codope commented on code in PR #9273:
URL: https://github.com/apache/hudi/pull/9273#discussion_r1280703805
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala:
##########
@@ -342,6 +342,20 @@ object HoodieFileIndex extends Logging {
if (listingModeOverride != null) {
properties.setProperty(DataSourceReadOptions.FILE_INDEX_LISTING_MODE_OVERRIDE.key,
listingModeOverride)
}
+ val tableConfig = metaClient.getTableConfig
+ val partitionColumns = tableConfig.getPartitionFields
+ if (partitionColumns.isPresent) {
+ val keyGeneratorClassName = tableConfig.getKeyGeneratorClassName
+ // NOTE: A custom key generator with multiple fields could have
non-encoded slashes in the partition columns'
+ // value. We might not be able to properly parse partition-values
from the listed partition-paths. Fallback
+ // to eager listing in this case.
+ val isCustomKeyGenerator =
(classOf[CustomKeyGenerator].getName.equalsIgnoreCase(keyGeneratorClassName)
+ ||
classOf[CustomAvroKeyGenerator].getName.equalsIgnoreCase(keyGeneratorClassName))
+ val hasMultiplePartitionFields = partitionColumns.get().length > 1
+ if (hasMultiplePartitionFields && isCustomKeyGenerator) {
+
properties.setProperty(DataSourceReadOptions.FILE_INDEX_LISTING_MODE_OVERRIDE.key,
DataSourceReadOptions.FILE_INDEX_LISTING_MODE_EAGER)
+ }
+ }
Review Comment:
makes sense. i've changeed the code accordingly.
--
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: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
