Skip to content

Core: Discard changes when suppressing historical snapshots in CatalogHandlers #17843

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ebyhr wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Core: Discard changes when suppressing historical snapshots in CatalogHandlers #17843

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/iceberg/rest/CatalogHandlers.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,6 +528,7 @@ public static LoadTableResponse loadTable(
TableMetadata.buildFrom(loadedMetadata)
.withMetadataLocation(loadedMetadata.metadataFileLocation())
.suppressHistoricalSnapshots()
.discardChanges()
.build();
break;
default:
Expand Down
71 changes: 71 additions & 0 deletions core/src/test/java/org/apache/iceberg/rest/TestRESTCatalog.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,8 @@
import org.apache.iceberg.CatalogProperties;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.DataFiles;
import org.apache.iceberg.GenericBlobMetadata;
import org.apache.iceberg.GenericStatisticsFile;
import org.apache.iceberg.HasTableOperations;
import org.apache.iceberg.HistoryEntry;
import org.apache.iceberg.MetadataUpdate;
Expand Down Expand Up @@ -1123,6 +1125,75 @@ public void testTableSnapshotLoading() {
any());
}

@Test
public void testTableSnapshotLoadingWithStatisticsOnHistoricalSnapshot() {
RESTCatalogAdapter adapter = Mockito.spy(new RESTCatalogAdapter(backendCatalog));

RESTCatalog catalog =
new RESTCatalog(SessionCatalog.SessionContext.createEmpty(), (config) -> adapter);
catalog.initialize(
"test",
ImmutableMap.of(
CatalogProperties.URI,
"ignored",
CatalogProperties.FILE_IO_IMPL,
"org.apache.iceberg.inmemory.InMemoryFileIO",
RESTCatalogProperties.SNAPSHOT_LOADING_MODE,
SnapshotMode.REFS.name()));

if (requiresNamespaceCreate()) {
catalog.createNamespace(TABLE.namespace());
}

Table table = catalog.createTable(TABLE, SCHEMA);
table
.newFastAppend()
.appendFile(
DataFiles.builder(PartitionSpec.unpartitioned())
.withPath("/path/to/data-a.parquet")
.withFileSizeInBytes(10)
.withRecordCount(2)
.build())
.commit();

long firstSnapshotId = table.currentSnapshot().snapshotId();

// add a statistics file to the first snapshot
table
.updateStatistics()
.setStatistics(
new GenericStatisticsFile(
firstSnapshotId,
"/path/to/stats.puffin",
100,
42,
ImmutableList.of(
new GenericBlobMetadata(
"some-stats", firstSnapshotId, 1, ImmutableList.of(1), ImmutableMap.of()))))
.commit();

// second snapshot makes the first snapshot historical (unreferenced)
table
.newFastAppend()
.appendFile(
DataFiles.builder(PartitionSpec.unpartitioned())
.withPath("/path/to/data-b.parquet")
.withFileSizeInBytes(10)
.withRecordCount(2)
.build())
.commit();

Table refsTable = catalog.loadTable(TABLE);

@ebyhr ebyhr Aug 27, 2026

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This line throws an exception if we revert CatalogHandlers's change:

Cannot set metadata location with changes to table metadata: 1 changes
java.lang.IllegalArgumentException: Cannot set metadata location with changes to table metadata: 1 changes
	at org.apache.iceberg.rest.ErrorHandlers$DefaultErrorHandler.accept(ErrorHandlers.java:339)
	at org.apache.iceberg.rest.ErrorHandlers$TableErrorHandler.accept(ErrorHandlers.java:160)
	at org.apache.iceberg.rest.ErrorHandlers$TableErrorHandler.accept(ErrorHandlers.java:142)
	at org.apache.iceberg.rest.RESTCatalogAdapter.execute(RESTCatalogAdapter.java:649)
	at java.base/java.lang.invoke.MethodHandle.invokeWithArguments(MethodHandle.java:732)
	at org.apache.iceberg.rest.RESTCatalogAdapter.execute(RESTCatalogAdapter.java:624)
	at java.base/java.lang.invoke.MethodHandle.invokeWithArguments(MethodHandle.java:732)
	at org.apache.iceberg.rest.RESTCatalogAdapter.execute(RESTCatalogAdapter.java:613)
	at org.apache.iceberg.rest.BaseHTTPClient.get(BaseHTTPClient.java:101)
	at java.base/java.lang.invoke.MethodHandle.invokeWithArguments(MethodHandle.java:732)
	at org.apache.iceberg.rest.BaseHTTPClient.get(BaseHTTPClient.java:100)
	at org.apache.iceberg.rest.RESTSessionCatalog.loadInternal(RESTSessionCatalog.java:453)
	at org.apache.iceberg.rest.RESTSessionCatalog.loadTable(RESTSessionCatalog.java:483)
	at org.apache.iceberg.catalog.BaseSessionCatalog$AsCatalog.loadTable(BaseSessionCatalog.java:105)
	at org.apache.iceberg.rest.RESTCatalog.loadTable(RESTCatalog.java:124)
	at org.apache.iceberg.rest.TestRESTCatalog.testTableSnapshotLoadingWithStatisticsOnHistoricalSnapshot(TestRESTCatalog.java:1187)
	at java.base/java.lang.reflect.Method.invoke(Method.java:569)
	at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)
	at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)


assertThat(((BaseTable) refsTable).operations().current())
.extracting("snapshots")
.asInstanceOf(InstanceOfAssertFactories.list(Snapshot.class))
.hasSize(1);

assertThat(refsTable.currentSnapshot()).isEqualTo(table.currentSnapshot());
Comment thread
ebyhr marked this conversation as resolved.
assertThat(refsTable.statisticsFiles()).isEmpty();
}

@ParameterizedTest
@ValueSource(strings = {"1", "2"})
public void testTableSnapshotLoadingWithDivergedBranches(String formatVersion) {
Expand Down
Loading