nsivabalan commented on a change in pull request #3873:
URL: https://github.com/apache/hudi/pull/3873#discussion_r744140634
##########
File path:
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/metadata/SparkHoodieBackedTableMetadataWriter.java
##########
@@ -145,15 +152,39 @@ protected void commit(List<HoodieRecord> records, String
partitionName, String i
*
* The record is tagged with respective file slice's location based on its
record key.
*/
- private JavaRDD<HoodieRecord> prepRecords(List<HoodieRecord> records, String
partitionName, int numFileGroups) {
+ private JavaRDD<HoodieRecord> prepRecords(JavaRDD<HoodieRecord> recordsRDD,
String partitionName, int numFileGroups) {
List<FileSlice> fileSlices =
HoodieTableMetadataUtil.loadPartitionFileGroupsWithLatestFileSlices(metadataMetaClient,
partitionName);
ValidationUtils.checkArgument(fileSlices.size() == numFileGroups,
String.format("Invalid number of file groups: found=%d, required=%d",
fileSlices.size(), numFileGroups));
- JavaSparkContext jsc = ((HoodieSparkEngineContext)
engineContext).getJavaSparkContext();
- return jsc.parallelize(records, 1).map(r -> {
+ return recordsRDD.map(r -> {
FileSlice slice =
fileSlices.get(HoodieTableMetadataUtil.mapRecordKeyToFileGroupIndex(r.getRecordKey(),
numFileGroups));
r.setCurrentLocation(new
HoodieRecordLocation(slice.getBaseInstantTime(), slice.getFileId()));
return r;
});
}
+
+ @Override
+ protected void commit(List<DirectoryInfo> partitionInfoList, String
createInstantTime) {
Review comment:
I can work on it. Once you are done with your changes, do let me know. I
can work on HoodieData abstractions and will update the patch. and then you can
review my changes
--
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]