the-other-tim-brown commented on code in PR #10578:
URL: https://github.com/apache/hudi/pull/10578#discussion_r1591737966
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/index/simple/HoodieSimpleIndex.java:
##########
@@ -143,19 +141,17 @@ protected <R> HoodieData<HoodieRecord<R>>
tagLocationInternal(
protected HoodiePairData<HoodieKey, HoodieRecordLocation>
fetchRecordLocationsForAffectedPartitions(
HoodieData<HoodieKey> hoodieKeys, HoodieEngineContext context,
HoodieTable hoodieTable,
int parallelism) {
- List<String> affectedPartitionPathList =
- hoodieKeys.map(HoodieKey::getPartitionPath).distinct().collectAsList();
- List<Pair<String, HoodieBaseFile>> latestBaseFiles =
+ HoodieData<String> affectedPartitionPathList =
+ hoodieKeys.map(HoodieKey::getPartitionPath).distinct();
+ HoodieData<Pair<String, HoodieBaseFile>> latestBaseFiles =
getLatestBaseFilesForAllPartitions(affectedPartitionPathList, context,
hoodieTable);
- return fetchRecordLocations(context, hoodieTable, parallelism,
latestBaseFiles);
+ return fetchRecordLocations(hoodieTable, parallelism, latestBaseFiles);
}
protected HoodiePairData<HoodieKey, HoodieRecordLocation>
fetchRecordLocations(
- HoodieEngineContext context, HoodieTable hoodieTable, int parallelism,
- List<Pair<String, HoodieBaseFile>> baseFiles) {
- int fetchParallelism = Math.max(1, Math.min(baseFiles.size(),
parallelism));
-
- return context.parallelize(baseFiles, fetchParallelism)
+ HoodieTable hoodieTable, int parallelism,
+ HoodieData<Pair<String, HoodieBaseFile>> baseFiles) {
+ return baseFiles.repartition(Math.max(1,
Math.min(baseFiles.getNumPartitions(), parallelism)))
Review Comment:
There is no coalesce option on HoodieData
--
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]