Skip to content

[FLINK-40051][pipeline-connector/hudi] Fix schema operator UID with operator UID prefix#4460

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
qiuyanjun888 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[FLINK-40051][pipeline-connector/hudi] Fix schema operator UID with operator UID prefix #4460

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
15 changes: 12 additions & 3 deletions ...tor-hudi/src/main/java/org/apache/flink/cdc/connectors/hudi/sink/HudiDataSinkFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ public class HudiDataSinkFactory implements DataSinkFactory {
private static final Logger LOG = LoggerFactory.getLogger(HudiDataSinkFactory.class);

public static final String IDENTIFIER = "hudi";
private static final String SCHEMA_OPERATOR_UID_SUFFIX = "schema-operator";

@Override
public String identifier() {
Expand Down Expand Up @@ -70,9 +71,7 @@ public HudiDataSink createDataSink(Context context) {
}
config.set(HudiConfig.INDEX_TYPE, HoodieIndex.IndexType.BUCKET.name());

String schemaOperatorUid =
context.getPipelineConfiguration()
.get(PipelineOptions.PIPELINE_SCHEMA_OPERATOR_UID);
String schemaOperatorUid = getSchemaOperatorUid(context.getPipelineConfiguration());

return new HudiDataSink(config, schemaOperatorUid);
}
Expand All @@ -91,4 +90,14 @@ public Set<ConfigOption<?>> optionalOptions() {
options.add(HudiConfig.INDEX_TYPE);
return options;
}

private static String getSchemaOperatorUid(Configuration pipelineConfig) {
if (pipelineConfig.contains(PipelineOptions.PIPELINE_OPERATOR_UID_PREFIX)) {
return String.format(
"%s-%s",
pipelineConfig.get(PipelineOptions.PIPELINE_OPERATOR_UID_PREFIX),
SCHEMA_OPERATOR_UID_SUFFIX);
}
return pipelineConfig.get(PipelineOptions.PIPELINE_SCHEMA_OPERATOR_UID);
}
}
38 changes: 38 additions & 0 deletions ...hudi/src/test/java/org/apache/flink/cdc/connectors/hudi/sink/HudiDataSinkFactoryTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,11 @@
import org.apache.flink.cdc.common.configuration.Configuration;
import org.apache.flink.cdc.common.factories.DataSinkFactory;
import org.apache.flink.cdc.common.factories.FactoryHelper;
import org.apache.flink.cdc.common.pipeline.PipelineOptions;
import org.apache.flink.cdc.common.sink.DataSink;
import org.apache.flink.cdc.common.sink.FlinkSinkProvider;
import org.apache.flink.cdc.composer.utils.FactoryDiscoveryUtils;
import org.apache.flink.cdc.connectors.hudi.sink.v2.HudiSink;
import org.apache.flink.table.api.ValidationException;

import org.apache.flink.shaded.guava31.com.google.common.collect.ImmutableMap;
Expand All @@ -31,6 +34,7 @@
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.io.TempDir;

import java.lang.reflect.Field;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
Expand Down Expand Up @@ -59,6 +63,34 @@ void testCreateDataSink() {
Assertions.assertThat(dataSink).isInstanceOf(HudiDataSink.class);
}

@Test
void testSchemaOperatorUidFollowsOperatorUidPrefix() throws Exception {
DataSinkFactory sinkFactory =
FactoryDiscoveryUtils.getFactoryByIdentifier("hudi", DataSinkFactory.class);
Assertions.assertThat(sinkFactory).isInstanceOf(HudiDataSinkFactory.class);

Configuration sinkConfig =
Configuration.fromMap(
ImmutableMap.<String, String>builder()
.put(HudiConfig.PATH.key(), temporaryFolder.toString())
.build());
Configuration pipelineConfig = new Configuration();
pipelineConfig.set(
PipelineOptions.PIPELINE_OPERATOR_UID_PREFIX, "mysql_hudi_user_behavior");

DataSink dataSink =
sinkFactory.createDataSink(
new FactoryHelper.DefaultContext(
sinkConfig,
pipelineConfig,
Thread.currentThread().getContextClassLoader()));
FlinkSinkProvider sinkProvider = (FlinkSinkProvider) dataSink.getEventSinkProvider();
HudiSink hudiSink = (HudiSink) sinkProvider.getSink();

Assertions.assertThat(getSchemaOperatorUid(hudiSink))
.isEqualTo("mysql_hudi_user_behavior-schema-operator");
}

@Test
void testLackRequireOption() {
DataSinkFactory sinkFactory =
Expand Down Expand Up @@ -141,4 +173,10 @@ void testPrefixRequireOption() {
conf, conf, Thread.currentThread().getContextClassLoader()));
Assertions.assertThat(dataSink).isInstanceOf(HudiDataSink.class);
}

private static String getSchemaOperatorUid(HudiSink hudiSink) throws Exception {
Field field = HudiSink.class.getDeclaredField("schemaOperatorUid");
field.setAccessible(true);
return (String) field.get(hudiSink);
}
}