HuangZhenQiu commented on code in PR #18040:
URL: https://github.com/apache/hudi/pull/18040#discussion_r2744677300
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/source/reader/HoodieRecordEmitter.java:
##########
@@ -18,19 +18,55 @@
package org.apache.hudi.source.reader;
+import org.apache.flink.api.common.eventtime.Watermark;
import org.apache.flink.api.connector.source.SourceOutput;
import org.apache.flink.connector.base.source.reader.RecordEmitter;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.util.ValidationUtils;
import org.apache.hudi.source.split.HoodieSourceSplit;
/**
* Default Hoodie record emitter.
- * @param <T>
+ *
+ * <p>This emitter handles watermark emission based on split information.
+ *
+ * @param <T> The type of records to emit
*/
public class HoodieRecordEmitter<T> implements
RecordEmitter<HoodieRecordWithPosition<T>, T, HoodieSourceSplit> {
+ private static final Logger LOG =
LoggerFactory.getLogger(HoodieRecordEmitter.class);
+ private HoodieSourceSplit lastSplit = null;
+ private long watermark = Long.MIN_VALUE;
@Override
public void emitRecord(HoodieRecordWithPosition<T> record, SourceOutput<T>
output, HoodieSourceSplit split) throws Exception {
+ if (lastSplit == null || !split.splitId().equals(lastSplit.splitId())) {
+ long newWatermark = extractWatermark(split);
+ if (newWatermark < watermark) {
+ LOG.info(
+ "Received a new split with lower watermark. Previous watermark =
{}, current watermark = {}, previous split = {}, current split = {}",
Review Comment:
In this case, all of the split discovered by the one time scan will emit the
same watermark, right? But there could be multiple commits before the lastest
commit are returned from scan. Thus, will not base instant time be more
accurate?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
