flyrain commented on a change in pull request #3287:
URL: https://github.com/apache/iceberg/pull/3287#discussion_r731221444



##########
File path: 
spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnarBatchReader.java
##########
@@ -47,18 +57,58 @@ public final ColumnarBatch read(ColumnarBatch reuse, int 
numRowsToRead) {
       closeVectors();
     }
 
+    Map<Integer, 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 {
+        arrowColumnVectors[i] = 
ColumnVectorWithFilter.forHolder(vectorHolders[i], rowIdMapping, 
numRowsInVector);
+      }
     }
+
+    rowStartPos += numRowsToRead;
     ColumnarBatch batch = new ColumnarBatch(arrowColumnVectors);
-    batch.setNumRows(numRowsToRead);
+
+    if (rowIdMapping == null) {
+      batch.setNumRows(numRowsToRead);
+    } else {
+      batch.setNumRows(rowIdMapping.size());
+    }
     return batch;
   }
+
+  private Map<Integer, Integer> rowIdMapping(int numRows) {
+    if (deletes != null && deletes.hasPosDeletes()) {
+      Set<Long> deletedRows = deletes.posDeletedRowIds();
+      if (deletedRows != null) {
+        Set<Integer> deletedRowIds = Sets.newHashSet();
+        deletedRows.stream().forEach(x -> deletedRowIds.add((int) (x - 
rowStartPos)));

Review comment:
       Will remove this part in the next commit.




-- 
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]

Reply via email to