lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-3838] Moved the getPartitionColumns logic to driver. (#5303)

Browse Source
This commit is contained in:
Vinoth Govindarajan
2022-04-12 15:03:00 -07:00
committed by GitHub
parent 25dce94ba2
commit 2d46d5287e
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
hudi-utilities/src/main/java/org/apache/hudi/utilities/deltastreamer/DeltaSync.java
View File

@@ -480,9 +480,10 @@ public class DeltaSync implements Serializable {
}
boolean shouldCombine = cfg.filterDupes || cfg.operation.equals(WriteOperationType.UPSERT);
List<String> partitionColumns = getPartitionColumns(keyGenerator, props);
JavaRDD<GenericRecord> avroRDD = avroRDDOptional.get();
JavaRDD<HoodieRecord> records = avroRDD.map(record -> {
GenericRecord gr = isDropPartitionColumns() ? HoodieAvroUtils.removeFields(record, getPartitionColumns(keyGenerator, props)) : record;
GenericRecord gr = isDropPartitionColumns() ? HoodieAvroUtils.removeFields(record, partitionColumns) : record;
HoodieRecordPayload payload = shouldCombine ? DataSourceUtils.createPayload(cfg.payloadClassName, gr,
(Comparable) HoodieAvroUtils.getNestedFieldVal(gr, cfg.sourceOrderingField, false, props.getBoolean(
KeyGeneratorOptions.KEYGENERATOR_CONSISTENT_LOGICAL_TIMESTAMP_ENABLED.key(),