jonvex commented on code in PR #8875:
URL: https://github.com/apache/hudi/pull/8875#discussion_r1218288972
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/hudi/ProvidesHoodieConfig.scala:
##########
@@ -89,6 +89,62 @@ trait ProvidesHoodieConfig extends Logging {
defaultOpts = defaultOpts, overridingOpts = overridingOpts)
}
+ /**
+ * Get the insert operation.
+ * See if we are able to set bulk insert, else use deduceOperation
+ */
+ private def getOperation(isPartitionedTable: Boolean,
+ isOverwritePartition: Boolean,
+ isOverwriteTable: Boolean,
+ insertModeSet: Boolean,
+ dropDuplicate: Option[String],
+ enableBulkInsert: Option[String],
+ isInsertInto: Boolean,
+ isNonStrictMode: Boolean,
+ hasPrecombineColumn: Boolean): String = {
+ val notSetToNonStrict = !insertModeSet || isNonStrictMode
+ //if options are not set, we assume they are configs to do bulk insert
+ (isInsertInto, notSetToNonStrict, enableBulkInsert.getOrElse("true"),
+ dropDuplicate.getOrElse("false"), isOverwritePartition,
isPartitionedTable) match {
+ case (true, true, "true", "false", false, _) =>
BULK_INSERT_OPERATION_OPT_VAL
+ case (true, true, "true", "false", true, false) =>
BULK_INSERT_OPERATION_OPT_VAL
+
+ //if config is set such that we cant make it bulk insert, we need to use
defaults for unset configs
+ case _ =>
deduceOperation(enableBulkInsert.getOrElse(SQL_ENABLE_BULK_INSERT.defaultValue).toBoolean,
+ isOverwritePartition, isOverwriteTable,
dropDuplicate.getOrElse(INSERT_DROP_DUPS.defaultValue).toBoolean,
+ isNonStrictMode, isPartitionedTable, hasPrecombineColumn)
+ }
+ }
+
+ /**
+ * Deduce the insert operation
+ */
+ private def deduceOperation(enableBulkInsert: Boolean, isOverwritePartition:
Boolean, isOverwriteTable: Boolean,
+ dropDuplicate: Boolean, isNonStrictMode:
Boolean, isPartitionedTable: Boolean,
+ hasPrecombineColumn: Boolean): String = {
+ (enableBulkInsert, isOverwritePartition, isOverwriteTable, dropDuplicate,
isNonStrictMode, isPartitionedTable) match {
Review Comment:
No 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]
