Skip to content

ESQL: Fix REVERSE with backspace character (#115245) #115263

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
nik9000 merged 1 commit into from
Oct 22, 2024
Merged

ESQL: Fix REVERSE with backspace character (#115245) #115263

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 8 additions & 0 deletions docs/changelog/115245.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
pr: 115245
summary: "ESQL: Fix `REVERSE` with backspace character"
area: ES|QL
type: bug
issues:
- 114372
- 115227
- 115228
13 changes: 6 additions & 7 deletions ...src/main/java/org/elasticsearch/xpack/esql/expression/function/scalar/string/Reverse.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,6 @@
import org.apache.lucene.util.BytesRef;
import org.elasticsearch.common.io.stream.NamedWriteableRegistry;
import org.elasticsearch.common.io.stream.StreamInput;
import org.elasticsearch.common.lucene.BytesRefs;
import org.elasticsearch.compute.ann.Evaluator;
import org.elasticsearch.compute.operator.EvalOperator.ExpressionEvaluator;
import org.elasticsearch.xpack.esql.core.expression.Expression;
Expand Down Expand Up @@ -79,8 +78,6 @@ protected TypeResolution resolveType() {

/**
* Reverses a unicode string, keeping grapheme clusters together
* @param str
* @return
*/
public static String reverseStringWithUnicodeCharacters(String str) {
BreakIterator boundary = BreakIterator.getCharacterInstance(Locale.ROOT);
Expand All @@ -100,10 +97,12 @@ public static String reverseStringWithUnicodeCharacters(String str) {
return reversed.toString();
}

private static boolean isOneByteUTF8(BytesRef ref) {
private static boolean reverseBytesIsReverseUnicode(BytesRef ref) {
int end = ref.offset + ref.length;
for (int i = ref.offset; i < end; i++) {
if (ref.bytes[i] < 0) {
if (ref.bytes[i] < 0 // Anything encoded in multibyte utf-8
|| ref.bytes[i] == 0x28 // Backspace
) {
return false;
}
}
Expand All @@ -112,13 +111,13 @@ private static boolean isOneByteUTF8(BytesRef ref) {

@Evaluator
static BytesRef process(BytesRef val) {
if (isOneByteUTF8(val)) {
if (reverseBytesIsReverseUnicode(val)) {
// this is the fast path. we know we can just reverse the bytes.
BytesRef reversed = BytesRef.deepCopyOf(val);
reverseArray(reversed.bytes, reversed.offset, reversed.length);
return reversed;
}
return BytesRefs.toBytesRef(reverseStringWithUnicodeCharacters(val.utf8ToString()));
return new BytesRef(reverseStringWithUnicodeCharacters(val.utf8ToString()));
}

@Override
Expand Down