danny0405 commented on code in PR #11727:
URL: https://github.com/apache/hudi/pull/11727#discussion_r1779312050
##########
hudi-flink-datasource/hudi-flink1.18.x/src/main/java/org/apache/hudi/table/format/cow/ParquetSplitReaderUtil.java:
##########
@@ -546,15 +615,30 @@ private static WritableColumnVector
createWritableColumnVector(
// schema evolution: read the file with a new extended field name.
int fieldIndex =
getFieldIndexInPhysicalType(rowType.getFields().get(i).getName(), groupType);
if (fieldIndex < 0) {
- columnVectors[i] = (WritableColumnVector)
createVectorFromConstant(rowType.getTypeAt(i), null, batchSize);
+ if (groupType.getRepetition().equals(Type.Repetition.REPEATED) &&
!rowType.getTypeAt(i).is(LogicalTypeRoot.ARRAY)) {
+ columnVectors[i] = (WritableColumnVector)
createVectorFromConstant(
+ new ArrayType(rowType.getTypeAt(i).isNullable(),
rowType.getTypeAt(i)), null, batchSize);
+ } else {
+ columnVectors[i] = (WritableColumnVector)
createVectorFromConstant(rowType.getTypeAt(i), null, batchSize);
+ }
} else {
- columnVectors[i] =
- createWritableColumnVector(
- batchSize,
- rowType.getTypeAt(i),
- groupType.getType(fieldIndex),
- descriptors,
- depth + 1);
+ if (descriptors.get(fieldIndex).getMaxRepetitionLevel() > 0 &&
!rowType.getTypeAt(i).is(LogicalTypeRoot.ARRAY)) {
+ columnVectors[i] =
+ createWritableColumnVector(
+ batchSize,
+ new ArrayType(rowType.getTypeAt(i).isNullable(),
rowType.getTypeAt(i)),
Review Comment:
Can you explain why we use array logical type here if the row field type is
not array?
--
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]
