deniskuzZ commented on code in PR #3746:
URL: https://github.com/apache/hive/pull/3746#discussion_r1032268630
##########
ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/CompactionQueryBuilder.java:
##########
@@ -287,16 +302,27 @@ private void buildAddClauseForAlter(StringBuilder query) {
private void buildSelectClauseForInsert(StringBuilder query) {
// Need list of columns for major crud, mmmajor partitioned, mmminor
List<FieldSchema> cols;
- if (major && crud || major && insertOnly && sourcePartition != null ||
minor && insertOnly) {
+ if (rebalance || major && crud || major && insertOnly && sourcePartition
!= null || minor && insertOnly) {
if (sourceTab == null) {
return; // avoid NPEs, don't throw an exception but skip this part of
the query
}
cols = sourceTab.getSd().getCols();
} else {
cols = null;
}
-
- if (crud) {
+ if (rebalance) {
+ query.append("0, t2.writeId, t2.rowId / CEIL(numRows / ");
+ query.append(numberOfBuckets);
+ query.append("), t2.rowId, t2.writeId, t2.data from (select ");
+ query.append("count(ROW__ID.writeId) over() as numRows, ROW__ID.writeId
as writeId, " +
+ "(row_number() OVER (order by ROW__ID.writeId ASC, ROW__ID.bucketId
ASC, ROW__ID.rowId ASC)) -1 AS rowId, " +
+ "NAMED_STRUCT(");
+ for (int i = 0; i < cols.size(); ++i) {
Review Comment:
should we check for null?
--
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]
