gaborkaszab commented on code in PR #12089:
URL: https://github.com/apache/iceberg/pull/12089#discussion_r1952507098
##########
core/src/main/java/org/apache/iceberg/RemoveSnapshots.java:
##########
@@ -218,23 +218,34 @@ private TableMetadata internalApply() {
updatedMetaBuilder.removeSnapshots(idsToRemove);
if (cleanExpiredMetadata) {
- // TODO: Support cleaning expired schema as well.
Set<Integer> reachableSpecs = Sets.newConcurrentHashSet();
reachableSpecs.add(base.defaultSpecId());
+ Set<Integer> reachableSchemas = Sets.newConcurrentHashSet();
+ reachableSchemas.add(base.currentSchemaId());
+
Tasks.foreach(idsToRetain)
.executeWith(planExecutorService)
.run(
- snapshot ->
- base.snapshot(snapshot).allManifests(ops.io()).stream()
- .map(ManifestFile::partitionSpecId)
- .forEach(reachableSpecs::add));
+ snapshotId -> {
+ base.snapshot(snapshotId).allManifests(ops.io()).stream()
Review Comment:
Done
##########
core/src/test/java/org/apache/iceberg/TestRemoveSnapshots.java:
##########
@@ -1705,6 +1706,36 @@ public void testRemoveSpecsDoesntRemoveDefaultSpec()
throws IOException {
.containsExactly(dataBucketSpec.specId());
}
+ @TestTemplate
+ public void testRemoveSchemas() {
+ table.newAppend().appendFile(FILE_A).commit();
+
+ Set<String> expectedDeletedFiles = Sets.newHashSet();
+ expectedDeletedFiles.add(table.currentSnapshot().manifestListLocation());
+
+ table.updateSchema().addColumn("extra_col1",
Types.StringType.get()).commit();
+
+ table.newAppend().appendFile(FILE_B).commit();
+ expectedDeletedFiles.add(table.currentSnapshot().manifestListLocation());
+
+ table.updateSchema().addColumn("extra_col2",
Types.LongType.get()).deleteColumn("id").commit();
+
+ table.newAppend().appendFile(FILE_A2).commit();
+
+ assertThat(table.schemas().size()).isEqualTo(3);
+
+ Set<String> deletedFiles = Sets.newHashSet();
+ // Expire all snapshots except the current one. Also expire all schemas
except the current one.
Review Comment:
Done
##########
core/src/main/java/org/apache/iceberg/TableMetadata.java:
##########
@@ -1183,6 +1183,21 @@ Builder removeSpecs(Iterable<Integer> specIds) {
.filter(s -> !specIdsToRemove.contains(s.specId()))
.collect(Collectors.toList());
changes.add(new MetadataUpdate.RemovePartitionSpecs(specIdsToRemove));
+
+ return this;
+ }
+
+ Builder removeSchemas(Iterable<Integer> schemaIds) {
Review Comment:
Done
##########
core/src/main/java/org/apache/iceberg/TableMetadata.java:
##########
@@ -1183,6 +1183,21 @@ Builder removeSpecs(Iterable<Integer> specIds) {
.filter(s -> !specIdsToRemove.contains(s.specId()))
.collect(Collectors.toList());
changes.add(new MetadataUpdate.RemovePartitionSpecs(specIdsToRemove));
+
+ return this;
+ }
+
+ Builder removeSchemas(Iterable<Integer> schemaIds) {
+ Set<Integer> schemaIdsToRemove = Sets.newHashSet(schemaIds);
+ Preconditions.checkArgument(
+ !schemaIdsToRemove.contains(currentSchemaId), "Cannot remove the
current schema");
+
+ this.schemas =
+ schemas.stream()
+ .filter(s -> !schemaIdsToRemove.contains(s.schemaId()))
+ .collect(Collectors.toList());
+ changes.add(new MetadataUpdate.RemoveSchemas(schemaIdsToRemove));
Review Comment:
Good point! Done
Will create a separate PR for the same for RemovePartitionSpecs once we sort
this one out.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
