vortual commented on code in PR #7795:
URL: https://github.com/apache/hudi/pull/7795#discussion_r1091705308
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/utils/Pipelines.java:
##########
@@ -139,10 +142,17 @@ public static DataStreamSink<Object>
bulkInsert(Configuration conf, RowType rowT
dataStream = dataStream.partitionCustom(partitioner,
rowDataKeyGen::getPartitionPath);
}
if (conf.getBoolean(FlinkOptions.WRITE_BULK_INSERT_SORT_INPUT)) {
- SortOperatorGen sortOperatorGen = new SortOperatorGen(rowType,
partitionFields);
- // sort by partition keys
+ String[] sortFields = partitionFields;
+ if
(conf.getBoolean(FlinkOptions.WRITE_BULK_INSERT_SORT_INPUT_BY_RECORD_KEY)) {
+ // sort by record keys
+ ArrayList<String> sortList = new
ArrayList<>(Arrays.asList(partitionFields));
+ Collections.addAll(sortList,
conf.getString(FlinkOptions.RECORD_KEY_FIELD).split(","));
+ sortFields = sortList.toArray(new String[0]);
+ }
+ SortOperatorGen sortOperatorGen = new SortOperatorGen(rowType,
sortFields);
+ // sort by partition keys or (partition keys and record keys)
dataStream = dataStream
- .transform("partition_key_sorter",
+ .transform("partition_and_record_key_sorter",
InternalTypeInfo.of(rowType),
sortOperatorGen.createSortOperator())
Review Comment:
Hello, I have modified the code, please help to see if there is anything
else to change @danny0405
--
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]
