the-other-tim-brown commented on code in PR #13261:
URL: https://github.com/apache/hudi/pull/13261#discussion_r2094127283
##########
hudi-utilities/src/main/java/org/apache/hudi/utilities/streamer/StreamSync.java:
##########
@@ -950,22 +940,23 @@ private String startCommit(String instantTime, boolean
retryEnabled) {
// No-Op
}
}
- instantTime = writeClient.createNewInstantTime();
}
throw lastException;
}
private WriteClientWriteResult writeToSink(InputBatch inputBatch, String
instantTime, boolean useRowWriter) {
WriteClientWriteResult writeClientWriteResult = null;
- instantTime = startCommit(instantTime, !autoGenerateRecordKeys);
if (useRowWriter) {
Dataset<Row> df = (Dataset<Row>) inputBatch.getBatch().orElseGet(() ->
hoodieSparkContext.getSqlContext().emptyDataFrame());
HoodieWriteConfig hoodieWriteConfig =
prepareHoodieConfigForRowWriter(inputBatch.getSchemaProvider().getTargetSchema());
- BaseDatasetBulkInsertCommitActionExecutor executor = new
HoodieStreamerDatasetBulkInsertCommitActionExecutor(hoodieWriteConfig,
writeClient, instantTime);
+ BaseDatasetBulkInsertCommitActionExecutor executor = new
HoodieStreamerDatasetBulkInsertCommitActionExecutor(hoodieWriteConfig,
writeClient);
writeClientWriteResult = new WriteClientWriteResult(executor.execute(df,
!HoodieStreamerUtils.getPartitionColumns(props).isEmpty()).getWriteStatuses());
} else {
- JavaRDD<HoodieRecord> records = (JavaRDD<HoodieRecord>)
inputBatch.getBatch().orElseGet(() -> hoodieSparkContext.emptyRDD());
+ HoodieRecordType recordType = createRecordMerger(props).getRecordType();
+ Option<JavaRDD<HoodieRecord>> recordsOption =
HoodieStreamerUtils.createHoodieRecords(cfg, props, inputBatch.getBatch(),
schemaProvider,
Review Comment:
Yes, you're right. The old code has a local variable `schemaProvider` that
is set to the `inputBatch.getSchemaProvider()`
--
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]