aokolnychyi commented on a change in pull request #3287:
URL: https://github.com/apache/iceberg/pull/3287#discussion_r736703380
##########
File path:
spark/v3.0/spark3/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnarBatchReader.java
##########
@@ -47,18 +68,71 @@ public final ColumnarBatch read(ColumnarBatch reuse, int
numRowsToRead) {
closeVectors();
}
+ Pair<int[], Integer> rowIdMapping = rowIdMapping(numRowsToRead);
+
for (int i = 0; i < readers.length; i += 1) {
vectorHolders[i] = readers[i].read(vectorHolders[i], numRowsToRead);
int numRowsInVector = vectorHolders[i].numValues();
Preconditions.checkState(
numRowsInVector == numRowsToRead,
"Number of rows in the vector %s didn't match expected %s ",
numRowsInVector,
numRowsToRead);
- arrowColumnVectors[i] =
- IcebergArrowColumnVector.forHolder(vectorHolders[i],
numRowsInVector);
+
+ if (rowIdMapping == null) {
+ arrowColumnVectors[i] =
IcebergArrowColumnVector.forHolder(vectorHolders[i], numRowsInVector);
+ } else {
+ int[] rowIdMap = rowIdMapping.first();
+ Integer numRows = rowIdMapping.second();
+ arrowColumnVectors[i] =
ColumnVectorWithFilter.forHolder(vectorHolders[i], rowIdMap, numRows);
+ }
}
+
+ rowStartPosInBatch += numRowsToRead;
ColumnarBatch batch = new ColumnarBatch(arrowColumnVectors);
- batch.setNumRows(numRowsToRead);
+
+ if (rowIdMapping == null) {
+ batch.setNumRows(numRowsToRead);
+ } else {
+ Integer numRows = rowIdMapping.second();
+ batch.setNumRows(numRows);
+ }
return batch;
}
+
+ private Pair<int[], Integer> rowIdMapping(int numRows) {
+ if (deletes != null && deletes.hasPosDeletes()) {
+ return buildRowIdMapping(deletes.deletedRowPositions(), numRows);
+ } else {
+ return null;
+ }
+ }
+
+ /**
Review comment:
Thanks for doc!
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
