Skip to content

[9.0] Fix decoding of non-ascii field names in ignored source (#132018) #132034

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
merged 1 commit into from
Jul 28, 2025
Merged

[9.0] Fix decoding of non-ascii field names in ignored source (#132018) #132034

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
5 changes: 5 additions & 0 deletions docs/changelog/132018.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
pr: 132018
summary: Fix decoding of non-ascii field names in ignored source
area: Mapping
type: bug
issues: []
8 changes: 6 additions & 2 deletions server/src/main/java/org/elasticsearch/index/mapper/IgnoredSourceFieldMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,8 +181,12 @@ static NameValue decode(Object field) {
int encodedSize = ByteUtils.readIntLE(bytes, 0);
int nameSize = encodedSize % PARENT_OFFSET_IN_NAME_OFFSET;
int parentOffset = encodedSize / PARENT_OFFSET_IN_NAME_OFFSET;
String name = new String(bytes, 4, nameSize, StandardCharsets.UTF_8);
BytesRef value = new BytesRef(bytes, 4 + nameSize, bytes.length - nameSize - 4);

String decoded = new String(bytes, 4, bytes.length - 4, StandardCharsets.UTF_8);
String name = decoded.substring(0, nameSize);
int nameByteCount = name.getBytes(StandardCharsets.UTF_8).length;

BytesRef value = new BytesRef(bytes, 4 + nameByteCount, bytes.length - nameByteCount - 4);
return new NameValue(name, parentOffset, value, null);
}

Expand Down
11 changes: 11 additions & 0 deletions server/src/test/java/org/elasticsearch/index/mapper/IgnoredSourceFieldMapperTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,12 +10,14 @@
package org.elasticsearch.index.mapper;

import org.apache.lucene.index.DirectoryReader;
import org.elasticsearch.common.Strings;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.core.CheckedConsumer;
import org.elasticsearch.core.Nullable;
import org.elasticsearch.search.lookup.SourceFilter;
import org.elasticsearch.test.FieldMaskingReader;
import org.elasticsearch.xcontent.XContentBuilder;
import org.elasticsearch.xcontent.json.JsonXContent;
import org.hamcrest.Matchers;

import java.io.IOException;
Expand Down Expand Up @@ -122,6 +124,15 @@ public void testIgnoredString() throws IOException {
);
}

public void testIgnoredStringFullUnicode() throws IOException {
String value = randomUnicodeOfCodepointLengthBetween(5, 20);
String fieldName = randomUnicodeOfCodepointLength(5);

String expected = Strings.toString(JsonXContent.contentBuilder().startObject().field(fieldName, value).endObject());

assertEquals(expected, getSyntheticSourceWithFieldLimit(b -> b.field(fieldName, value)));
}

public void testIgnoredInt() throws IOException {
int value = randomInt();
assertEquals("{\"my_value\":" + value + "}", getSyntheticSourceWithFieldLimit(b -> b.field("my_value", value)));
Expand Down