Skip to content

fix AddFilesIT filter for BigLake #39533

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
aIbrahiim wants to merge 2 commits into
base: master
Choose a base branch
from
+12 −3
Open

fix AddFilesIT filter for BigLake #39533

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3629200
fix AddFilesIT filter for BigLake
aIbrahiim Jul 28, 2026
d139340
fix Spotless
aIbrahiim Jul 28, 2026
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
15 changes: 12 additions & 3 deletions sdks/java/io/iceberg/src/test/java/org/apache/beam/sdk/io/iceberg/AddFilesIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,7 @@
import org.apache.beam.sdk.transforms.Filter;
import org.apache.beam.sdk.transforms.JsonToRow;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.SerializableFunction;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.PCollectionRowTuple;
import org.apache.beam.sdk.values.Row;
Expand Down Expand Up @@ -246,10 +247,13 @@ public void testStreamingImportFromExistingIcebergTable()
// first create a source iceberg table
catalog.createTable(srcTableId, beamSchemaToIcebergSchema(ROW_SCHEMA), SPEC);

String filter = format("%s/%s/data/", namespace, srcTableName);
// BigLake may write under {namespace}/{table}/{id}/data/... rather than the Hive-style
// {namespace}/{table}/data/... layout, so match the table prefix and a /data/ segment.
String tablePrefix = format("%s/%s/", namespace, srcTableName);

// build AddFiles pipeline and let it run in the background
PipelineResult addFilesPipeline = startAddFilesListener(filter);
PipelineResult addFilesPipeline =
startAddFilesListener(name -> name.contains(tablePrefix) && name.contains("/data/"));

// before writing, confirm the destination table still does not exist
assertFalse(catalog.tableExists(destTableId));
Expand Down Expand Up @@ -503,14 +507,19 @@ private boolean checkTableHasRegisteredParquetFiles(List<String> parquetFiles) {
}

private PipelineResult startAddFilesListener(String filter) throws InterruptedException {
return startAddFilesListener(name -> name.contains(filter));
}

private PipelineResult startAddFilesListener(
SerializableFunction<String, Boolean> objectNameFilter) throws InterruptedException {
DirectOptions options = TestPipeline.testingPipelineOptions().as(DirectOptions.class);
options.setBlockOnRun(false);
Pipeline p = Pipeline.create(options);

PCollectionRowTuple tuple =
p.apply(PubsubIO.readStrings().fromTopic(notificationsTopic))
.apply(JsonToRow.withSchema(NOTIFICATION_SCHEMA))
.apply(Filter.by(row -> row.getString("name").contains(filter)))
.apply(Filter.by(row -> objectNameFilter.apply(row.getString("name"))))
.apply(
MapElements.into(strings())
.via(
Expand Down
Loading