This is an automated email from the ASF dual-hosted git repository.
JingsongLi 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 5f57f60cc3 [common] Fix ClassCastException when computing row size for
blob fields (#9087)
5f57f60cc3 is described below
commit 5f57f60cc386a168ea6efead17bd0206388c297b
Author: Arnav Balyan <[email protected]>
AuthorDate: Mon Aug 17 11:02:33 2026 +0530
[common] Fix ClassCastException when computing row size for blob fields
(#9087)
---
.../paimon/types/InternalRowToSizeVisitor.java | 23 ++++++++++-
.../paimon/types/InternalRowToSizeVisitorTest.java | 48 ++++++++++++++++++++++
2 files changed, 70 insertions(+), 1 deletion(-)
diff --git
a/paimon-common/src/main/java/org/apache/paimon/types/InternalRowToSizeVisitor.java
b/paimon-common/src/main/java/org/apache/paimon/types/InternalRowToSizeVisitor.java
index 8487100c8f..9cd4c4cd21 100644
---
a/paimon-common/src/main/java/org/apache/paimon/types/InternalRowToSizeVisitor.java
+++
b/paimon-common/src/main/java/org/apache/paimon/types/InternalRowToSizeVisitor.java
@@ -18,6 +18,11 @@
package org.apache.paimon.types;
+import org.apache.paimon.data.Blob;
+import org.apache.paimon.data.BlobData;
+import org.apache.paimon.data.BlobDescriptor;
+import org.apache.paimon.data.BlobRef;
+import org.apache.paimon.data.BlobView;
import org.apache.paimon.data.DataGetters;
import org.apache.paimon.data.InternalArray;
import org.apache.paimon.data.InternalMap;
@@ -32,6 +37,7 @@ public class InternalRowToSizeVisitor
implements DataTypeVisitor<BiFunction<DataGetters, Integer, Integer>> {
public static final int NULL_SIZE = 0;
+ private static final int UNKNOWN_SIZE = 1;
@Override
public BiFunction<DataGetters, Integer, Integer> visit(CharType charType) {
@@ -243,11 +249,26 @@ public class InternalRowToSizeVisitor
if (row.isNullAt(index)) {
return NULL_SIZE;
} else {
- return Math.toIntExact(row.getVariant(index).sizeInBytes());
+ Blob blob = row.getBlob(index);
+ if (blob instanceof BlobData) {
+ return ((BlobData) blob).toData().length;
+ } else if (blob instanceof BlobRef) {
+ return descriptorLength(blob.toDescriptor());
+ } else if (blob instanceof BlobView) {
+ BlobView view = (BlobView) blob;
+ return view.isResolved()
+ ? descriptorLength(view.toDescriptor())
+ : view.viewStruct().serialize().length;
+ }
+ return UNKNOWN_SIZE;
}
};
}
+ private static int descriptorLength(BlobDescriptor descriptor) {
+ return descriptor.length() < 0 ? UNKNOWN_SIZE :
Math.toIntExact(descriptor.length());
+ }
+
@Override
public BiFunction<DataGetters, Integer, Integer> visit(ArrayType
arrayType) {
return (row, index) -> {
diff --git
a/paimon-common/src/test/java/org/apache/paimon/types/InternalRowToSizeVisitorTest.java
b/paimon-common/src/test/java/org/apache/paimon/types/InternalRowToSizeVisitorTest.java
index cfdae649c1..15c198774c 100644
---
a/paimon-common/src/test/java/org/apache/paimon/types/InternalRowToSizeVisitorTest.java
+++
b/paimon-common/src/test/java/org/apache/paimon/types/InternalRowToSizeVisitorTest.java
@@ -18,13 +18,18 @@
package org.apache.paimon.types;
+import org.apache.paimon.catalog.Identifier;
import org.apache.paimon.data.BinaryString;
+import org.apache.paimon.data.Blob;
+import org.apache.paimon.data.BlobDescriptor;
+import org.apache.paimon.data.BlobViewStruct;
import org.apache.paimon.data.DataGetters;
import org.apache.paimon.data.Decimal;
import org.apache.paimon.data.GenericArray;
import org.apache.paimon.data.GenericMap;
import org.apache.paimon.data.GenericRow;
import org.apache.paimon.data.Timestamp;
+import org.apache.paimon.utils.UriReader;
import org.assertj.core.api.Assertions;
import org.junit.jupiter.api.BeforeEach;
@@ -192,4 +197,47 @@ public class InternalRowToSizeVisitorTest {
Assertions.assertThat(feildSizeCalculator.get(23).apply(row,
23)).isEqualTo(0);
}
+
+ @Test
+ void testBlobSize() {
+ Assertions.assertThat(blobSize(Blob.fromData(new byte[] {1, 2,
3}))).isEqualTo(3);
+ Assertions.assertThat(blobSize(null)).isEqualTo(0);
+ }
+
+ @Test
+ void testBlobRefSize() {
+ Assertions.assertThat(
+ blobSize(
+ Blob.fromDescriptor(
+ UriReader.fromHttp(),
+ new
BlobDescriptor("https://example.com/blob";, 0, 3))))
+ .isEqualTo(3);
+
Assertions.assertThat(blobSize(Blob.fromHttp("https://example.com/blob";))).isEqualTo(1);
+ }
+
+ @Test
+ void testUnresolvedBlobViewSize() {
+ BlobViewStruct viewStruct = new BlobViewStruct(Identifier.create("db",
"t"), 1, 2L);
+ Assertions.assertThat(blobSize(Blob.fromView(viewStruct)))
+ .isEqualTo(viewStruct.serialize().length);
+ }
+
+ @Test
+ void testBlobStreamSize() {
+ Assertions.assertThat(
+ blobSize(
+ Blob.fromInputStream(
+ () -> {
+ throw new AssertionError();
+ })))
+ .isEqualTo(1);
+ }
+
+ private int blobSize(Blob blob) {
+ RowType rowType = RowType.builder().field("b",
DataTypes.BLOB()).build();
+ InternalRowToSizeVisitor visitor = new InternalRowToSizeVisitor();
+ BiFunction<DataGetters, Integer, Integer> calculator =
+ rowType.getFieldTypes().get(0).accept(visitor);
+ return calculator.apply(GenericRow.of(blob), 0);
+ }
}
