minihippo commented on a change in pull request #3173:
URL: https://github.com/apache/hudi/pull/3173#discussion_r769785613
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/MergeOnReadSnapshotRelation.scala
##########
@@ -219,17 +226,31 @@ class MergeOnReadSnapshotRelation(val sqlContext:
SQLContext,
} else {
Option.empty
}
-
val logPaths =
fileSlice.getLogFiles.sorted(HoodieLogFile.getLogFileComparator).iterator().asScala
.map(logFile =>
MergeOnReadSnapshotRelation.getFilePath(logFile.getPath)).toList
val logPathsOptional = if (logPaths.isEmpty) Option.empty else
Option(logPaths)
- HoodieMergeOnReadFileSplit(partitionedFile, logPathsOptional,
queryInstant, metaClient.getBasePath,
- maxCompactionMemoryInBytes, mergeType)
+ (fileSlice.getBaseFile, HoodieMergeOnReadFileSplit(partitionedFile,
logPathsOptional, queryInstant, metaClient.getBasePath,
+ maxCompactionMemoryInBytes, mergeType))
}).toList
- fileSplits
+ groupFilesWithBucket(fileSplits)
}
}
}
+
+ private def groupFilesWithBucket(
Review comment:
This is a read optimizer. I revert this changes and will create another
pr to cover the query optimizer part.
--
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]
