yihua commented on code in PR #10957:
URL: https://github.com/apache/hudi/pull/10957#discussion_r1628612267
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieHadoopFsRelationFactory.scala:
##########
@@ -161,15 +167,14 @@ abstract class HoodieBaseHadoopFsRelationFactory(val
sqlContext: SQLContext,
val shouldExtractPartitionValueFromPath =
optParams.getOrElse(DataSourceReadOptions.EXTRACT_PARTITION_VALUES_FROM_PARTITION_PATH.key,
DataSourceReadOptions.EXTRACT_PARTITION_VALUES_FROM_PARTITION_PATH.defaultValue.toString).toBoolean
- val shouldUseBootstrapFastRead =
optParams.getOrElse(DATA_QUERIES_ONLY.key(), "false").toBoolean
-
- shouldOmitPartitionColumns || shouldExtractPartitionValueFromPath ||
shouldUseBootstrapFastRead
+ shouldOmitPartitionColumns || shouldExtractPartitionValueFromPath
}
protected lazy val mandatoryFieldsForMerging: Seq[String] =
Seq(recordKeyField) ++ preCombineFieldOpt.map(Seq(_)).getOrElse(Seq())
- protected lazy val shouldUseRecordPosition: Boolean =
checkIfAConfigurationEnabled(HoodieReaderConfig.MERGE_USE_RECORD_POSITIONS)
+ //feature added in spark 3.5
+ protected lazy val shouldUseRecordPosition: Boolean =
checkIfAConfigurationEnabled(HoodieReaderConfig.MERGE_USE_RECORD_POSITIONS) &&
HoodieSparkUtils.gteqSpark3_5
Review Comment:
We can still merge deletes and updates based on record positions encoded in
the log block headers, correct?
--
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]
