kbuci commented on code in PR #18172:
URL: https://github.com/apache/hudi/pull/18172#discussion_r2796474337
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/cluster/strategy/PartitionAwareClusteringPlanStrategy.java:
##########
@@ -102,15 +102,23 @@ protected Pair<Stream<HoodieClusteringGroup>, Boolean>
buildClusteringGroupsForP
}
if (!currentGroup.isEmpty()) {
- if (currentGroup.size() > 1 ||
writeConfig.shouldClusteringSingleGroup()) {
- int numOutputGroups = getNumberOfOutputFileGroups(totalSizeSoFar,
writeConfig.getClusteringTargetFileMaxBytes());
- log.info("Adding final clustering group " + totalSizeSoFar + " max
bytes: "
- + writeConfig.getClusteringMaxBytesInGroup() + " num input slices:
" + currentGroup.size() + " output groups: " + numOutputGroups);
- fileSliceGroups.add(Pair.of(currentGroup, numOutputGroups));
- }
+ int numOutputGroups = getNumberOfOutputFileGroups(totalSizeSoFar,
writeConfig.getClusteringTargetFileMaxBytes());
+ log.info("Adding final clustering group " + totalSizeSoFar + " max
bytes: "
+ + writeConfig.getClusteringMaxBytesInGroup() + " num input slices: "
+ currentGroup.size() + " output groups: " + numOutputGroups);
+ fileSliceGroups.add(Pair.of(currentGroup, numOutputGroups));
}
- return Pair.of(fileSliceGroups.stream().map(fileSliceGroup ->
+ return Pair.of(fileSliceGroups.stream().filter(fileSliceGroup -> {
+ if (fileSliceGroup.getLeft().size() == 1 && fileSliceGroup.getRight() ==
1 && !writeConfig.isSingleGroupClusteringEnabled()) {
+ FileSlice targetedFileSlice = fileSliceGroup.getLeft().get(0);
+ long size = targetedFileSlice.getBaseFile().isPresent() ?
targetedFileSlice.getBaseFile().get().getFileSize() :
writeConfig.getParquetMaxFileSize();
Review Comment:
Sorry that was a typo, thanks for catching. Updated
--
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]
