Skip to content

[core] Fix incorrect substring result for unicode characters #9328

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
+14 −5
Open

[core] Fix incorrect substring result for unicode characters #9328

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
862eb97
update
ArnavBalyan Aug 20, 2026
3f80965
update
ArnavBalyan Aug 21, 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
10 changes: 5 additions & 5 deletions paimon-common/src/main/java/org/apache/paimon/predicate/SubstringTransform.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,21 +75,21 @@ public final Object transform(InternalRow row) {
return null;
}

String sourceJavaString = sourceString.toString();
int sourceLength = sourceString.numChars();
int beginIndex = readPosition(inputs.get(1), row);
if (beginIndex > sourceJavaString.length()) {
if (beginIndex > sourceLength) {
return BinaryString.EMPTY_UTF8;
}

int endIndex = sourceJavaString.length();
int endIndex = sourceLength;
if (hasLength) {
endIndex = beginIndex + readPosition(inputs.get(2), row) - 1;
}
endIndex = Math.min(endIndex, sourceJavaString.length());
endIndex = Math.min(endIndex, sourceLength);
beginIndex--;
checkArgument(beginIndex < endIndex);

return BinaryString.fromString(sourceJavaString.substring(beginIndex, endIndex));
return sourceString.substring(beginIndex, endIndex);
}

private static boolean isNullPosition(Object position, InternalRow row) {
Expand Down
9 changes: 9 additions & 0 deletions paimon-common/src/test/java/org/apache/paimon/predicate/SubstringTransformTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
import org.junit.jupiter.api.Test;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

import static org.assertj.core.api.Assertions.assertThat;
Expand Down Expand Up @@ -82,6 +83,14 @@ public void testNormalInputs() {
assertThat(result).isEqualTo(BinaryString.fromString(""));
}

@Test
public void testSubstringWithSupplementaryCharacter() {
SubstringTransform transform =
new SubstringTransform(Arrays.asList(BinaryString.fromString("A😀B"), 2, 1));

assertThat(transform.transform(GenericRow.of())).isEqualTo(BinaryString.fromString("😀"));
}

@Test
public void testSubstringRefInputs() {
List<Object> inputs = new ArrayList<>();
Expand Down
Loading