jonvex commented on code in PR #8303:
URL: https://github.com/apache/hudi/pull/8303#discussion_r1164683803
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DefaultSource.scala:
##########
@@ -270,6 +271,21 @@ object DefaultSource {
}
}
+ private def resolveHoodieBootstrapRelation(sqlContext: SQLContext,
+ globPaths: Seq[Path],
+ userSchema: Option[StructType],
+ metaClient: HoodieTableMetaClient,
+ parameters: Map[String, String]):
BaseRelation = {
+ val enableFileIndex = HoodieSparkConfUtils.getConfigValue(parameters,
sqlContext.sparkSession.sessionState.conf,
+ ENABLE_HOODIE_FILE_INDEX.key,
ENABLE_HOODIE_FILE_INDEX.defaultValue.toString).toBoolean
+ if (!enableFileIndex || globPaths.nonEmpty ||
parameters.getOrElse(HoodieBootstrapConfig.DATA_QUERIES_ONLY.key(), "true") !=
"true") {
Review Comment:
Spark applies special optimizations to HadoopFsRelation so unless we
contribute PRs to spark, this is the only way to do it as far as I can tell
--
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]
