Skip to content

[core] Fix paimon_incremental_query with limit push down #7269

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
JingsongLi merged 6 commits into from
Feb 11, 2026
+36 −2
Merged

[core] Fix paimon_incremental_query with limit push down #7269

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2983425
[core] Fix ClassCastException when paimon_incremental_query with limi…
Feb 11, 2026
af2f6f1
return Optional.of(result) when non DataSplit
Feb 11, 2026
040c661
clean code format
Feb 11, 2026
66c54f0
clean code format
Feb 11, 2026
52e83da
clean code
Feb 11, 2026
1513e5d
fix code format
Feb 11, 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
17 changes: 15 additions & 2 deletions paimon-core/src/main/java/org/apache/paimon/table/source/DataTableBatchScan.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,14 @@ private Optional<StartingScanner.Result> applyPushDownLimit() {

long scannedRowCount = 0;
SnapshotReader.Plan plan = ((ScannedResult) result).plan();
List<DataSplit> splits = plan.dataSplits();
List<Split> planSplits = plan.splits();
// Limit pushdown only supports DataSplit. Skip for IncrementalSplit.
if (planSplits.stream().anyMatch(s -> !(s instanceof DataSplit))) {
return Optional.of(result);
}
@SuppressWarnings("unchecked")
List<DataSplit> splits = (List<DataSplit>) (List<?>) planSplits;

LOG.info("Applying limit pushdown. Original splits count: {}", splits.size());
if (splits.isEmpty()) {
return Optional.of(result);
Expand Down Expand Up @@ -193,7 +200,13 @@ private Optional<StartingScanner.Result> applyPushDownTopN() {
}

SnapshotReader.Plan plan = ((ScannedResult) result).plan();
List<DataSplit> splits = plan.dataSplits();
List<Split> planSplits = plan.splits();
// TopN pushdown only supports DataSplit. Skip for IncrementalSplit.
if (planSplits.stream().anyMatch(s -> !(s instanceof DataSplit))) {
return Optional.of(result);
}
@SuppressWarnings("unchecked")
List<DataSplit> splits = (List<DataSplit>) (List<?>) planSplits;
if (splits.isEmpty()) {
return Optional.of(result);
}
Expand Down
21 changes: 21 additions & 0 deletions ...paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/TableValuedFunctionsTest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,6 +344,27 @@ class TableValuedFunctionsTest extends PaimonHiveTestBase {
}
}

test("incremental query by tag with LIMIT") {
sql("use paimon")
withTable("t") {
spark.sql("""
|CREATE TABLE t (a INT, b INT, c STRING)
|USING paimon
|TBLPROPERTIES ('primary-key'='a,b', 'bucket' = '2')
|PARTITIONED BY (a)
|""".stripMargin)
spark.sql("INSERT INTO t VALUES (1, 1, '1'), (2, 2, '2')")
sql("CALL sys.create_tag('t', 'tag1')")
spark.sql("INSERT INTO t VALUES (1, 3, '3'), (2, 4, '4')")
sql("CALL sys.create_tag('t', 'tag2')")

checkAnswer(
spark.sql(
"SELECT * FROM paimon_incremental_query('t', 'tag1', 'tag2') ORDER BY a, b LIMIT 5"),
Seq(Row(1, 3, "3"), Row(2, 4, "4")))
}
}

private def incrementalDF(tableIdent: String, start: Int, end: Int): DataFrame = {
spark.read
.format("paimon")
Expand Down