HuangZhenQiu commented on code in PR #19844:
URL: https://github.com/apache/hudi/pull/19844#discussion_r3946925955
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/utils/Pipelines.java:
##########
@@ -410,11 +410,22 @@ public static DataStream<HoodieFlinkInternalRow>
bootstrap(
boolean overwrite) {
final boolean globalIndex = conf.get(FlinkOptions.INDEX_GLOBAL_ENABLED);
if (overwrite || OptionsResolver.isBucketIndexType(conf)) {
+ // overwrite and bucket index do not rely on a bootstrapped key index.
return rowDataToHoodieRecord(conf, rowType, dataStream);
}
- if (bounded && !globalIndex && OptionsResolver.isPartitionedTable(conf)) {
+ boolean isRLI = OptionsResolver.isGlobalRecordLevelIndex(conf) ||
OptionsResolver.isRecordLevelIndex(conf);
+ if (bounded && isRLI && !conf.get(FlinkOptions.INDEX_BOOTSTRAP_ENABLED)) {
+ // RLI bucket assignment (global or partitioned) looks up the record
index directly,
+ // so the generic bootstrap step can be skipped unless it is explicitly
requested.
+ return rowDataToHoodieRecord(conf, rowType, dataStream);
+ }
+ if (bounded && !globalIndex && !isRLI &&
OptionsResolver.isPartitionedTable(conf)) {
+ // non-RLI partitioned tables shuffle by partition path and bootstrap
per-partition
+ // during batch execution to support batch UPSERT.
return boundedBootstrap(conf, rowType, dataStream);
}
+ // streaming execution, or bounded execution for a
non-partitioned/global-index/RLI-with-
Review Comment:
The logic will be handled by this PR It will be handled by this PR
https://github.com/apache/hudi/pull/19837.
--
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]
