Skip to content

[9.1] Disable utf-8 parsing optimization #135180

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 2 commits into from
Sep 22, 2025
Merged

[9.1] Disable utf-8 parsing optimization #135180

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
fe6aa70
Disable utf-8 parsing optimization (#135172)
martijnvg Sep 22, 2025
214ceb9
fix test compile errors
martijnvg Sep 22, 2025
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: 1 addition & 9 deletions ...ntent/impl/src/main/java/org/elasticsearch/xcontent/provider/json/JsonXContentParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,15 +143,7 @@ public String text() throws IOException {

@Override
public XContentString optimizedText() throws IOException {
if (currentToken().isValue() == false) {
throwOnNoText();
}
if (parser instanceof ESUTF8StreamJsonParser esParser) {
var bytesRef = esParser.getValueAsText();
if (bytesRef != null) {
return bytesRef;
}
}
// TODO: enable utf-8 parsing optimization once verified it is completely safe
return new Text(text());
}

Expand Down
23 changes: 23 additions & 0 deletions server/src/test/java/org/elasticsearch/common/xcontent/json/JsonXContentTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,10 @@

package org.elasticsearch.common.xcontent.json;

import org.elasticsearch.common.bytes.BytesReference;
import org.elasticsearch.common.xcontent.BaseXContentTestCase;
import org.elasticsearch.xcontent.Text;
import org.elasticsearch.xcontent.XContentBuilder;
import org.elasticsearch.xcontent.XContentGenerator;
import org.elasticsearch.xcontent.XContentParseException;
import org.elasticsearch.xcontent.XContentParser;
Expand All @@ -18,6 +21,9 @@
import org.elasticsearch.xcontent.json.JsonXContent;

import java.io.ByteArrayOutputStream;
import java.util.Set;

import static org.hamcrest.Matchers.equalTo;

public class JsonXContentTests extends BaseXContentTestCase {

Expand All @@ -41,4 +47,21 @@ public void testMalformedJsonFieldThrowsXContentException() throws Exception {
assertThrows(XContentParseException.class, () -> parser.text());
}
}

public void testOptimizedTextHasBytes() throws Exception {
XContentBuilder builder = builder().startObject().field("text", new Text("foo")).endObject();
XContentParserConfiguration parserConfig = parserConfig();
if (randomBoolean()) {
parserConfig = parserConfig.withFiltering(null, Set.of("*"), null, true);
}
try (XContentParser parser = createParser(parserConfig, xcontentType().xContent(), BytesReference.bytes(builder))) {
assertSame(XContentParser.Token.START_OBJECT, parser.nextToken());
assertSame(XContentParser.Token.FIELD_NAME, parser.nextToken());
assertTrue(parser.nextToken().isValue());
Text text = (Text) parser.optimizedText();
// TODO: uncomment after utf8 optimized parsing has been enabled again:
// assertTrue(text.hasBytes());
assertThat(text.string(), equalTo("foo"));
}
}
}