This is an automated email from the ASF dual-hosted git repository.
lzljs3620320 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new db56793fbb [spark] Disable compaction for data evolution table (#6342)
db56793fbb is described below
commit db56793fbb2f580eb1f1090e8dbb0bb4f0c81e7c
Author: Juntao Zhang <[email protected]>
AuthorDate: Fri Oct 10 12:05:52 2025 +0800
[spark] Disable compaction for data evolution table (#6342)
---
docs/content/append-table/data-evolution.md | 4 ++--
.../apache/paimon/spark/procedure/CompactProcedure.java | 3 +++
.../org/apache/paimon/spark/sql/RowTrackingTestBase.scala | 15 +++++++++++++++
3 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/docs/content/append-table/data-evolution.md
b/docs/content/append-table/data-evolution.md
index 7d3ff96a11..3cdf67da7e 100644
--- a/docs/content/append-table/data-evolution.md
+++ b/docs/content/append-table/data-evolution.md
@@ -67,7 +67,7 @@ ON t.id = s.id
WHEN MATCHED THEN UPDATE SET t.b = s.b
WHEN NOT MATCHED THEN INSERT (id, b, c) VALUES (id, b, 0);
-SELECT * FROM my_table;
+SELECT * FROM target_table;
+----+----+----+
| id | b | c |
+----+----+----+
@@ -80,7 +80,7 @@ This statement updates only the `b` column in the target
table `target_table` ba
`source_table`. The `id` column and `c` column remain unchanged, and new
records are inserted with the specified values. The difference between this and
table those are not enabled with data evolution is that only the `b` column
data is written to new files.
Note that:
-* Data Evolution Table does not support 'Delete' statement yet.
+* Data Evolution Table does not support 'Delete', 'Update', or 'Compact'
statement yet.
* Merge Into for Data Evolution Table does not support 'WHEN NOT MATCHED BY
SOURCE' clause.
## Spec
diff --git
a/paimon-spark/paimon-spark-common/src/main/java/org/apache/paimon/spark/procedure/CompactProcedure.java
b/paimon-spark/paimon-spark-common/src/main/java/org/apache/paimon/spark/procedure/CompactProcedure.java
index 7788a5a0be..2796b6deb6 100644
---
a/paimon-spark/paimon-spark-common/src/main/java/org/apache/paimon/spark/procedure/CompactProcedure.java
+++
b/paimon-spark/paimon-spark-common/src/main/java/org/apache/paimon/spark/procedure/CompactProcedure.java
@@ -191,6 +191,9 @@ public class CompactProcedure extends BaseProcedure {
tableIdent,
table -> {
checkArgument(table instanceof FileStoreTable);
+ checkArgument(
+ !((FileStoreTable)
table).coreOptions().dataEvolutionEnabled(),
+ "Compact operation is not supported when data
evolution is enabled yet.");
checkArgument(
sortColumns.stream().noneMatch(table.partitionKeys()::contains),
"order_by should not contain partition cols,
because it is meaningless, your order_by cols are %s, and partition cols are
%s",
diff --git
a/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/RowTrackingTestBase.scala
b/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/RowTrackingTestBase.scala
index 422b51a10e..cda852f3a4 100644
---
a/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/RowTrackingTestBase.scala
+++
b/paimon-spark/paimon-spark-ut/src/test/scala/org/apache/paimon/spark/sql/RowTrackingTestBase.scala
@@ -340,6 +340,21 @@ abstract class RowTrackingTestBase extends
PaimonSparkTestBase {
}
}
+ test("Data Evolution: compact table throws exception") {
+ withTable("t") {
+ sql(
+ "CREATE TABLE t (id INT, b INT) TBLPROPERTIES ('row-tracking.enabled'
= 'true', 'data-evolution.enabled' = 'true')")
+ for (i <- 1 to 6) {
+ sql(s"INSERT INTO t VALUES ($i, $i)")
+ }
+ assert(
+ intercept[RuntimeException] {
+ sql("CALL sys.compact(table => 't')")
+ }.getMessage
+ .contains("Compact operation is not supported when data evolution is
enabled yet."))
+ }
+ }
+
test("Data Evolution: delete table throws exception") {
withTable("t") {
sql(
