10, endAt=null)` followed by a
tombstone at `15`
+ * reconciles into a closed upsert `[10, 15)`, making the tombstone
redundant. Likewise, an
+ * existing closed `[10, 20)` bisected by an event at `15` reconciles the
event into `[15, 20)`,
+ * making the `[null, 20)` decomposition tail redundant.
+ */
+ private[autocdc] def dropLeftoverDeletesPostReconciliation(
+ reconciledDf: DataFrame): DataFrame = {
+ val recordStartAt =
+
Scd2BatchProcessor.recordStartAtOf(F.col(AutoCdcReservedNames.cdcMetadataColName))
+ val startAt = F.col(Scd2BatchProcessor.startAtColName)
+ val endAt = F.col(Scd2BatchProcessor.endAtColName)
+
+ // Both tombstones and decomposition tails encode a delete boundary in
their `endAt`. Either
+ // becomes redundant when the immediately preceding upsert was reconciled
to close exactly on
+ // that boundary, since the resulting closed upsert already carries it.
+ val row = Scd2IntervalColumns(recordStartAt, startAt, endAt)
+ val isTombstone = RowClassifier.isTombstone(row)
+ val isDecompositionTail = RowClassifier.isDecompositionTail(row)
+ val isDeleteEncodedRow = isTombstone || isDecompositionTail
+
+ val withWindowCols = reconciledDf
+ .withColumn(
+ Scd2BatchProcessor.previousEndAtColName,
+ F.lag(endAt, 1).over(orderChronologicallyPerKeyWindow)
+ )
+ .withColumn(
+ Scd2BatchProcessor.isRedundantDeleteEncodingColName,
+ isDeleteEncodedRow && (F.col(Scd2BatchProcessor.previousEndAtColName)
<=> endAt)
+ )
+
+ withWindowCols
Review Comment:
I suppose. this still relates to the previous comment? If so, I hope the
updated doc makes it clear
--
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]
