rdblue commented on code in PR #4578:
URL: https://github.com/apache/iceberg/pull/4578#discussion_r863332089
##########
core/src/main/java/org/apache/iceberg/RemoveSnapshots.java:
##########
@@ -163,21 +188,100 @@ private TableMetadata internalApply() {
this.base = ops.refresh();
Set<Long> idsToRetain = Sets.newHashSet();
- List<Long> ancestorIds = SnapshotUtil.ancestorIds(base.currentSnapshot(),
base::snapshot);
- if (minNumSnapshots >= ancestorIds.size()) {
+ // Identify refs that should be removed
+ Set<String> expiredRefs = computeExpiredRefs(base.refs());
+ Set<Long> idsOfRetainedRefs = base.refs().entrySet().stream()
+ .filter(ref -> !expiredRefs.contains(ref.getKey()))
+ .map(refEntry -> refEntry.getValue().snapshotId())
+ .collect(Collectors.toSet());
+
+ for (Long idToRemove : idsToRemove) {
+ Preconditions.checkArgument(!idsOfRetainedRefs.contains(idToRemove),
+ "Cannot expire %s. There is a reference to it", idToRemove);
+ }
+
+ idsToRetain.addAll(idsOfRetainedRefs);
+
+ List<Map.Entry<String, SnapshotRef>> branches =
base.refs().entrySet().stream()
+ .filter(refEntry -> refEntry.getValue().isBranch())
+ .collect(Collectors.toList());
+
+ Set<Long> branchSnapshotsToRetain =
computeAllBranchSnapshotsToRetain(branches);
+ idsToRetain.addAll(branchSnapshotsToRetain);
+ TableMetadata.Builder updatedMetaBuilder = TableMetadata.buildFrom(base);
+ idsToRemove.addAll(base.snapshots().stream().map(Snapshot::snapshotId)
+ .filter(snapshot ->
!idsToRetain.contains(snapshot)).collect(Collectors.toSet()));
+ updatedMetaBuilder.removeSnapshots(idsToRemove);
+ expiredRefs.forEach(updatedMetaBuilder::removeRef);
+ TableMetadata updatedMetadata = updatedMetaBuilder.build();
+ List<Snapshot> updateSnapshots = updatedMetadata.snapshots();
+ List<Snapshot> baseSnapshots = base.snapshots();
+ boolean updated = updateSnapshots.size() != baseSnapshots.size() ||
expiredRefs.size() > 0;
+ return updated ? updatedMetadata : base;
Review Comment:
The builder should return the original metadata if there are no updates, so
you don't need to duplicate the logic here.
--
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]
