Skip to content

[Iceberg AddFiles] Remove shardedKey #39024

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

Merged
ahmedabu98 merged 1 commit into from
Jun 18, 2026
Merged

[Iceberg AddFiles] Remove shardedKey #39024

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
2 changes: 1 addition & 1 deletion .github/trigger_files/IO_Iceberg_Integration_Tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
{
"comment": "Modify this file in a trivial way to cause this test suite to run.",
"modification": 1
"modification": 2
}
11 changes: 5 additions & 6 deletions sdks/java/io/iceberg/src/main/java/org/apache/beam/sdk/io/iceberg/AddFiles.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,6 @@
import org.apache.beam.sdk.transforms.WithKeys;
import org.apache.beam.sdk.transforms.windowing.BoundedWindow;
import org.apache.beam.sdk.transforms.windowing.PaneInfo;
import org.apache.beam.sdk.util.ShardedKey;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.PCollectionRowTuple;
Expand Down Expand Up @@ -226,8 +225,8 @@ public PCollectionRowTuple expand(PCollection<String> input) {
batchManifestFiles.withMaxBufferingDuration(checkStateNotNull(intervalTrigger));
}

PCollection<KV<ShardedKey<Integer>, Iterable<SerializableDataFile>>> groupedFiles =
keyedFiles.apply("GroupDataFilesIntoBatches", batchDataFiles.withShardedKey());
PCollection<KV<Integer, Iterable<SerializableDataFile>>> groupedFiles =
keyedFiles.apply("GroupDataFilesIntoBatches", batchDataFiles);

PCollection<KV<String, byte[]>> manifests =
groupedFiles.apply(
Expand Down Expand Up @@ -660,7 +659,7 @@ static String getPartitionFromMetrics(Metrics metrics, InputFile inputFile, Tabl
* downstream {@link CommitManifestFilesDoFn}.
*/
static class CreateManifests
extends DoFn<KV<ShardedKey<Integer>, Iterable<SerializableDataFile>>, KV<String, byte[]>> {
extends DoFn<KV<Integer, Iterable<SerializableDataFile>>, KV<String, byte[]>> {
private final IcebergCatalogConfig catalogConfig;
private final String identifier;
private transient @MonotonicNonNull Table table;
Expand All @@ -672,7 +671,7 @@ public CreateManifests(IcebergCatalogConfig catalogConfig, String identifier) {

@ProcessElement
public void process(
@Element KV<ShardedKey<Integer>, Iterable<SerializableDataFile>> batch,
@Element KV<Integer, Iterable<SerializableDataFile>> batch,
OutputReceiver<KV<String, byte[]>> output)
throws IOException {
if (!batch.getValue().iterator().hasNext()) {
Expand All @@ -682,7 +681,7 @@ public void process(
table = catalogConfig.catalog().loadTable(TableIdentifier.parse(identifier));
}

PartitionSpec spec = checkStateNotNull(table.specs().get(batch.getKey().getKey()));
PartitionSpec spec = checkStateNotNull(table.specs().get(batch.getKey()));

String manifestPath =
String.format(
Expand Down
Loading