RussellSpitzer commented on a change in pull request #2752:
URL: https://github.com/apache/iceberg/pull/2752#discussion_r661785343
##########
File path:
spark3/src/main/java/org/apache/iceberg/spark/source/SparkMicroBatchStream.java
##########
@@ -169,35 +176,44 @@ public void stop() {
private List<FileScanTask> planFiles(StreamingOffset startOffset,
StreamingOffset endOffset) {
List<FileScanTask> fileScanTasks = Lists.newArrayList();
- MicroBatch latestMicroBatch = null;
StreamingOffset batchStartOffset =
StreamingOffset.START_OFFSET.equals(startOffset) ?
new StreamingOffset(SnapshotUtil.oldestSnapshot(table).snapshotId(),
0, false) :
startOffset;
+ StreamingOffset currentOffset = null;
+
do {
- StreamingOffset currentOffset =
- latestMicroBatch != null && latestMicroBatch.lastIndexOfSnapshot() ?
- new
StreamingOffset(snapshotAfter(latestMicroBatch.snapshotId()), 0L, false) :
- batchStartOffset;
+ if (currentOffset == null) {
+ currentOffset = batchStartOffset;
+ } else {
+ Snapshot snapshotAfter = SnapshotUtil.snapshotAfter(table,
currentOffset.snapshotId());
+ currentOffset = new StreamingOffset(snapshotAfter.snapshotId(), 0L,
false);
+ }
- latestMicroBatch =
MicroBatches.from(table.snapshot(currentOffset.snapshotId()), table.io())
+ if(!shouldProcess(table.snapshot(currentOffset.snapshotId()))) {
+ LOG.debug("Skipping snapshot: {}", currentOffset.snapshotId());
Review comment:
Probably add a little more info about the context of this skip, Skipping
snapshot in stream x? of table y? Whatever you feel is appropriate
--
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]
