Skip to content

[common] Fix ClassCastException when computing row size for blob fields #9087

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
ArnavBalyan wants to merge 2 commits into
base: master
Choose a base branch
from
+70 −1
Open

[common] Fix ClassCastException when computing row size for blob fields #9087

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f8e1f0f
update
ArnavBalyan Aug 6, 2026
21745df
update
ArnavBalyan Aug 14, 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
23 changes: 22 additions & 1 deletion paimon-common/src/main/java/org/apache/paimon/types/InternalRowToSizeVisitor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand All @@ -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) {
Expand Down Expand Up @@ -229,11 +235,26 @@ public BiFunction<DataGetters, Integer, Integer> visit(BlobType blobType) {
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) -> {
Expand Down
48 changes: 48 additions & 0 deletions paimon-common/src/test/java/org/apache/paimon/types/InternalRowToSizeVisitorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand Down Expand Up @@ -192,4 +197,47 @@ void testCalculatorSize() {

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);
}
}
Loading